majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 2 weeks ago last updated
- ▌ Over · majiayu000 bundleUse as load-bearing work lands, or when the user asks to debrief, hand off recent work, or check what they actually own versus what AI carried. Triggers on "debrief", "what do I own", "hand over", "hand it back", "over", and recently shipping a load-bearing decision the human has not reasoned through.
- ▌ Saga · majiayu000 bundleUse when a user runs saga or asks to autonomously build a sizable feature. Produces a spec tree, delegates to worker subagents in isolated worktrees, validates at each milestone, and gates user acceptance before VCS commit. Not for executing a given plan — use subagent-driven.
- ▌ Xray · majiayu000 bundleInvestigate how a concept, code path, application, network flow, system, incident, document, or local artifact actually works, then deliver a two-depth visual HTML explainer with a dead-simple big-picture first layer and source-backed technical depth behind it. Use when the user invokes $xray, asks how something works under the hood, wants a module or app behavior traced across boundaries, requests web, code, network, or safe static artifact research before explanation, or asks for an evidence-backed explainer. Do not use for answer-only definitions, general web design, full codebase audits, or invasive binary reverse engineering without explicit authorization.
- ▌ Nf · majiayu000 bundleConduct in-depth feature discovery interview to explore, challenge, and document a new feature. Use when asked to 'detail a feature', 'explore a new feature', 'feature discovery', 'interview about feature', or 'spec out a feature'. NOT for quick brainstorming (use /brainstorm), NOT for PRD/JTBD docs (use /product), NOT for implementation tasks (use /ct).
- ▌ Rr · majiayu000 bundle코드 리뷰. 작업 후 변경사항을 Z.AI 모델로 검토하고, Codex가 결과를 다시 검증해 유효한 이슈만 정리한다. /rr 또는 'GLM 리뷰' 요청 시 사용.
- ▌ Sr · majiayu000 bundleConduct comprehensive code review before PR merge. Use when asked to 'review code', 'start code review', 'review PR', 'check before merge', or 'pre-merge review'. NOT for addressing review comments (use /prc), NOT for code exploration (use /code-analysis).
- ▌ Wip · majiayu000 bundleWork-in-progress prompt workflow. Log, improve, and propose prompt patterns from the skills library with safe mutation guardrails.
- ▌ Mac · majiayu000 bundleSwitch to macOS development mode. Copies docs/mac-claude.md to the root CLAUDE.md file, applying macOS-specific instructions. Use when switching from Windows to a macOS computer.
- ▌ Elves · majiayu000 bundleAutonomous multi-batch development agent for long unattended runs. Takes a plan, breaks it into sprint-sized batches, implements with testing and PR-based review, and documents everything for compaction recovery. Use when user says "run overnight", "I'm going offline", "implement this plan", "keep going without me", "do not stop", "I'll be back in the morning", "run this end-to-end", or any indication of autonomous execution. Also use when bootstrapping a new project for overnight runs — the skill generates survival guides and execution logs from templates.
- ▌ Jules · majiayu000 bundleDelegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delegate to Jules', 'send to Jules', 'ask Jules to', 'check Jules sessions', 'pull Jules results', 'jules add tests', 'jules add docs', 'jules review pr'. Handles: bug fixes, documentation, features, tests, refactoring, code reviews. Works with GitHub repos, creates PRs.
- ▌ Nexus · majiayu000 bundleNexus conversational PI agent architecture, development, and deployment. Use when working on the Nexus orchestrator, gateway, or tools.
- ▌ Ralph · majiayu000 bundleAutonomous feature development - setup and execution. Triggers on: ralph, set up ralph, run ralph, run the loop, implement tasks. Two phases: (1) Setup - chat through feature, create tasks with dependencies (2) Loop - pick ready tasks, implement, commit, repeat until done.
- ▌ Train · majiayu000 bundleAuto-generate custom agents and skills for remaining capability gaps after assembly. Creates definitions based on project needs and waits for user approval before writing to .claude/.
- ▌ Adhd · majiayu000 bundleADHD-optimized code explainer. Generates layered, scannable explanations with hooks, maps, and progress markers.
- ▌ Math · majiayu000 bundleMulti-layer cognitive stack for machine-verified mathematical problem solving across 14 sub-disciplines.
- ▌ Mode · majiayu000 bundleUse when the user wants to change optimization aggressiveness, switch between aggressive/balanced/thorough modes, or adjust token-saving behavior.
- ▌
- ▌ Cs Ml · majiayu000 bundleML: supervised/unsupervised/RL, CNN/RNN/Transformer, training, evaluation, MLOps, LLM fine-tuning
- ▌
- ▌
- ▌
- ▌ Ds · majiayu000 bundleThis skill should be used when the user asks to 'start data analysis', 'brainstorm analysis approach', 'plan a data project', 'clarify analysis requirements', or needs the full 5-phase data science workflow with output-first verification.
- ▌ Re · majiayu000 bundleExplicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration.
- ▌ API Sdk · majiayu000 bundleUse when working with the TypeScript SDK for making API calls to Bknd, handling authentication, and managing data operations from client or server code. Covers Api class initialization, CRUD operations, auth methods, and module-specific APIs.
- ▌ Cashout · majiayu000 bundleSell Base USDC for fiat with cashout from @usdctofiat/offramp. Use when a user wants a non-custodial cash-out from a real Base wallet into Venmo, Revolut, PayPal, Zelle, Monzo, Chime, or Mercado Pago. Require an explicit fast or best mode. Cash App new creation is disabled in the SDK.
- ▌ Clinpgx · majiayu000 bundleQuery the ClinPGx API for pharmacogenomic gene-drug data, clinical annotations, CPIC guidelines, and FDA drug labels
- ▌ Doc Ctr · majiayu000 bundleCreate Data Contracts (CTR) - Optional Layer 9 artifact using dual-file format (.md + .yaml) for API/data contracts
- ▌ Integrating Jupiter · majiayu000 bundleComprehensive guidance for integrating Jupiter APIs (Ultra Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.
- ▌ Postman · majiayu000 bundlePostman API platform for testing and documentation. Use for API testing.
- ▌ Sanctum · majiayu000 bundleComplete Sanctum SDK for liquid staking, LST swaps, and Infinity pool operations on Solana. Use when working with LSTs (mSOL, jitoSOL, bSOL, INF), staking SOL, swapping between liquid staking tokens, or integrating Sanctum's liquidity infrastructure.
- ▌ Shioaji · majiayu000 bundleShioaji Taiwan financial trading API guide. Use when trading stocks/futures/options on Taiwan markets, subscribing to real-time market data, querying account info, or building automated trading systems. Shioaji 台灣金融交易 API 指南。適用於:股票/期貨/選擇權交易、即時行情訂閱、帳務查詢、自動交易系統開發。
- ▌ Weather · majiayu000 bundleGet current weather and forecasts using free APIs (no API key required). Use when asked about weather, temperature, forecasts, or climate conditions for any location.
- ▌ Web API · majiayu000 bundleREST + GraphQL + tRPC API design: OpenAPI 3.1, auth JWT/OAuth2, rate limiting, pagination
- ▌ Woo API · majiayu000 bundleBuild and consume WooCommerce REST API v3 endpoints — authentication, custom endpoints, extending existing resources, webhooks, and batch operations. Use when creating custom API endpoints or integrating external systems with WooCommerce.
- ▌ Commit · majiayu000 bundleStage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "open a PR", "merge to main", "let's commit this", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Runs the standard commit-PR-merge cycle; never force-pushes or skips hooks.
- ▌ Deploy · majiayu000 bundleRender Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use when user says "deploy", "publish the slides", "ship to pages", "push the lecture live", "render and publish", or after Quarto edits that need to go public. NOT for local Quarto render only — use `quarto render` directly for that.
- ▌ Skill · majiayu000 bundle从数据剖析到出版级成图的完整可视化工具。先做数据剖析(列类型/样本量/分布/异常值/分组结构/相关性), 再结合论证目标推荐图型,主动拦截科研画图经典错误,产出 Nature / Science / IEEE / Elsevier / PNAS / 中文核心期刊级别的成图。覆盖数据 EDA、图表契约、选图决策、出版级绘制、程序自检 + AI 读图闭环、多格式 导出和文件审计。数学建模场景额外支持三类图体系(原始数据/过程/结果)和子问题覆盖检查。 当用户涉及论文配图、科研画图、数据可视化、选图、期刊投稿图、figure、出版级图表、matplotlib、seaborn、 plotly、误差棒、显著性标注、色盲安全配色、矢量图导出、中文论文图表、多面板时使用。
- ▌ Rename · majiayu000 bundle⚡ ULTRA-FAST skill - executes in seconds using pure Bash (no file reading to context).
- ▌ Revise · majiayu000 bundleRevise the most recent or provided p11 shareable document based on comments/replies and publish a new version. Use when Claude Code should apply clear reviewer decisions to a p11 document.
- ▌ Wizard · majiayu000 bundleGenerate an interactive bash wizard that walks a human through a manual procedure: third-party setup, a one-off migration, or an A to B state transition. It opens URLs, captures values, confirms each step, and writes .env entries and GitHub Actions secrets. Author it, never run it.
- ▌
- ▌ AI App · majiayu000 bundleFull-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications. Triggers: chatbot, chat app, agent dashboard, AI application, Next.js AI, useChat, streamText, ai-elements, build AI app, create chatbot
- ▌ Assign · majiayu000 bundleTask Assignment Agent - Assigns Native Tasks to worker terminals, updates ownership, and syncs progress tracking. Pipeline Position: After /orchestrate, Before /worker Handoff: Workers run /worker start
- ▌ AWS V2 · majiayu000 bundleMigrate from AWS SDK for Java v1 (com.amazonaws) to v2 (software.amazon.awssdk). Use when projects need to move away from deprecated AWS SDK v1 to the modern v2 API.
- ▌ Df Az CLI · majiayu000 bundleThis skill should be used when working with Azure DevOps from the command line. Trigger when user mentions az devops, az repos, az pipelines, az boards, or asks about managing PRs, work items, pipelines, or repositories in Azure DevOps. Also trigger for questions about Azure DevOps CLI setup, authentication, or querying work items.
- ▌ Banana · majiayu000 bundleGenerate images using Google's Gemini image generation model with Deno. Use this skill when the user wants to create AI-generated images, perform image-to-image transformations, or generate visual content from text prompts. Triggers include requests like "generate an image of...", "create a picture of...", "make an image with...", or "transform this image to...".
- ▌ Bitrix · majiayu000 bundleBitrix24 REST API via curl. Use this skill to manage CRM (leads, deals, contacts), tasks, and users.
- ▌ Bizdev · majiayu000 bundleBusiness Development - assign partnership strategy, market expansion, deal structuring, and ecosystem tasks
- ▌ Bizops · majiayu000 bundleBusiness Operations - assign business cases, financial analysis, KPI tracking, and data analysis tasks
- ▌ Blazor · majiayu000 bundleGuidelines for Blazor development including component lifecycle, state management, and performance optimization
- ▌ Bugfix · majiayu000 bundleInvestigates and fixes bugs systematically with root cause analysis. Use when asked to debug, troubleshoot, fix a bug, investigate an issue, or find why something is broken. Creates reproduction tests and verifies fixes.
- ▌ Bundle · majiayu000 bundleBundle and share code as gists or markdown. Use to create shareable code bundles, extract imports, and create GitHub gists.
- ▌ Ca Adr · majiayu000 bundleAuthor a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/.
- ▌ Cancel · majiayu000 bundleCancel active Loop. Use when loop needs to stop early, done iterating manually, want to abort, or change direction. Triggers on "cancel loop", "stop iterating", "end loop", "terminate loop", "abort loop", "kill loop", "stop the loop", "halt". Graceful termination that preserves completed work.
- ▌ Canvas · majiayu000 bundleDisplay HTML content on connected Clawdbot nodes (Mac app, iOS, Android).
- ▌ Capcom · majiayu000 bundleCheck mission status and progress via fresh subagent. Queries Beads for features, tasks, bugs, and recent work activity. Keeps HOUSTON context lean.
- ▌ Cheney Practical Go · majiayu000 bundleWrite Go code in the style of Dave Cheney, Go community leader. Emphasizes practical patterns, clear error handling, and performance awareness. Use when writing production Go that needs to be maintainable and performant.
- ▌ Cherri · majiayu000 bundleUse when writing Apple Shortcuts as code using Cherri language. Covers syntax, actions, compilation, and common patterns.
- ▌ CI Fix · majiayu000 bundleFix GitHub Actions CI failures using GitHub CLI (gh): inspect runs/logs, identify root cause, patch workflows/code, rerun jobs, and summarize verification. Use when GitHub Actions CI is failing or needs diagnosis.
- ▌ Claims · majiayu000 bundleProcess expense claims by matching YNAB transactions with uploaded receipts. Use when the user mentions claims, expenses, reimbursements, receipts, or YNAB TODOs.
- ▌ Get Shit Done · majiayu000 bundleStructured spec-driven workflow for planning and executing software projects with Claude Code.
- ▌ Cmedia · majiayu000 bundleC-Media Electronics MPN encoding patterns, USB audio controller decoding, and handler guidance. Use when working with C-Media audio ICs or CMediaHandler.
- ▌ Co2lpm · majiayu000 bundleValidates code and provides physics reasoning for the 0-D CO2 lumped-parameter model for geothermal reservoirs. Use when modifying ODE solvers, parameter classes, emissions calculations, or concentration dynamics. Also use when debugging simulation behavior, explaining physics concepts, or planning changes to physics-related code.
- ▌ Codeql · majiayu000 bundleCodeQL is a static analysis framework that queries code as a database. Use when you need interprocedural analysis or complex data flow tracking.
- ▌
- ▌ Colima · majiayu000 bundleUse when Docker commands fail with "Cannot connect to Docker daemon", when starting/stopping container environments, or when managing multiple Docker contexts on macOS - provides Colima lifecycle management, profile handling, SSH commands, and troubleshooting
- ▌
- ▌ Colors · majiayu000 bundlePreview CYNIC's color system with semantic colors, health indicators, progress bars, and Dog colors (Sefirot). Use when testing terminal colors or wanting to see the visual theme.
- ▌ Common · majiayu000 bundleShared utilities for Gemini-based skills including API key management, Vertex AI configuration, and client helpers. Use as dependency for skills requiring Gemini API access.
- ▌ Cortex · majiayu000 bundleAutomatic session tracking and memory system for Claude Code. Activates when working in git repositories to track file changes, commits, and session context. Creates .cortex_log.md (session history), .cortex_status.json (current state), and .cortex_handoff.md (next steps) for session continuity across conversations. Use when needing persistent memory, session handoffs, or work history tracking.
- ▌
- ▌ Nlss · majiayu000 bundleWorkspace-first R statistics suite with subskills and agent-run metaskills (including run-demo for guided onboarding, explain-statistics for concept explanations, explain-results for interpreting outputs, format-document for NLSS format alignment, screen-data for diagnostics, check-assumptions for model-specific checks, and write-full-report for end-to-end reporting) that produce NLSS format tables/narratives and JSONL logs from CSV/SAV/RDS/RData/Parquet. Covers descriptives, frequencies/crosstabs, correlations, t-tests/ANOVA/nonparametric, regression/mixed models, SEM/CFA/mediation, EFA, power, reliability/scale analysis, assumptions, plots, missingness/imputation, data transforms, and workspace management.
- ▌ Node · majiayu000 bundleNode.js LTS runtime and server-side JavaScript patterns for INVOOPAY backend. Use when: working with backend services, async operations, crypto, Buffer handling, or Node.js APIs.
- ▌
- ▌ Nuke · majiayu000 bundleKill all shella processes and reset state. Nuclear option when things are broken. Use with caution.
- ▌ Nuqs · majiayu000 bundlenuqs (type-safe URL query state) best practices for Next.js applications. This skill should be used when writing, reviewing, or refactoring code that uses nuqs for URL state management. Triggers on tasks involving useQueryState, useQueryStates, search params, URL state, query parameters, nuqs parsers, or Next.js routing with state.
- ▌ Odoo19 Oca Devops · majiayu000 bundleBuild enterprise-grade Odoo 19 ERP using OCA community modules instead of Enterprise licenses. Scaffold modules, vendor OCA dependencies, generate production Docker deployments, and deploy to DigitalOcean with Supabase - saving $4,728/year in licensing costs.
- ▌ Ooda · majiayu000 bundleOODA loop decision framework (Observe, Orient, Decide, Act). Use for complex decisions, problem-solving, unclear situations, or when someone is jumping to solutions without analysis.
- ▌ Osay · majiayu000 bundleAI-powered text-to-speech CLI tool. Use for pronunciation queries, reading text aloud, generating audio files, or language practice. Triggers on "how to pronounce", "say this", "read aloud", "TTS", "text to speech", "speak", or audio generation requests.
- ▌ Page · majiayu000 bundleGuide for creating page components. This skill should be used when users want to create a new page component (or update an existing page component)
- ▌ Papi · majiayu000 bundleCLI reference for paperpipe (papi). Use BEFORE MCP RAG tools. For listing, searching, showing, adding papers.
- ▌
- ▌ Pep8 · majiayu000 bundleEnforces modern Python 3.11+ coding standards, PEP 8 compliance, and type-hinting best practices automatically. This skill should be used when writing, reviewing, or refactoring Python code to ensure consistency with PEP 8, proper type hints, Google-style docstrings, and modern Python idioms.
- ▌ Perf · majiayu000 bundlePerformance profiling and optimization. Use for benchmarking code, analyzing performance, running Lighthouse audits, and finding hotspots.
- ▌ Phab · majiayu000 bundleUse phab CLI for Phabricator task management, code review workflows, revision creation and updates, with Git integration and auto-detection features.
- ▌ Pike Simplicity First · majiayu000 bundleWrite Go code in the style of Rob Pike, co-creator of Go. Emphasizes radical simplicity, concurrency through communication, and composition over inheritance. Use when writing Go that should be clear, concurrent, and maintainable.
- ▌ Pods · majiayu000 bundleAggregate management for all AI pod services. Provides status overview and bulk operations across all pod containers (ollama, jupyter, comfyui, openwebui, localai, fiftyone, jellyfin, runners).
- ▌ Pull · majiayu000 bundlePull request and merge request management. Use when user asks to view PR/MR comments, review feedback, iterate on changes, manage remote branches, or work with GitHub/GitLab pull requests.
- ▌ Puya · majiayu000 bundlePuya Semiconductor MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Puya SPI NOR Flash memory components or PuyaHandler.
- ▌ Pytd · majiayu000 bundleExpert assistance for using pytd (Python SDK) to query and import data with Treasure Data. Use this skill when users need help with Python-based data analysis, querying Presto/Hive, importing pandas DataFrames, bulk data uploads, or integrating TD with Python analytical workflows.
- ▌ Pyth · majiayu000 bundleComplete guide for Pyth Network - decentralized oracle providing real-time price feeds for DeFi. Covers price feed integration, confidence intervals, EMA prices, on-chain CPI, off-chain fetching, and streaming updates for Solana applications.
- ▌ Qwik · majiayu000 bundleBuilds instant-loading web applications with Qwik's resumable architecture and fine-grained lazy loading. Use when creating highly performant sites, when user mentions Qwik, resumability, zero hydration, or O(1) startup time.
- ▌ Repo · majiayu000 bundleCreate repository context bundles and code maps. Use to share codebase context, generate documentation, and understand project structure.
- ▌ Rice · majiayu000 bundleRICE prioritization scoring initiatives by Reach, Impact, Confidence, and Effort. Use for feature prioritization, roadmap planning, or when comparing initiatives objectively.
- ▌ Riff · majiayu000 bundleGenerate multiple Vibes app variations in parallel with business models and rankings. Use when exploring different interpretations of a broad objective or loose creative prompt.
- ▌ Rlhf · majiayu000 bundleUnderstanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.
- ▌ Rloo · majiayu000 bundleReinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction techniques for stable RL training. Includes thinking-aware patterns.
- ▌ Room · majiayu000 bundleRooms are intertwingled navigable activation context maps. Entering = calling. Exiting = returning.
- ▌ Roth Detection Engineering · majiayu000 bundleApply Florian Roth's detection engineering methodology with YARA and Sigma rules. Emphasizes portable detection logic, community sharing, and signature quality. Use when creating detection rules that work across platforms.
- ▌ Rsdt · majiayu000 bundleSpecification-driven development workflow for creating requirements, design, and tasks. Use when the user wants to plan new features, fix bugs with proper specifications, refactor code systematically, or needs help breaking down complex implementation work. Creates requirement-spec.md (Japanese), design.md (Japanese), and tasks.md (Japanese) in RsDT/<feature_name>/ directory.