jiayaoqijia
- 3.9k skills
- 0 followers
- 81 repo stars
- 3 days ago last updated
- ▌ Ac Direct Real Estate · jiayaoqijia bundleAnalysing direct property as an asset rather than through a fund: net operating income and its stability, lease structure and tenant credit, capitalisation rates and what they assume, valuation methods and the appraisal they rest on, capital expenditure and its deferred component, financing and covenants at the property level, and the written property record. It explains the income and valuation arithmetic; it never recommends a property and never predicts prices. Use when asking "net operating income", "NOI", "cap rate", "lease structure", "triple net", "tenant credit", "property valuation", "appraisal", "deferred maintenance", "property level debt", "direct real estate". Not for real-estate vehicles and funds (ac-alternatives-and-real-assets), not for REIT equity analysis (ac-equity-research), not for mortgage-backed securities (ac-securitisation-and-tranches).
- ▌ Trading Start · jiayaoqijia bundleStart here for anything trading - routes a goal (find trades, read news and results, track insiders, analyse a chart, time an entry, plan, size, backtest, place orders, set alerts, review performance) to the right trading-skills, runs the end-to-end idea-to-trade workflow, and produces a daily trading brief combining market regime, risk status, open positions versus stops, a watchlist screen and live chart patterns, designed for scheduled pre-market and end-of-day runs. Use when the user asks "how do I use these trading skills", "what should I do today", for a morning or daily brief, a trading routine, or automation of their trading workflow.
- ▌ Ac Backtest Integrity · jiayaoqijia bundleAuditing whether a trading backtest can be believed: multiple-testing deflation, look-ahead and survivorship leakage, sample and regime adequacy, execution-cost honesty, placebo and null tests, pre-registration, and the decision rule that kills a strategy. Audits evidence; never recommends a strategy. Use when asking "is this backtest real", "validate my strategy", "deflated Sharpe", "look-ahead bias", "pre-register a study". Not for data collection (ac-market-data-collection), forensics (ac-cascade-forensics), or the trade record (ac-crypto-trading-discipline).
- ▌ Trading Entry · jiayaoqijia bundleEntry timer for intraday setups in any market - watches bar by bar and says the moment a setup triggers, waiting (and how far), still forming, expired or market closed. Opening-range breakout (first 15 minutes by default) or a break of any level you give, long or short, on 1, 2, 5 or 15-minute bars, with an optional volume check and a no-entries-near-the-close cutoff. Reads each exchange's session from the data (NSE 09:15, NYSE 09:30, LSE 08:00...), replays past sessions for practice, and hands the trigger to trading-plan with stop ideas. Never places an order. Use when the user says "tell me when to get in", "watch RELIANCE", "has it broken out", "did it break the opening range", "time my entry", "ORB", "check my watchlist for breakouts", or after a scan finds a setup.
- ▌ Trading Setup · jiayaoqijia bundleConfigure the trading-skills toolkit - account size, currency, benchmark index, risk limits, data provider (free Yahoo, CSV, or broker), broker (paper or a live broker adapter), credentials and the live-trading switch. Use when the user is getting started, says "set up trading", wants to change risk per trade or limits, connect or log in to a broker, reset the paper account, or when another trading skill reports missing config.
- ▌ Ac Technical Writing · jiayaoqijia bundleProduct and process documentation: the docs set — README, tutorial, how-to, explanation, reference — procedures, SOPs, runbooks and KB articles, release notes, and the in-product strings users meet: button labels, error messages, empty states. Use when asking "write a README", "tutorial or how-to", "structure the docs", "write a procedure", "SOP", "runbook", "KB article", "release notes", "write this error message", "button label", "empty state". Not for designing the interface itself or laying the strings into a component; that work sits outside this skill.
- ▌ Ac Test Environments · jiayaoqijia bundleEnvironments where tests run beyond the developer's machine: local parity with CI, ephemeral preview environments per change, shared versus isolated test data, seeded data and its realism, environment drift and how it breaks tests, concurrent test execution and shared-state conflicts, and the written environment record. It explains how to make environments reproducible and trustworthy; it never recommends a cloud vendor and never promises a functional test suite. Use when asking "works on my machine", "CI environment", "preview environment", "ephemeral environment", "test data seed", "environment drift", "flaky in CI", "shared staging", "parallel test conflicts". Not for test case design (ac-testing), not for CI pipeline wiring (ac-ci-and-release), not for deployment strategy (ac-ci-and-release).
- ▌ Ac Venture Financing · jiayaoqijia bundleThe financial mechanics of venture-backed private companies: the cap table before and after each round, preference stacks and liquidation waterfalls, option pools and dilution arithmetic, term sheets as a leverage sequence, venture debt as an alternative layer, exit waterfalls for distributing proceeds across classes of stock, 409A valuations as the internal price of common stock, and the written financing record. It explains the arithmetic of ownership as investments pile up; it never recommends a security or predicts a fund raising outcome. Use when asking "cap table", "liquidation preference", "anti-dilution", "option pool", "priced round", "SAFE", "convertible note", "venture debt", "waterfall", "409A", "exit waterfall". Not for public equity analysis of the listed companies (ac-equity-research), not for fund manager diligence (ac-manager-and-vehicle-diligence), not for secondary share sales (ac-portfolio-financing secondaries coverage).
- ▌ Ac Writing Standards · jiayaoqijia bundleWriting-standards reference: which standard, style guide or reporting guideline exists, which edition is current, and what each governs - ISO 24495-1 and 24495-2, CMOS, AP Stylebook, APA, MLA, CSE, the Microsoft guide, the Plain Writing Act, WCAG text criteria, PRISMA and the EQUATOR reporting-guideline family - plus done criteria for each stage of the editorial sequence, and the lifecycle frame itself: which editorial pass is allowed to change meaning. Use when asking "which style guide exists for this", "what does ISO 24495-1 / CMOS / AP say", "what makes a document done", "which editorial pass changes meaning", "the editorial sequence". Not for doing the work itself: writing the brief, drafting, revising, editing or publishing. Those are craft tasks outside this skill.
- ▌ Trading Chart · jiayaoqijia bundleTechnical analysis of any stock, ETF, index, forex pair or crypto - trend stage, moving averages, RSI, MACD, ADX, ATR, Bollinger squeeze, Supertrend, volume/OBV, 52-week range, support and resistance levels, and daily vs weekly agreement, rolled into a -100..+100 bias score with reasons. Use when the user asks "what does the chart say", "is X bullish", "analyze X", for support/resistance, indicator values, or wants to test a rule such as price above its 200-day average on a symbol.
- ▌ Ac Narrative Writing · jiayaoqijia bundleStory craft in true writing and for the ear: narrative nonfiction structure, case stories and customer stories; talks, keynote outlines, demo narration, video and podcast scripts. Use when asking "add a story arc", "case story", "customer story", "write a talk script", "keynote outline", "demo narration", "video script", "podcast script". Not for breaking-news structure or a standalone internal decision document, and not for the argument grammar itself; that work sits outside this skill.
- ▌ Ac Security Engineer · jiayaoqijia bundleHardens software against attack across the whole lifecycle. Use when threat-modelling a feature or system, reviewing a change for security defects, picking a verification target against OWASP ASVS, or fixing findings in input handling, injection, browser-side attacks, authentication, sessions and tokens, authorization, API security, secrets, cryptography, SSRF, file uploads or deserialization. Also covers supply-chain and CVE triage, security testing gates, LLM and agent tool security, privacy duties, abuse and rate limiting, security logging, incident first response and vulnerability disclosure. Not for writing prose documentation, building release pipelines, running infrastructure operations, or offensive penetration testing against systems the user does not own — those tasks sit outside application hardening.
- ▌ Ac Service Lifecycle · jiayaoqijia bundleThe start-to-stop life of a long-running service: startup ordering and readiness versus liveness, configuration load and validation before traffic, graceful shutdown and connection draining, in-flight work at termination, health endpoints and their levels, dependency startup order and circuit-breaking into unavailable dependencies, and the written lifecycle record. It explains how a service comes up and goes down correctly; it never recommends a runtime or orchestrator and never promises an availability. Use when asking "readiness versus liveness", "graceful shutdown", "connection draining", "health check", "startup ordering", "SIGTERM handling", "warmup", "why do requests fail during deploys", "why does the service start but crash after". Not for CI pipeline wiring and deployment strategy (ac-ci-and-release), not for resilience budgets around steady-state calls (ac-resilience-budgets), not for container and runtime configuration (ac-performance).
- ▌ Ac Stream Processing · jiayaoqijia bundleComputing over unbounded data as it arrives: event time versus processing time, watermarks that declare a stream complete, windowing by tumbling, sliding, and session, handling late and out-of-order events, state and its size, aggregation functions over streams, streaming joins, and the written stream record. It explains how correctness is defined when the data has no end; it never recommends a framework and never promises a latency. Use when asking "stream processing", "watermark", "event time", "processing time", "tumbling window", "sliding window", "session window", "late data", "out of order events", "streaming join", "windowed aggregation", "why is my stream count wrong", "allowed lateness". Not for event delivery between services and consumer lag (ac-event-driven-architecture), not for market data collection specifically (ac-market-data-collection), not for durable workflows and sagas (ac-durable-execution).
- ▌ Ac Frontend Bundling · jiayaoqijia bundleHow front-end code becomes something a browser can load: module resolution and the import graph, code splitting and entry points, tree shaking and dead code, bundle budgets and route-level loading, source maps in production, asset graphs and cache-busting, and the written bundle record. It explains what the build produces and how to keep it small; it never recommends a bundler and never promises a load time. Use when asking "bundle size", "code splitting", "tree shaking", "lazy load", "dynamic import", "source map", "module resolution", "entry point", "chunk", "why is my bundle so big", "import cycle". Not for Core Web Vitals targets and field data (ac-performance), not for monorepo dependency graphs and remote caches (ac-monorepo-and-build-systems), not for general build hermeticity (ac-monorepo-and-build-systems).
- ▌ Ac Funding And Basis · jiayaoqijia bundlePerpetual-futures funding and basis craft: how funding is computed and paid, funding extremes as positioning evidence (and what they cannot predict), the cash-and-carry basis trade and its arithmetic, carry economics and the full cost stack, open-interest reading across venues, the measured fact that liquidations do not cluster at funding settlement, and the carry risk register. It analyses funding and basis; it never recommends a trade, a venue, or a return. Use when asking "funding rate", "basis trade", "cash and carry", "carry trade", "open interest", "is funding a signal", "perp funding". Not for venue evaluation (ac-perp-venue-diligence), not for the trade record or risk budget (ac-crypto-trading-discipline), not for hunt analysis (ac-liquidation-hunt-analysis).
- ▌ Ac Inference Serving · jiayaoqijia bundleServing model inference to real traffic: the memory wall and why tokens per second is a budget problem, KV-cache management as the core allocation, batching from static-naive to continuous with its latency trade, streaming responses and the first-token latency that users feel, throughput-versus-latency as the explicit design axis, autoscaling model replicas, and the written serving record. It explains how inference infrastructure behaves under load; it never promises a tokens-per-second figure. Use when asking "LLM inference serving", "KV cache", "continuous batching", "first token latency", "TTFT", "model deployment GPUs", "inference throughput", "streaming responses", "serving stack", "vLLM vs TensorRT", "why is inference slow", "inference autoscaling". Not for GPU kernel programming within a model (ac-gpu-and-parallel-compute), not for the deployment mechanics of ordinary services (ac-ci-and-release), not for picking model tiers per request (ac-token-cost-optimization).
- ▌ Ac Model Fine Tuning · jiayaoqijia bundleAdapting a pretrained model to your task by changing its weights: when fine-tuning beats prompting at all, the training-data craft of instruction pairs and preference pairs, SFT and its overfit traps, LoRA-class parameter-efficient methods, preference optimisation from RLHF to DPO, evaluating during training rather than after, serving the trained adapter beside its pinned base model with canary probes against quality drift, and the fine-tuning pipeline record. It explains the adaptation pipeline and its failure modes; it never promises a benchmark score. Use when asking "fine-tune a model", "LoRA adapter", "SFT", "DPO", "preference optimization", "RLHF alternative", "training data curation", "adapter serving", "catastrophic forgetting", "fine-tuning record", "canary probes", "base model pinned". Not for ML systems practice around the trained model (ac-ml-systems-practice), not for prompt and context craft (ac-prompt-engineer), not for model evaluation suites for selection (ac-model-evaluation).
- ▌ Ac Cascade Forensics · jiayaoqijia bundleReconstructs after the fact what happened in a leveraged crypto liquidation crash: branching ratios, fill-log timelines, tape reconstruction, participation anomalies, and evidence standards. Analyses past cascades with rigorous data; it never predicts future liquidations or prices. Use when asking 'cascade forensics', 'analyse this liquidation event', 'what happened in this crash', 'branching ratio', 'reconstruct the timeline', 'was this a cascade'. Not for reading a live set-up (ac-liquidation-hunt-analysis), not for the trade record (ac-crypto-trading-discipline), not for generic research method (ac-deep-researcher).
- ▌ Ac Code Construction · jiayaoqijia bundleWriting new code and delivering it in small steps: naming, error handling, lint and type gates, walking skeletons, always-green commits, time-boxed spikes, and docs-as-code inside the repo. Use when asking "implement this""split this feature into small shippable steps keeping main green",, "write the function", "how should I name this", "how should this handle errors", "build it step by step", "walking skeleton", "keep main green", "quick prototype to test this", "spike this for two days", "add docstrings", "generate the API reference". Not for planning the task list or estimates, cleaning up existing working code as a goal in itself, choosing the test portfolio, or branch policy; those sit outside this skill.
- ▌ Ac Commodity Options · jiayaoqijia bundleTrading commodity options by their own mechanics: options on futures and their expiry before the future, American exercise and early assignment, supply-driven skew and seasonal volatility, average-price and spread options, exercising into delivery risk, hedging physical exposure, and the written record. It explains how the contracts behave; it never recommends a commodity or predicts a price. Use when asking "options on crude futures", "commodity option expiry", "early exercise commodity option", "average price option", "Asian option", "crack spread option", "why is the skew so wide in gas". Not for generic greeks and structures (ac-options-and-volatility), not for commodity futures mechanics (ac-commodities-trading), not for commodity allocation (ac-alternatives-and-real-assets).
- ▌ Ac Corporate Actions · jiayaoqijia bundleHandling corporate actions correctly in a portfolio and in data: splits and consolidations, dividends and distributions, mergers and acquisitions, spin-offs and rights, the price and volume adjustment that keeps history comparable, the accounting and tax treatment, and the written corporate-actions record. It explains mechanics and record-keeping; it never recommends a security or predicts an outcome. Use when asking "stock split", "dividend adjustment", "merger arbitrage", "spin-off", "rights issue", "adjusted prices", "corporate action". Not for valuation (ac-valuation), not for equity research (ac-equity-research), not for tax computation (ac-trading-records-and-tax).
- ▌ Ac Durable Execution · jiayaoqijia bundleRunning long-lived work that must survive restarts: workflow state and durable checkpoints, sagas and compensating actions, exactly-once effects through idempotency, activity timeouts and heartbeats, versioning a workflow that is already running, human-in-the-loop waits, and the written workflow record. It explains how to make a process resumable and how that fails; it never recommends a workflow engine and never guarantees completion. Use when asking "durable execution", "workflow engine", "saga pattern", "compensating transaction", "distributed transaction", "long running process", "resume after crash", "workflow versioning", "human approval step", "temporal workflow". Not for event messaging and outbox patterns (ac-event-driven-architecture), not for queue delivery semantics alone (ac-webhook-and-async-delivery), not for CI pipeline orchestration (ac-ci-and-release).
- ▌ Trading Risk · jiayaoqijia bundleMandatory risk checkpoint before any order - verifies stop placement, risk per trade, reward:risk, position size, total portfolio heat, max positions, duplicate exposure, daily loss limit, losing-streak pause, drawdown circuit breaker and the kill switch, then issues a short-lived approval that trading-broker requires. Also shows a live risk dashboard. Use when about to place, submit or confirm any trade, when the user asks "can I take this trade", "am I over-risked", "how much risk do I have on", or whenever trading-broker asks for an approval.
- ▌ Trading Size · jiayaoqijia bundleCalculate exactly how much to buy or sell - fixed-fractional risk sizing from entry and stop, risk-amount sizing, lot/contract sizes with futures multipliers and margin, fractional crypto units, position-size tables, Kelly fraction, volatility-target sizing and risk-of-ruin. Pure math, no data or API needed. Use when the user asks "how many shares/lots/coins", "how much should I risk", "what if I risk 2%", about Kelly criterion, or leverage and margin math.
- ▌ Ac Agent Tool Design · jiayaoqijia bundleDeciding what tools an agent gets and shaping each one so the model uses it correctly: which capabilities deserve to be tools at all, writing descriptions the model actually reads, result payloads sized for a context window, the tool menu and its confusion costs, error returns that teach recovery instead of dead ends, and the written tool-surface record. It teaches the craft of the tool interface seen from the model's side; it never recommends a framework and never promises an agent will behave. Use when asking "should this be a tool", "tool description writing", "how many tools is too many", "tool naming", "tool result format", "tool menu design", "agent tool design", "tool error messages", "tool schema design", "when not to give an agent a tool". Not for the client-side agent loop and multi-turn plumbing (ac-llm-api-integration), not for MCP server protocol and transport (ac-mcp-authoring), not for sandboxing what a tool may touch (ac-wasm-and-sandboxes).
- ▌ Trading Odds · jiayaoqijia bundleMonte Carlo simulation for traders - estimate the odds a specific setup hits its target before its stop by block-bootstrapping the symbol's own price behaviour, and stress-test a strategy by resampling its trade R-multiples into thousands of equity paths to get realistic return ranges, drawdown percentiles, losing streaks and risk of ruin. Use when the user asks "what are the odds", "how likely is my target", "how bad can drawdowns get", "risk of ruin", or after a backtest or journal review.
- ▌ Trading Plan · jiayaoqijia bundleTurn a trade idea into a complete, numbers-first plan - entry (limit, market or pattern pivot), stop options (ATR, structure, swing, pattern, percent), targets (R-multiples or next resistance), reward:risk, invalidation and position size from the account's risk rules, optionally scaled by market regime and saved to the journal. Works for stocks, ETFs, futures (contract multipliers), options underlyings and fractional crypto. Use when the user asks "how should I trade X", "where's my stop", "how many shares", "plan an entry", or after a screener/pattern hit.
- ▌ Trading Data · jiayaoqijia bundleFetch price history (OHLCV bars) and quotes for stocks, ETFs, indices, forex, futures and crypto in any market - free via Yahoo Finance with no API key, from local CSV files, or from a broker feed. Use when the user asks for a price, chart data, historical candles, intraday bars, wants to download or export data to CSV, or when another skill needs data. Handles daily, weekly, monthly and intraday intervals.
- ▌ Trading News · jiayaoqijia bundleNews monitor for any market - shows only what is new on the stocks you watch since the last check, newest first, in the exchange's local time, each item tagged (earnings, analyst, deal, capital, people, legal, regulatory, halt, risk, macro), with how far each stock is from the previous close and MOVING flags. Google News for every market (US, India NSE/BSE, UK, Japan...), Yahoo Finance headlines for US tickers and SEC 8-K filings for US companies. Free, no API key. Use when the user asks "any news on X", "why is this moving", "morning briefing", "what's the news on my watchlist", "did anything break", "check the 8-Ks", or before planning a trade.
- ▌ Ac Factor Investing · jiayaoqijia bundleBuilding and evaluating factor exposures: what a factor is and how factors are constructed, cross-sectional standardisation and neutralisation, the value and size and momentum and quality families, portfolio sorts versus regression, capacity and crowding, factor timing and its poor record, and the written factor record. It explains construction and measurement; it never recommends a factor or predicts its return. Use when asking "factor investing", "factor construction", "cross-sectional", "neutralise a factor", "momentum", "value factor", "factor crowding", "smart beta", "should I time factors". Not for judging whether a backtest is real (ac-backtest-integrity), not for fund vehicle comparison (ac-fund-selection), not for portfolio risk budgeting (ac-portfolio-construction).
- ▌ Ac Model Evaluation · jiayaoqijia bundleBuilding evaluation suites that decide between models for a task: what the eval measures before any prompt is written, constructing cases from real failure modes and coding them from task-native artifacts, contamination and why held-out data no longer guarantees freshness, automatic scoring with exact-match and judge limits, pass-at-k and aggregate metrics read honestly, human comparison and preference data as a separate instrument, and the written evaluation record. It designs the measurement; it never certifies a model as good and never recommends a vendor. Use when asking "model evaluation", "eval suite design", "build a benchmark", "contamination", "held-out set", "LLM as judge", "pass at k", "model comparison", "regression suite for model upgrades", "golden set", "cost of evaluation". Not for improving a prompt against fixed cases (ac-prompt-engineer), not for running the harness code itself (ac-llm-api-integration), not for evaluating datasets as research evidence (ac-alternative-data).
- ▌ Ac Money Arithmetic · jiayaoqijia bundleRepresenting and computing money without losing cents: integer minor units versus binary floating point, decimal semantics and precision, rounding modes and where each is appropriate, allocation that distributes remainders, currency conversion and its rounding sequence, day-count and accrual arithmetic, reconciliation tolerance, and the written money-policy record. Use when asking "floating point money", "decimal places", "rounding mode", "banker's rounding", "split an amount", "allocate a remainder", "penny discrepancy", "currency conversion rounding", "why is there a cent missing", "money type". Not for pricing strategy, not for tax computation, and not for test technique in general (ac-testing).
- ▌ Ac Proposal Writing · jiayaoqijia bundleScored application documents: proposals and RFP responses with compliance matrices and win themes; grant narratives and specific-aims pages; cover letters, personal statements and admissions essays. Use when asking "answer this RFP", "bid response", "compliance matrix", "win themes", "write this grant section", "specific aims page", "cover letter", "personal statement", "admissions essay". Not for persuasive marketing copy, the one-ask business email, or a news announcement; that work sits outside this skill.
- ▌ Ac Subskills Author · jiayaoqijia bundleAuthors new self-contained Agent Skills that contain subskills, and audits skills before install (install only after a human approves, or through a fail-closed install gate the operator runs). Every emitted leaf holds its full procedure and hands no work to another skill. Use when creating a skill-with-subskills, decomposing an oversized skill into a subskills/ layout, rebuilding a skill so it depends on no other skill, vetting a third-party skills.sh skill for install, scanning a skill tree for injection or hand-off lines (scripts/skill_scan.py), linting a subskill tree against the 4 enforceable rules, or running a blind routing evaluation (does a task reach the right leaf?) on a skill's description and index. Not for writing a small flat skill with no subskills.
- ▌ Ac Alternative Data · jiayaoqijia bundleEvaluating non-traditional datasets before they are used in a decision: provenance and vendor claims, point-in-time integrity and backfill leakage, survivorship and restatement in vendor history, coverage and representativeness, signal decay as a dataset becomes popular, licensing and permitted use, and the written data-vendor record. It evaluates datasets as evidence; it never recommends a strategy or predicts a return. Use when asking "alternative data", "data vendor", "point-in-time", "backfill bias", "is this dataset any good", "signal decay", "panel data", "satellite data", "web scraping data". Not for building the pipeline (ac-market-data-collection), not for testing a strategy on it (ac-backtest-integrity), not for prompt or model design (ac-prompt-engineer).
- ▌ Ac Brand Guidelines · jiayaoqijia bundleCodify corporate brand standards into a testable brand specification, build machine-checkable project style sheets, audit document corpuses against terminology and voice rules, detect recurring style slips, and run remediation passes with editorial sign-off. Use when asking "write our brand guidelines", "audit our docs against the brand", "does this match our style guide", "brand voice consistency", "terminology compliance", "our documents don't sound like us". Not for choosing a public style guide for one author's voice (use ac-voice-and-style), not for line-level copyediting of a draft (ac-editing), not for readability and inclusive language (ac-plain-language), not for creating marketing copy (ac-persuasive-writing).
- ▌ Ac Business Writing · jiayaoqijia bundleWorkplace communication: the one-ask email and its follow-up, the memo, the status report, the board update and the executive summary. Use when asking "write this email", "reply to this thread", "follow up on this thread", "one-ask email", "write a memo", "status report", "executive summary", "board update". Not for managing or sorting an inbox, and not for scored bids, grant narratives or press statements; that work sits outside this skill.
- ▌ Ac Database Changes · jiayaoqijia bundleDatabase schema design and zero-downtime schema change: tables, keys, constraints, normalisation trade-offs, expand-migrate-contract, backfills, renames and drops without locking production. Use when asking "design the tables", "what primary key", "normalise this schema", "should this be NoSQL", "add a column with no downtime", "rename this column", "backfill a table", "the migration locked the database". Not for the first-pass API resource shapes, retiring a public API, feature removal, or backup-and-restore mechanics; those sit outside this skill.
- ▌ Ac Earnings Quality · jiayaoqijia bundleReading reported earnings for what they conceal: accruals versus cash flow, cash conversion and the working-capital swing, non-GAAP bridges and what they exclude, revenue recognition timing, restructuring and one-off patterns that recur, guidance mechanics and consensus behaviour, restatement red flags, and the written quality record. It analyses reported results forensically; it never accuses a company of fraud and never recommends a security. Use when asking "earnings quality", "accruals", "cash conversion", "non-GAAP adjustment", "revenue recognition", "channel stuffing", "guidance cut", "restatement". Not for the investment case (ac-equity-research), not for ratio interpretation in general (ac-equity-research), not for the reporting on the statements (ac-technical-writing).
- ▌ Okx MCP Services · jiayaoqijia bundleAccess NewsLiquid / 6551 through the OnchainOS CLI. Use for explicitly chosen NewsLiquid, News Liquid, 6551 or 6551Team operations and clear continuations, including information queries, wallet-backed service plans and WSS client guidance; explain supported services locally.
- ▌ Trading Fno · jiayaoqijia bundleFutures and options (F&O) analysis for India (NSE) and US - Black-Scholes price and Greeks (delta, gamma, theta, vega), implied volatility from a price, multi-leg payoff with breakevens and max profit/loss (long/short calls and puts, spreads, straddles, strangles, iron condor, butterfly), and option-chain reading - open interest, put/call ratio, max pain, OI walls, ATM straddle and implied move. Chains come from a US ticker (Cboe delayed data), an NSE option-chain CSV you download, or Kite instruments and quotes when Kite is set up. Analysis only, never places an order. Use when the user says "option chain", "PCR", "max pain", "what are the Greeks", "implied volatility", "payoff of an iron condor", "breakeven on this spread", "NIFTY options", "F&O", or before sizing an options trade.
- ▌ Icp Deploy Check · jiayaoqijia bundlePre-deploy safety gate for an Internet Computer Rust canister (ic-cdk). A fast, read-only checklist for the five deploy-time footguns that brick a canister or let anyone drain it - anonymous-principal access, fetch_root_key in shipped code, unguarded admin methods, pre_upgrade traps, single controller - with grep signals, the tracing rules to confirm each hit, and a PASS/FAIL/REVIEW report. Use before `icp deploy -e ic` (or `dfx deploy --network ic`), in CI, or when asked whether a canister is ready or safe for mainnet. For the secure-coding patterns themselves, use canister-security.
- ▌ Ac Academic Writing · jiayaoqijia bundleScholarly writing: structuring an IMRaD paper or a thesis chapter, choosing the reporting guideline by study type, managing submission and the response to reviewers; narrative and systematic literature reviews with search, screening, synthesis and PRISMA conduct. Use when asking "structure this paper", "IMRaD", "thesis chapter", "pick a reporting guideline", "respond to reviewers", "write a lit review", "systematic review", "PRISMA", "synthesise these studies". Not for running the literature search that finds the study set, nor for verifying that individual citations resolve; that work sits outside this skill.
- ▌ Ac Release Publish · jiayaoqijia bundlePublish or update a small public release of an agent-written artifact — skill files, spec documents, prompts — by treating every user-facing file as a claim set: inventory each factual sentence, verify it against the bytes, audit independently, repair from evidence, audit the delta, and gate the irreversible push. Use when asking 'publish this release', 'cut a release', 'verify the README before push', 'the release claims are wrong', 'sync the public files', or when a shipped release carries claims nobody checked. Not for: feature code, CI pipelines, or app deployment.
- ▌ Ac Static Analysis · jiayaoqijia bundleGetting value from tools that read code without running it: what linters and analyzers can and cannot find, rule selection and severity discipline, suppressions with a reason and an expiry, baselines for adopted code, metrics from analysis and their misuse, wiring analysis into review and CI, and the written analysis record. It explains how static analysis is chosen and kept useful; it never recommends a specific tool and never treats a clean report as proof of correctness. Use when asking "linter", "static analysis", "code smell", "cyclomatic complexity", "naming convention", "lint suppression", "baseline", "why did the linter stop finding anything", "should I enforce this rule". Not for runtime debugging (ac-debugging), not for test design (ac-testing), not for security vulnerability assessment (ac-security-engineer).
- ▌ Ac Time And Clocks · jiayaoqijia bundleHandling time correctly in software: monotonic versus wall clocks and what each is for, clock skew between machines, NTP and how clocks actually stay honest, UTC as a transport format and its local-presentation exceptions, the timezone database as a changing dependency, leap seconds and discontinuities, and the written time-policy record. It explains how software should treat time; it never recommends an NTP product and never converts times by guesswork. Use when asking "monotonic clock", "wall clock", "clock skew", "NTP", "UTC everywhere", "timezone database", "tzdata", "leap second", "why do my timestamps disagree", "time went backwards", "timer drift", "midnight boundary". Not for locale formatting of dates for users (ac-i18n-and-localisation), not for stream event-time semantics (ac-stream-processing), not for scheduled job semantics (ac-scheduled-jobs).
- ▌ Ac Token Diligence · jiayaoqijia bundleStructured pre-exposure diligence on a crypto token or protocol: supply and unlock schedules, holder concentration, treasury and runway, governance and admin control, liquidity and market structure, a red-flag checklist, and the written diligence record. It analyses evidence and states confidence; it never recommends a token, predicts a price, or gives investment advice. Use when asking "should I look at this token", "token diligence", "unlock schedule", "who holds this token", "is this token safe", "tokenomics review". Not for venue safety (ac-perp-venue-diligence), not for the trade decision record (ac-crypto-trading-discipline), not for post-event forensics (ac-cascade-forensics).
- ▌ Ac Voice And Style · jiayaoqijia bundleHow text sounds and the rules that keep it consistent: choosing a style guide (AP, Chicago, APA, MLA, CSE, Microsoft), building a project style sheet, keeping one author or brand voice across documents, setting the tone for tense or high-stakes messages, and removing machine tells from AI-flavoured drafts. Use when asking "which style guide", "AP or Chicago", "build a style sheet", "keep my voice", "brand voice", "this sounds cold", "deliver bad news", "soften this", "does this sound like AI", "de-slop this". Not for the copyedit consistency pass that applies the sheet, nor for the AI-disclosure policy decision; that work sits outside this skill.
- ▌ Ac Media Pipelines · jiayaoqijia bundleBuilding the pipeline that turns user uploads into web-usable media: the transcoding job and its state, upload verification before processing, image optimisation and format negotiation, thumbnail and poster generation at multiple sizes, video ladders from a single source rendition to adaptive bitrate, the async worker pattern with progress, metadata extraction and privacy scrubbing, and the written media pipeline record. It explains how media is processed in a pipeline; it never recommends a codec and never promises a file size. Use when asking 'transcoding', 'ffmpeg', 'video pipeline', 'thumbnail generation', 'image optimisation', 'WebP', 'AVIF', 'adaptive bitrate', 'video ladder', 'HLS rendition', 'progressive JPEG', 'EXIF strip', 'upload then process', 'source then derivatives'. Not for the security of accepting uploads (ac-security-engineer), not for realtime peer-to-peer media transport (ac-realtime-media-transport), not for capacity planning and profiling (ac-performance).
- ▌ Ac Municipal Bonds · jiayaoqijia bundleReading the municipal bond market on its own terms: general obligation versus revenue pledges, tax-equivalent yield and the tax status that drives it, call features and refunding arithmetic, insurer wraps and their residual value, official statements and continuing disclosure, pension and OPEB liabilities behind a credit, and the written municipal record. It explains the pledge, the tax treatment and the credit arithmetic; it never recommends a bond and never predicts a default. Use when asking "municipal bond", "general obligation", "revenue bond", "tax equivalent yield", "muni call", "refunding", "bond insurer", "official statement", "muni pension liability", "why is the muni yield lower". Not for corporate credit analysis (ac-bank-and-credit-analysis), not for sovereign debt restructuring (ac-sovereign-debt), not for the taxable bond curve (ac-fixed-income-and-rates).
- ▌ Ac Order Execution · jiayaoqijia bundleUse when asking how to execute orders, manage slippage, select order types, place stops, slice large orders, or audit fills. Covers order types, cascade execution, slippage and market impact, tactical order placement, slicing and timing, execution records, and failure modes. Not for the venue evaluation (ac-perp-venue-diligence), not for the trade record or journal (ac-crypto-trading-discipline), not for liquidation risk geometry (ac-liquidation-risk-management).
- ▌ Ac Prompt Engineer · jiayaoqijia bundleEngineers prompts for LLMs and agents: instruction lines, structure, examples, named techniques, model and sampler choices, context budget, grounding, injection resistance, and proof that a change helped. Use when the user wants to tune a prompt or the standing instructions an agent runs under, get a model to follow a format or stop refusing, add few-shot examples, pick between reasoning and instruction models, set temperature or reasoning effort, shrink a bloated instruction set, ground answers on retrieved documents, harden a prompt against injection, organize a prompt library, rewrite an agent's tool or handoff sections, prompt image or video models, or check whether a prompt edit actually improved anything. Not for one-off chat messages, model training or fine-tuning, choosing an AI product to buy, or building attack payloads.
- ▌ Ac Deep Researcher · jiayaoqijia bundleRuns a full deep-research study end to end. Reframes the question into falsifiable hypotheses, decomposes it into a query plan, triages sources on a trust ladder, pulls evidence through the keyless-first retrieval cascade, verifies every load-bearing claim against two or more independent source lineages with verbatim quotes archived, attacks the draft conclusions with an adversarial pass, stops on declared criteria with the reason stated, keeps a claim-to-source evidence ledger, and delivers the answer-first evidence report. Use for "research this question", "map the literature", "verify this claim properly", "write the evidence report", "investigate before we decide", or any question where a wrong answer costs more than the research. Not for one-hop factual lookups (what, who, when, price), single-page fetches, multi-day autonomous desk operations, or formal systematic-review protocol compliance.
- ▌ Ac Doc Coauthoring · jiayaoqijia bundleStaged co-authoring workflow for structured documents (proposals, specs, decision docs, RFCs): the author and the agent build the document together through explicit stages including context gathering, iterative section-by-section construction, and a fresh-reader test before release. Use when asking 'co-author this document', 'draft this proposal with me', 'let's write this spec together', 'guide me through writing this RFC', 'test my draft with a fresh reader', 'PRD', 'decision doc'. Not for producing a first draft alone (ac-drafting), line-editing an existing draft (ac-editing), or doc-type conventions (ac-spec-writing).
- ▌ Ac Domain Modeling · jiayaoqijia bundleThe craft of modeling a business domain in code, domain-driven: building the shared language between domain experts and developers, drawing context boundaries, designing aggregates and their consistency rules, expressing state changes as domain events, isolating persistence behind repository contracts, and evolving the model as understanding deepens. Use when asking "model this domain", "define our bounded contexts", "ubiquitous language", "aggregate design", "domain events", "where does this logic belong", "model the business rules". Not for choosing system topology or structure styles (that is ac-architecture), not for schema migrations and storage mechanics (ac-database-changes), not for surveying an existing codebase for candidates (ac-architecture-survey).
- ▌ Ac Equity Research · jiayaoqijia bundleFundamental research on a listed company before capital is committed: primary filings and sources, the three financial statements and how they link, ratio analysis with its caveats, evidence for or against a durable competitive advantage, management and capital-allocation record, accounting and business red flags, and the written research record. It analyses evidence and states confidence; it never recommends a stock, predicts a price, or gives investment advice. Use when asking "research this company", "read the 10-K", "is this a good business", "equity research", "what do the accounts say". Not for valuing the company (ac-valuation), not for portfolio policy (ac-investment-policy-statement), not for token diligence (ac-token-diligence).
- ▌ Ac Geospatial Data · jiayaoqijia bundleStoring and querying data that lives on a map: coordinate reference systems and the disaster of mixing them, spatial indexes from R-tree to geohash and what each is for, nearest-neighbour and radius queries, bounding boxes as the cheap filter and where they mislead, distance computation over a sphere, polygons and containment, and the written geospatial record. It explains how spatial storage and queries behave; it never recommends a spatial database and never promises a query time. Use when asking "spatial index", "geohash", "R-tree", "nearest neighbour query", "radius search", "bounding box", "coordinate system", "WGS 84", "latitude longitude storage", "point in polygon", "haversine", "postgis", "why is my distance query slow", "GeoJSON". Not for general database indexing and partitioning (ac-query-and-index-design, ac-database-engine-internals), not for general analytical data modelling and dimensions (ac-analytical-data-modeling), not for map rendering and visual design (ac-dataviz).
- ▌ Ac Private Credit · jiayaoqijia bundleAnalysing private credit as an asset class rather than a borrower: direct lending structure, unitranche and first-out/last-out splits, covenant-lite terms and what a covenant gives up, PIK and amortisation, sponsor dynamics and the lender's position, mark and valuation in an illiquid book, distress and lender-on-lender conflict, and the written private-credit record. It explains the structure and the arithmetic; it never recommends a fund or predicts a default. Use when asking "private credit", "direct lending", "unitranche", "covenant lite", "PIK interest", "how is my private credit fund marked", "lender on lender violence", "sponsor backed lending". Not for assessing a single borrower's ability to repay (ac-bank-and-credit-analysis), not for the allocation decision (ac-alternatives-and-real-assets), not for private fund financing and continuation vehicles (ac-portfolio-financing).
- ▌ Ac Scheduled Jobs · jiayaoqijia bundleDesigning and diagnosing work that runs on a schedule rather than on request: run semantics when a trigger is missed, at-least-once delivery and idempotent job bodies, singleton execution and the lock that prevents overlaps, long-run and overdue jobs, backfill and catch-up after downtime, monitoring liveness versus completion, and the written schedule record. It explains the semantics of time-triggered work; it never recommends a scheduler and never treats silence as success. Use when asking "cron job", "scheduled job", "missed run", "job overlap", "singleton lock", "catch up after downtime", "backfill schedule", "why didn't the 9am job run", "job still running", "at least once job". Not for multi-step durable workflows (ac-durable-execution), not for queue delivery to endpoints you don't own (ac-webhook-and-async-delivery), not for CI pipeline scheduling (ac-ci-and-release).
- ▌ Ac Skill Adoption · jiayaoqijia bundleThird-party skill adoption and consumer governance for agent packs: discovering registries, judging trust signals, security vetting against prompt injection, verifying provenance and open-source licenses, staged install gating, build-versus-adopt trade-offs, and managing post-install lifecycles. Use when asking 'find skills for this task', 'should I install this skill', 'vet a third-party skill', 'is this skill safe', 'explore skill registries', 'adopt vs build skill', 'check skill license', 'audit adopted skill'. Not for: authoring your own skills from scratch (use ac-subskills-author), publishing your own releases (use ac-release-publish), or auditing internal system security (use ac-security-engineer).
- ▌ Ac Sovereign Debt · jiayaoqijia bundleSovereign debt and its restructuring mechanics: the difference between a sovereign and a corporate credit, collective action and aggregation clauses, the restructuring process from exchange offer to IMF programme, currency mismatch and the local-versus-foreign law split, holdout creditors and their limits, recovery arithmetic and the exit yield, and the written sovereign record. It explains the legal and economic machinery of restructuring; it never recommends a bond and never predicts a default or a policy outcome. Use when asking "sovereign debt", "collective action clause", "CAC", "debt restructuring", "IMF programme", "Paris Club", "holdout creditor", "local law versus foreign law", "sovereign default", "recovery value". Not for reading macro releases and policy (ac-macro-and-policy-reading), not for corporate credit analysis (ac-bank-and-credit-analysis), not for FX risk in a portfolio (ac-currency-and-fx-risk).
- ▌ Osint Ctf Databases · jiayaoqijia bundleAuthoritative public databases and live APIs for OSINT CTF work. Use for geolocation, map/POI proximity, Wikidata/Commons verification, domain/RDAP/certificate history, web archives, corporate registries, flight/vessel enrichment, and turning a vague clue into a reproducible source trail.
- ▌ Ac Fund Selection · jiayaoqijia bundleEvaluating funds and ETFs as vehicles: expense ratios and the total cost stack, tracking difference versus tracking error, index methodology, structure and counterparty risk, liquidity and spreads, tax efficiency, and the written fund record. It evaluates vehicles; it never recommends a fund or predicts returns. Use when asking "which ETF", "fund fees", "tracking error", "index fund", "should I use this fund", "fund structure", "mutual fund or ETF". Not for choosing the asset allocation (ac-investment-policy-statement), not for evaluating a company (ac-equity-research), not for alternatives vehicles (ac-alternatives-and-real-assets).
- ▌ Ac Inbound Triage · jiayaoqijia bundleRouting index for inbound work before it is worked: decide what to do first, what to schedule, what to hand off, and what to drop. Seven leaves: queue-definition (one intake point, scope, service classes, queue versus backlog), triage-axes (urgency, impact, reversibility, effort, dependency, ownership), dispositions (act now, schedule, delegate, drop), severity-escalation (severity matrix, paging threshold, escalation ladder), batching-wip (context-switch cost, protected blocks, batch windows, WIP limits), triage-log (one line per item, review cadence, aging report, median and oldest age), false-urgency (manufactured urgency, deadline provenance, renegotiation, the 24-hour test). Use when asking 'triage my inbox', 'triage this queue', 'what do I do first', 'everything is urgent', 'sort these requests', 'my backlog is out of control'. Not for: planning work already accepted (that is task planning), writing the reply itself, or incident command during an active outage.
- ▌ Ac Liquidity Risk · jiayaoqijia bundleManaging liquidity as its own budget rather than a property of assets: market liquidity versus funding liquidity, days-to-liquidate at portfolio level, the liquidity ladder and its haircuts, fire-sale spirals and the discount that clears them, margin calls as a liquidity event, liquidity under stress when correlations converge, and the written liquidity record. It measures what can be sold and when; it never recommends a position and never predicts a crisis. Use when asking "liquidity risk", "days to liquidate", "liquidity budget", "fire sale", "funding liquidity", "liquidity ladder", "how much can I exit in a week". Not for sizing a single stock position (ac-stock-trading), not for risk budgeting across strategies (ac-portfolio-construction), not for margin mechanics on one position (ac-portfolio-leverage).
- ▌ Ac Message Queues · jiayaoqijia bundleThe middleware layer that decouples producers from consumers: broker topologies and what a direct, fanout, or topic exchange actually routes, delivery guarantees from at-most-once through to effectively-once, acknowledgement and redelivery when a consumer dies mid-message, poison messages and the dead-letter path, priority and fair dispatch, queue backpressure and bounded buffers, competing consumers and ordering under scale-out, and the written queue record. It explains how a queue behaves and where it fails; it never recommends a broker. Use when asking "message queue", "dead letter queue", "poison message", "ack and redeliver", "competing consumers", "fanout exchange", "topic routing", "work queue", "priority queue", "why did this message arrive twice", "prefetch". Not for event-driven design between your own services (ac-event-driven-architecture), not for webhook delivery to endpoints you do not own (ac-webhook-and-async-delivery), not for durable workflows and sagas (ac-durable-execution).
- ▌ Ac Plain Language · jiayaoqijia bundlePlain-language rewriting for public-facing standards-bearing documents; readability scoring and testing with real readers; inclusive, bias-free and accessible text including alt text and Easy Read versions. Use when asking "make this plainer", "write for the public", "what grade level is this", "test this with readers", "is this biased", "inclusive-language pass", "alt text", "easy read version". Not for one-off clarity polishing of a single chat reply or sentence, and not for choosing a house style guide; that work sits outside this skill.
- ▌ Ac CI And Release · jiayaoqijia bundleCI pipelines, deployment, release: pipeline-as-code and required checks, canary and blue-green deploys, feature flags, SemVer release cuts and launch checklists, IaC and environment parity. Use when asking "set up CI", "add a GitHub Actions workflow", "which checks should be required", "speed up the pipeline", "deploy safely", "set up a canary", "roll back the release", "put it behind a flag", "cut a release", "launch checklist", "containerize this", "write the Terraform". Not for choosing which tests to run, triaging a red pipeline, branch policy, or incident response; those sit outside this skill.
- ▌ Ac Credit Options · jiayaoqijia bundleTrading credit options by their own mechanics: payer and receiver options on single-name CDS, expiry against the underlying swap, spread volatility and recovery assumptions, options on credit indices, exercise and settlement into protection, dealer liquidity, hedging with credit options, and the written record. It explains how the instruments quote and settle; it never recommends a credit or predicts a default. Use when asking "CDS option", "credit spread volatility", "option on CDS index", "swaption on credit", "credit vol quote", "how does a CDS option settle". Not for generic greeks and structures (ac-options-and-volatility), not for CDS mechanics and basis (ac-credit-derivatives), not for assessing a borrower (ac-bank-and-credit-analysis).
- ▌ Ac Crypto Options · jiayaoqijia bundleTrading crypto options by their own conventions: inverse coin-margined versus linear stablecoin-margined contracts, expiry grids and 08:00 UTC settlement, the volatility surface and its skew, venue structure and request-for-quote liquidity, margin and liquidation of short options, the yield-selling pattern and its tail, and the written record. It explains how the contracts behave; it never recommends a position or predicts a price. Use when asking "inverse option", "coin-margined option", "Deribit expiry", "DVOL", "crypto option spread", "selling options for yield", "option liquidation". Not for generic greeks and structures (ac-options-and-volatility), not for perpetual funding (ac-funding-and-basis), not for the spot venue's safety (ac-perp-venue-diligence).
- ▌ Ac Data Contracts · jiayaoqijia bundleTreating a data feed as an interface with obligations: schema and semantics in a contract, freshness and completeness guarantees, schema evolution and the compatibility rules that decide who breaks, ownership and escalation, quality checks at the boundary, and the written contract record. It explains how to specify a dataset's guarantees; it never certifies a dataset's correctness and never replaces profiling. Use when asking "data contract", "schema registry", "data freshness", "completeness SLA", "data quality checks", "who owns this pipeline", "breaking schema change", "data model change", "upstream data changed". Not for database schema migrations (ac-database-changes), not for event schema evolution between services (ac-event-driven-architecture), not for evaluating an external vendor dataset (ac-alternative-data).
- ▌ Ac Equity Options · jiayaoqijia bundleTrading listed equity options by their own mechanics: single-name versus index contracts, expiry and settlement conventions including AM-settled index options, dividends and early exercise, borrow and put-call parity distortions, index volatility versus component volatility and dispersion, corporate actions that adjust contracts, and the written record. It explains how the contracts behave; it never recommends a position or predicts a price. Use when asking "SPX AM settlement", "weekly options expiry", "early exercise before dividend", "hard to borrow put", "dispersion trading", "index vol versus single stock vol", "option adjustment after a split". Not for generic greeks and structures (ac-options-and-volatility), not for trading the underlying stock (ac-stock-trading), not for single-name event sizing (ac-stock-trading).
- ▌ Ac Text Encoding · jiayaoqijia bundleHandling text as bytes without corrupting it: what UTF-8 actually encodes and its malformed forms, normalization forms and why two identical-looking strings differ, grapheme clusters versus code points versus bytes, encoding boundaries at input and output, mojibake and how it happens, and the written text-policy record. It explains how text is represented and where it breaks; it never recommends a library and never guesses an encoding. Use when asking "UTF-8", "encoding error", "mojibake", "why do these strings not match", "normalization form", "NFC versus NFD", "grapheme cluster", "code point", "invalid byte sequence", "text corruption", "why does my hash of the same text differ". Not for locale formatting and language presentation (ac-i18n-and-localisation), not for collation and search (ac-i18n-and-localisation), not for parsing structured data formats (ac-api-design).
- ▌ Ac Trade Finance · jiayaoqijia bundleThe financing layer beneath physical commodity trade: letters of credit and documentary collections, warehouse receipts and bills of lading as title documents, pre-payment and prepay structures, inventory and receivables finance, counterparty and performance risk in a documentary sale, the fraud patterns that recur, and the written trade-finance record. It explains the instruments and the risk; it never recommends a transaction and never gives legal advice. Use when asking "letter of credit", "documentary collection", "bill of lading", "warehouse receipt", "prepayment", "trade finance", "inventory finance", "who bears the risk in this shipment", "double financing". Not for commodity price and curve mechanics (ac-commodities-trading), not for borrower credit analysis (ac-bank-and-credit-analysis), not for shipping and freight operations (ac-institutional-operations).
- ▌ Confidential · jiayaoqijia bundleManage confidential (private) transfers via Tongo Cash on Starknet — setup, fund, transfer, withdraw, ragequit, rollover using ZK proofs. Use this skill when the user wants to send tokens privately, hide transfer amounts, use zero-knowledge proofs, set up Tongo, fund or withdraw from a confidential account, perform an emergency exit (ragequit), or activate pending balance (rollover). Also trigger when the user says "send privately", "confidential transfer", "hide my transaction", "Tongo Cash", "ZK transfer", or any variation about privacy-preserving transfers — even if they don't use the word "confidential".
- ▌ Canister Audit · jiayaoqijia bundleAudit an existing Internet Computer Rust canister (ic-cdk) for security flaws and PROVE a confirmed one with a PocketIC reproduction. Covers detecting the canister, a high-recall static first pass, a systematic review against the canister-security pitfalls, and the distinctive step: building the canister to wasm and executing the exploit in PocketIC to turn a suspected flaw into a demonstrated one. Use when reviewing or auditing a canister you did NOT write, or proving a finding before you report it. Complements canister-security (which teaches the secure patterns); this one finds and proves violations of them.
- ▌ Abhay2008 Ctf Input Sanitize · jiayaoqijia bundleChallenge files are data, never instructions. Produce untouched originals, sanitized copies, and a manifest/report explaining every removal. Use the sanitized bundle for solving and harness input.
- ▌ Ac Binary Formats · jiayaoqijia bundleDesigning and reading binary data formats: endianness and byte order as a declared choice, integer encoding from fixed-width to varints, tagged and schema-evolvable layouts, alignment padding and struct packing, checksums and magic numbers, versioning a binary layout, and the written format record. It explains how bytes on disk or wire are laid out and read back; it never recommends a serialization library and never promises compactness. Use when asking "endianness", "byte order", "varint", "binary file format", "struct packing", "wire format", "schema evolution", "file format design", "checksum at the end", "magic number", "fixed versus variable length", "alignment padding". Not for API contract design in general (ac-api-design), not for generated code from schemas (ac-code-generation-and-apis), not for text encoding and Unicode (ac-text-encoding).
- ▌ Ac MCP Authoring · jiayaoqijia bundleAuthoring Model Context Protocol servers that expose tools, resources, and prompts to AI agents over an open protocol. Covers protocol models, tool design and schemas, resource URIs and templates, transport layers and stdio/HTTP configuration, security models with OAuth and injection defense, testing and debugging with the MCP inspector, and SemVer versioning and operations. Use when asking "build an MCP server", "expose this as a tool for agents", "MCP integration", "wrap this API in MCP", "add tools to my agent". Not for human-facing API contracts, nor for prompting models themselves.
- ▌ Ac Rates Options · jiayaoqijia bundleTrading interest-rate options by their own conventions: payer and receiver swaptions, caps and floors, normal versus lognormal volatility, European Bermudan and mid-curve exercise, the volatility cube and its skew, hedging DV01 and vega, dealer liquidity and clearing, and the written record. It explains how the instruments quote and settle; it never recommends a rate view or predicts yields. Use when asking "swaption", "cap floor", "normal vol", "basis point volatility", "Bermudan swaption", "mid-curve option", "rates vol cube", "why is my swaption vega not matching". Not for generic option greeks and structures (ac-options-and-volatility), not for bond futures mechanics (ac-rates-trading), not for bond portfolio mathematics (ac-fixed-income-and-rates).
- ▌ Ac Rates Trading · jiayaoqijia bundleTrading government bond futures as a venue: contract specifications and the cheapest-to-deliver, DV01 and hedge ratios, net basis and the delivery option, repo financing and specials, curve and butterfly trades, central-bank and auction calendars, and the written rates trading record. It explains how the contracts and the curve work; it never recommends a rate view or predicts yields. Use when asking "bond futures", "cheapest to deliver", "DV01", "hedge ratio for Treasuries", "2s10s", "net basis", "repo special", "why did my bond future track the CTD". Not for bond price and duration mechanics in a portfolio (ac-fixed-income-and-rates), not for macro release reading (ac-macro-and-policy-reading), not for perpetual funding (ac-funding-and-basis).
- ▌ Ac Stock Trading · jiayaoqijia bundleTrading individual equities as a venue: session structure and the overnight gap, single-name liquidity screening, earnings and event risk, halts and news, index and flow events, borrow and short-sale constraints, and the written stock trading record. It covers the recurring process of trading one name; it never recommends a stock or predicts a price. Use when asking "should I trade this stock", "earnings gap risk", "pre-market trading", "LULD halt", "index rebalance", "hard to borrow", "position size for one stock". Not for market-structure mechanics (ac-equity-market-structure), not for order placement tactics (ac-order-execution), not for the investment case (ac-equity-research).
- ▌ Ac Task Planning · jiayaoqijia bundleTask breakdown and planning: slicing a spec into ordered vertical tasks, estimates and forecasts, cadence choice, risk registers, build-vs-buy calls. Use when asking "break this into tasks", "split this epic", "estimate this", "how long will this take", "when can we ship", "scrum or kanban", "what are the risks", "should we build or buy". Not for writing the spec or requirements themselves, choosing the system structure, or step sizing inside the coding loop; those sit outside this skill.
- ▌ Ac Git Workflow · jiayaoqijia bundleVersion-control craft: branching models and trunk-based development, branch protection, merge queues, CODEOWNERS and monorepo layout, plus commit messages, Conventional Commits, rebase versus merge, history repair and changelog generation. Use when asking "which branching model", "trunk-based or GitFlow", "set up branch protection", "add a merge queue", "set up CODEOWNERS", "write a commit message", "rebase or merge", "fix my git history", "which commit broke this". Not for preparing or judging a pull request, finding the defect a commit introduced, or pipeline job design; those sit outside this skill.
- ▌ Ac News Writing · jiayaoqijia bundleNews and announcement writing: the inverted-pyramid news story, the lede, feature structure, attribution, libel check, plus the organisation's own voice — press releases, media statements, holding lines and boilerplate. Use when asking "write this news story", "news lede", "feature structure", "attribution", "libel check", "write a press release", "media statement", "holding line". Not for memos to an internal reader or long-form narrative storytelling; that work sits outside this skill.
- ▌ Ac Spec Writing · jiayaoqijia bundleRequirements and specification writing: user stories, acceptance criteria, NFRs, design docs and RFCs. Use when asking "write a spec", "acceptance criteria for this", "is this requirement testable", "draft the design doc", "RFC for this change", "set the done criteria", "turn this request into requirements", "write the NFRs". Not for slicing an approved spec into a task list, estimating the work, or recording one decision already made; those sit outside this skill.
- ▌ Ac Audit Logging · jiayaoqijia bundleBuilding logs that serve as evidence rather than telemetry: what events an audit trail must record and who its reader is, tamper-evidence through hash chaining and external anchoring, append-only storage and the deletion problem, query patterns for investigators, retention and privacy tension with the trail's purpose, structured event schema for auditability, and the written audit record. It explains how to make a log that can be trusted after the fact; it never recommends a log product and never claims tamper-proof, only tamper-evident. Use when asking "audit log", "tamper evident", "hash chain log", "append only log", "who changed this record", "immutable log", "audit trail design", "compliance evidence", "log integrity", "sequence number gap". Not for observability and SLO telemetry (ac-reliability), not for structured logging in general (ac-reliability), not for access control decisions themselves (ac-security-engineer).
- ▌ Ac Forex Trading · jiayaoqijia bundleTrading spot foreign exchange as a venue: quoting conventions and pip value, venue types and spread quality, rollover and swap points, session liquidity and fixing windows, leverage and weekend gap risk, a repeatable trade process, and the written FX trading record. It explains the mechanics of the market you trade in; it never recommends a currency pair or predicts an exchange rate. Use when asking "how do pips work", "forex lot size", "rollover swap", "ECN or market maker", "forex leverage", "trading the London fix", "why is my EURUSD spread wide at night". Not for hedging a portfolio's currency exposure (ac-currency-and-fx-risk), not for emerging-market convertibility (ac-currency-and-fx-risk), not for general order placement (ac-order-execution).
- ▌ Ac Interrogation · jiayaoqijia bundleInterrogate an idea, plan, or decision before commitment: structured questioning that surfaces assumptions, maps failure modes, tests evidence, forces alternatives, and closes without looping. Eight leaves: interrogation-protocol (session order, cold read, time-box), question-craft (past behaviour over hypotheticals, follow-ups), assumption-audit (load-bearing assumptions, confidence labels), failure-mapping (pre-mortem, inversion, base rates), evidence-dial (falsification test, decide-vs-research gate), alternative-forcing (three alternatives plus do-nothing), steelman-discipline (attack the strongest version), close-and-stop (stop criteria, anti-loop cap, assumption ledger, kill criteria). Use when asking 'grill me on my plan', 'stress-test this idea', 'poke holes in this', 'interrogate this decision', 'what am I missing', 'challenge my assumptions'. Not for: reviewing an existing artifact (use ac-code-review), open-ended research (use ac-deep-researcher), or writing requirements (use ac-spec-writing).
- ▌ Multi Swap · jiayaoqijia bundleExecute multiple token swaps in a single Starknet transaction via Fibrous (default). Supports per-provider selection (avnu, ekubo, or auto to race all). Supports 2-3 swap pairs bundled into one multicall. Use this skill when the user wants to swap multiple token pairs at once, do batch swaps, execute several trades simultaneously, perform parallel swaps, or do bulk trading in one transaction. Also trigger when the user mentions "two swaps", "three swaps", "swap X and Y at the same time", or wants to convert multiple tokens in a single call.
- ▌ Ctf Web Devtools · jiayaoqijia bundleBrowser-native reconnaissance with chrome-devtools-mcp for CTF web targets. Use when the challenge is a JS-heavy page or SPA and you need the exact API requests the page makes, POST bodies, console errors with stack traces, computed CSS, localStorage/secrets, or screenshots — before moving to wire replay with curl/ffuf. Pairs with ctf-web (ops loop) and feeds har_map.py.
- ▌ Ac Architecture · jiayaoqijia bundleSoftware architecture and design records: system structure and styles, C4 views, quality-attribute trade-offs, internal module boundaries, coupling and cohesion, Architecture Decision Records. Use when asking "how should we structure this system", "monolith or microservices", "which architecture style", "will this scale", "C4 view", "where should this code live", "this module does too much", "reduce coupling", "record this decision", "write an ADR". Not for the external API contract itself, line-level code cleanup, or drawing slide-deck diagrams; those sit outside this skill.
- ▌ Ac Credit Curve · jiayaoqijia bundleReading and trading the credit curve: the term structure of spreads for one issuer, slope and shape versus the risk-free curve, roll-down and carry along the credit curve, curve trades and their DV01 weighting, inversion and what it signals, cross-issuer relative value, and the written curve record. It explains the shape and the arithmetic of curve positions; it never recommends a credit or predicts a default. Use when asking "credit curve", "spread curve", "roll down", "credit carry", "curve steepener", "inverted credit curve", "relative value across maturities", "why is the 5y wider than the 10y". Not for single-point spread DV01 and hedging (ac-credit-derivatives), not for the risk-free yield curve (ac-fixed-income-and-rates), not for borrower analysis (ac-bank-and-credit-analysis).
- ▌ Ac Design Taste · jiayaoqijia bundleJudging and critiquing UI and visual-design quality: the judgment layer between building an interface and reviewing its code. Eight leaves: the critique protocol and perception order; typography scale and pairing; spacing grids and optical alignment; color and WCAG contrast math; Nielsen heuristic evaluation run as a protocol; AI-slop anti-patterns; a 0-10 scoring rubric; a taste-development practice loop. Use when asking "critique this UI", "does this design look right", "score this mock", "is this contrast acceptable", "run a heuristic pass", "this UI looks like default AI slop", "sharpen my design taste". Not for: building components (use ac-frontend-ui) or WCAG conformance checklists (use ac-frontend-ui).
- ▌ Ac Frontend UI · jiayaoqijia bundleBuilding web interfaces and making them accessible: component structure and state placement, responsive layout, design systems and design tokens, plus WCAG 2.2 AA conformance — semantics, keyboard paths, contrast, screen-reader checks. Use when asking "build this UI", "make this component", "where should this state live", "make it responsive", "use our design tokens", "is this accessible", "keyboard users can't reach this", "fix contrast", "meet WCAG 2.2 AA". Not for browser automation tests, Core Web Vitals and bundle size, or native mobile UI; those sit outside this skill.
- ▌ Ac Performance · jiayaoqijia bundleMaking software fast, server and browser: measure-first performance budgets, percentile targets and tail latency, profiling, flame graphs and continuous profiling in production, memory profiling and heap snapshot diffs, controlled benchmarking with warmup and variance, latency budget allocation across the call chain, load and soak tests, N+1 and caching fixes, plus Core Web Vitals — LCP, INP, CLS — bundle cost and field versus lab data. Use when asking "this is slow", "profile this", "p99 latency is too high", "set a performance budget", "memory leak", "heap snapshot diff", "benchmark this", "latency budget", "load test this API", "improve LCP", "fix layout shift", "pass Core Web Vitals", "the bundle is too big". Not for SLO definition and alerting (ac-reliability), not for resource exhaustion diagnosis and OOM kills (ac-resource-exhaustion-diagnosis), not for failure injection and capacity headroom (ac-chaos-and-capacity-testing).
- ▌ Ac RAG Systems · jiayaoqijia bundleBuilding the whole retrieval-augmented answering loop as one system: the query transform stage before retrieval, multi-hop decomposition when one query cannot reach the answer, chunk-level citation so every claim traces to a source, grounding verification that catches unsupported answers, refusal behaviour when the corpus is silent, and the written RAG record. It explains how the loop components compose; it never recommends an embedding model and never promises an accuracy. Use when asking "RAG", "retrieval augmented generation", "query rewriting", "multi-hop retrieval", "citation extraction", "grounding check", "hallucination guard", "answer verification", "corpus is silent", "RAG evaluation", "RAG pipeline design". Not for vector index and hybrid search mechanics (ac-retrieval-and-vector-systems), not for the grounding prompt itself (ac-prompt-engineer), not for model evaluation suites (ac-model-evaluation).
- ▌ Ac Reliability · jiayaoqijia bundleRunning a service reliably: OpenTelemetry instrumentation with logs, metrics and traces, SLOs and error budgets, burn-rate alerting, backup and DR targets, incident response and blameless postmortems. Use when asking "add tracing""how do I instrument this service", "why is prod slow",, "set up structured logging", "instrument this service", "set an SLO", "write the alert rule", "error budget", "backup and DR plan", "prod is down", "run the incident", "write the postmortem". Not for rollout mechanics, performance budgets and load tests, or browser-side vitals; those sit outside this skill.
- ▌ Ac Slide Decks · jiayaoqijia bundleSlide-deck craft: make a deck shareable and readable. Eight leaves: brief-and-audience (who decides what after the read; title-and-decision trailer; tone per exec, team, customer), narrative-spine (SCQA and pyramid spine; one story per deck; section headings as claims), slide-grammar (Alley assertion-evidence; one claim per slide; headline-as-conclusion), charts-per-claim (Cleveland-McGill ranking; FT visual vocabulary; when no chart is right), density-and-reading (words per slide; 10-second skim rule; budgets by audience and format), type-and-media (projection type sizes; thirds layout; imagery discipline; animation restraint), accessibility (alt structure; reading order; WCAG 2.2 SC 1.4.3/1.4.11 contrast; captions; file metadata), recurring-qa (naming and versioning; report templates; title, skim, crash tests). Use when drafting, outlining or reviewing a deck. Not for: talk scripts or speaker notes (use ac-narrative-writing), document typesetting (use ac-technical-writing).