AI & ML

001tmf Bundle

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method nativ

algoderiv Bundle

RiceQuant RQData Python API - 米筐金融数据Python接口，用于获取中国A股、港股、期货、期权、基金、债券、宏观经济和另类数据。当使用rqdatac编写量化交易和金融分析Python代码时使用此skill。

gabrielmoreira Bundle

Review generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactors tests, before presenting, committing, or merging them. Use for pytest (test_*.py, *_test.py), PHPUnit/Pest (*Test.php), Jest/Vitest (*.test.ts, *.spec.js), Go (*_test.go), files under tests/, __tests__/, or spec/, and review requests like 'write tests for X', 'add tests', 'test this', 'review these tests', or PR diffs containing tests. Can also guide test writing when explicitly invoked before the work. This skill is the quality gate that prevents AI-generated test bloat. DO NOT USE for production or implementation code review (use clean-code-guard), CI or test-runner configuration, running or debugging tests, or general architecture discussion.

gabrielmoreira Bundle

Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output, output parser, RAG, vector store, a chat assistant/bot, or human-in-the-loop review. Covers Agent-vs-chain-vs-classifier choice, the model/memory/tools/outputParser slots, tool names/descriptions as prompt, structured output with autoFix, memory, RAG, human review, and chat topologies.

diegosouzapw Skill

Query available AI models, list model aliases, and browse the full model catalog from the CLI. Filter by provider, search by capability, and resolve model name variants.

diegosouzapw Skill

Manage the LLM response cache. View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching thresholds.

exa-labs Skill

Use Exa Agent for multi-step web research, list-building, enrichment, structured output, run continuation, and coverage validation. Exa Agent can access additional data providers: fiber, financial_datasets, similarweb, baselayer, affiliate, particle, and jinko.

ferminrp Bundle

Canonical registry and recipes for Ripio wFiat LATAM stablecoins (wARS, wBRL, wMXN, wCOP, wPEN, wCLP): contract addresses, CoinGecko ids, chains, and how to query prices/DEX via CoinGecko, GeckoTerminal, and Uniswap v4 subgraph. Always present wFiat prices inverted (fiat per 1 USD, e.g. USD/ARS). Use when the user mentions "wARS", "wBRL", "wMXN", "wCOP", "wPEN", "wCLP", "wfiat", "wFiat", "Ripio stablecoin", "stablecoin local Ripio", "peso wrapeado", "wrapped ARS/BRL/MXN/COP/PEN/CLP", or asks for addresses/prices/pools of these tokens.

first-fluke Bundle

Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests. Use for bug, debug, error, crash, traceback, exception, and regression work.

first-fluke Bundle

Multi-vendor AI image generation with authentication-aware parallel dispatch. Routes to Codex (gpt-image-2 via ChatGPT OAuth), Antigravity (Gemini-family "nano-banana" image models via `agy` CLI + Gemini Code Assist; exact model chosen internally by agy), and Pollinations (flux/zimage, free with signup). Use for image generation, image creation, visual asset generation, and AI art.

first-fluke Bundle

Analyze conversation histories from multiple AI tools (Grok, Claude, Codex, Gemini, Qwen, Cursor, Antigravity) and generate themed daily/period work summaries. Filter by date or time window.

first-fluke Bundle

Short-form, explainer, and demo video generation via a key-optional 3-tier router. Composes scripts, oma-voice narration, oma-image/oma-slide/stock visuals, key-free captions, and a per-run agent-authored Remotion composition (always-latest Remotion + remotion-dev/skills) into reproducible run directories. Routes three modes — shorts/reels (9:16), explainer (16:9 README/code/data), and demo/walkthrough (screen capture from human-recorded video). Use for video, shorts, reels, short-form, demo, explainer, walkthrough, screencast, web capture, video generation, 영상, 숏폼, 쇼츠, 릴스, 데모, 설명 영상.

gaasher Skill

Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor.

gaasher Skill

Use when the user wants to adversarially stress-test a guardrail, classifier, prompt, or API they own or are authorized to test, to surface the distinct ways it fails. Generates adversarial inputs, runs them through the target and a ground-truth oracle, logs every target-vs-oracle disagreement as a failure de-duplicated by technique class, and loops until rounds stop surfacing new classes. Produces a catalogue of distinct, reproducible failures — the attacker half of a find→fix setup. Not for patching the target, and not for attacking systems the user does not own or have permission to test.

gaasher Skill

Use when the user has a coding prompt — a feature, bug fix, or refactor — and wants it implemented end to end by a self-checking software loop, not a single pass. It refines the prompt into an executable plan (running the plan-loop internally), then executes the plan task by task: an Engineer subagent implements each PR-sized task editing only source, a separate QA subagent authors the tests that prove the task's acceptance criteria (or grades quality only when tests already cover them), runs the task's tests plus the full accumulated regression suite, and grades the code against a strict conciseness/readability/style-match rubric; the Engineer and QA loop on each task until the tests pass and the quality gate holds, then it commits and opens a pull request for the task — stacked PRs (one per task, each based on the prior) by default, or one combined PR — and moves to the next task. Author and critic have disjoint write scopes (Engineer owns source, QA owns tests) so neither can game the gate. Not for produci

hkuds Skill

CCXT unified crypto exchange library (100+ exchanges). Free public market data. Fallback when OKX is unavailable.

ilang-ai Bundle

Stop learning prompt engineering. Tell AI what you want in plain language — AI writes a structured instruction for you in I-Lang. Copy it to other AIs as a well-structured starting point. Zero prompt skills needed. Generates text instructions only, no code, no install, no credentials. Results may vary by model.

jdrhyne Skill

Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.

jdrhyne Bundle

Premium UI/UX design auditor with Jobs/Ive philosophy. Use when reviewing, evaluating, or elevating existing UI — triggers on "audit my design", "review UI", "make it feel premium", "design review", "UX audit", "elevate the design", "Jobs/Ive style", or when asked to improve visual quality of an existing interface without changing functionality.

kan-h Bundle

llama.cpp Windows 平台多模型部署与优化。涵盖：Router Mode 多模型管理、Gemma 4/Qwen/Phi-4 模型部署、QAT–MTP 推理优化、RTX 5060 Ti 16GB 显存调优、CPU 内存受限场景适配、预编译包快速部署、Preset 差异化配置、WSL2 通路配置、Agent/API 接入、Tool Calling 工具调用测试、纯 CPU 工具调用脚本、BAT 脚本编码修复。Use when: 部署 llama.cpp 服务、配置多模型路由、优化推理性能、排查显存/内存溢出、配置 MTP 投机解码、迁移 Qwen/Gemma 模型、测试模型工具调用、搭建纯 CPU 推理、修复 .bat 闪退/乱码。English: deploying llama.cpp on Windows, configuring Router Mode, optimizing GPU/CPU inference, troubleshooting OOM, setting up MTP speculative decoding, migrating between Gemma 4 and Qwen models, testing tool calling, running CPU-only inference, fixing .bat encoding crashes.

kayforkind Skill

Embeds alibaba/page-agent as an in-page GUI agent (DOM-as-text, OpenAI-compatible LLM) so end users drive a site with natural language. Use when adding an NL copilot inside a SaaS/admin app or evaluating page-agent against Ollama, Qwen, OpenAI, or OpenRouter. Not for an agent driving a browser from outside (Playwright/Browserbase) or screenshot/multimodal grounding. Never ship the demo CDN LLM proxy to production.

kayforkind Skill

Configures the Cursor CLI status line (statusLine.command in cli-config.json): stdin JSON for model, context %, git/worktree, ANSI stdout above the prompt. Use when the user mentions statusline, statusLine, CLI status bar, prompt footer, or a session context bar. Not for Starship, oh-my-posh, VS Code status bar, or tmux. Never block longer than timeoutMs; the line is local and does not spend API tokens.

kid-sid Bundle

Use when defining request/response schemas, writing custom validators, controlling serialization for PATCH endpoints, validating non-model data with TypeAdapter, or configuring app settings from environment variables with pydantic-settings.

kid-sid Bundle

Use when building or debugging the Agentex ADK temporal agent type — structuring workflows and activities, handling signal routing, managing state across replays, or diagnosing workflow failures and retry exhaustion. For standalone Temporal workers outside of Agentex, use general-temporal.

lambdatest Skill

Generates Protractor E2E tests for Angular/AngularJS apps in JS/TS. NOTE: Protractor is officially deprecated — recommend Playwright or Cypress. Use when user mentions "Protractor", "element(by.model())", "Angular E2E". Triggers on: "Protractor", "element(by.model)", "Angular E2E test", "protractor.conf".

liamgvchi Bundle

Analyze still images and design restrained, image-specific motion for image-to-video generation. Use when the user provides one or more images, screenshots, posters, collages, illustrations, editorial graphics, or an image folder and asks how the image should move, which elements must stay fixed, whether it should move at all, or how to write a prompt for Jimeng or another image-to-video model. Also use for requests about preventing text, paper, layouts, frames, or graphic elements from drifting during animation. Do not use for ordinary image generation, image editing, or analysis of an existing finished video unless the user wants a reusable still-image motion prompt from it.

manaflow-ai Bundle

Run end-user cmux diagnostics. Use when cmux hooks, notifications, session restore, settings, browser automation, socket access, CLI control, or agent resume behavior is not working, or when the user asks for a cmux health check, doctor report, or support-safe debug summary.

mblode Bundle

Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.

okx Skill

Use this skill when the user asks to: 'find a trading skill', 'search for skills', 'install a skill', 'add a skill', 'download a skill', 'browse skill marketplace', 'what skills are available', 'update a skill', 'check for skill updates', 'remove a skill', 'uninstall a skill', 'list installed skills', 'show my skills', 'skill categories', 'verify skill signature', 'verify installed skill', 're-verify a skill', 'check skill integrity', or any request to discover, install, update, verify, or manage AI trading skills from the OKX Skills Marketplace. This skill covers searching, browsing categories, installing via CLI, downloading zip packages, checking for updates, removing installed skills, and verifying Ed25519 signatures of installed skills. Requires API credentials for marketplace API access. Do NOT use for placing orders (use okx-cex-trade), market data (use okx-cex-market), or bot management (use okx-cex-bot).

openakita Bundle

FlyAI travel search and booking skill powered by Fliggy MCP. Search flights, hotels, attractions, trains, concerts, and travel deals with natural language. Supports diverse travel scenarios including individual, group, business, family trips. No API key required for basic features.

openakita Bundle

Install, configure, and add MCP servers to the OpenAkita system. Use when the user needs to install MCP packages (npm/pip/uvx), connect remote HTTP/SSE MCP services, set up custom local MCP servers, or manage MCP server configuration and lifecycle.

paulrberg Bundle

Brainstorm with the user to generate, combine, and refine non-obvious ideas into a promising concept. Use when the user wants to brainstorm, ideate, explore possibilities, escape obvious approaches, or find a creative solution.

paulrberg Bundle

Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.

rlaope Skill

[omh] Policy overlay for live lookups - add provider, freshness, units, and source-quality gates after preferring native live-data tools for ordinary weather, finance, sports, maps, and time-zone requests. Use when the user says: live-info-operator, live info operator, live information, real time information, real-time information, weather today, current weather, weather forecast.

rlaope Skill

[omh] Hermes Deep Interview workflow: one-question-at-a-time clarification. Use when the user says: deep-interview, interview, clarify, feature shaping, ambiguous product request, one question, 要件を詰めて, 曖昧な要求.

rohitg00 Skill

Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.