Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo. Given a handful of runnable reference tasks, produce thousands of "same-distribution, different-entity" tasks, roll out real trajectories, and emit SFT, RL data. Use this when: you have a tool-calling / MCP / agentic benchmark and want to…
Skill Claude CodeCodex
Convert files and URLs to Markdown. Supports PDF, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, GitHub URLs, images, audio, ZIP, and more. Use when you need to extract content from any document format.
Skill Claude CodeCodex needs its repo
Manage the yao-open-skills public collection. Use this skill whenever the user wants to evaluate whether a local skill should be open sourced, import a local skill into the yao-open-skills repository, register which skills are already public, track GitHub sync status, or update the collection README and catalog after…
Skill Claude CodeCodex
A Chinese-language guide for operating an X/Twitter account, covering topic selection, post and thread writing, audience growth, platform algorithms, account analysis, and monetization. It focuses especially on AI and technology content.
Skill Claude CodeCodex
Design and create AI-agent infrastructure for codebases: AGENTS.md, documentation architecture (docs/), linters with actionable errors (scripts/lint-), harness/ configs, and CI integration. Creates files directly — never writes business/application code.
chen0416ccc-cpu/codex-windows-fast-patch-skill
Skill Codex
Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig availablemodels filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browseruse gates, Goal command gates, Windows…
Skill Claude CodeCodex
Hunting skill for race condition vulnerabilities. Built from 12 public bug bounty reports including modern HTTP/2 single-packet attack cases (James Kettle DEF CON 2023 "Smashing the State Machine"; RyotaK / Flatt Security 10,000-request first-sequence-sync expansion 2024). Covers coupon double-redemption, gift-card…
matlab/simulink-agentic-toolkit
Skill Claude CodeCodex
Create and register Simulink block icons programmatically. Use when asked to create an icon, generate a block icon, design an SVG icon for a Simulink block, register an icon, or help with IconEditor features like visibility conditions, layout constraints, parts, port labels, dynamic text, or block frame shapes (e.g. a…
Skill Claude Code
Iterative strategy generation and evaluation system. Use when the user wants to evaluate agent output quality, run improvement loops, queue tasks for background evaluation, check run status, inspect runtime artifacts and session branch lineage, or discover available scenarios. Provides LLM-based judging with…
Skill Codex
A teaching skill for machine learning, deep learning, generative AI, large language models, AI agents, and speech modeling, using a structured, intuition-first approach.
Skill Claude CodeCodex
A news-aggregation tool that fetches and filters current articles, posts, papers, and newsletters from many technology, research, and international news sources. It can also analyze the collected material in depth.
fancyboi999/ai-engineering-from-scratch-zh
Skill Claude CodeCodex
A release-checking skill for evaluating whether an agent skill bundle is complete, safe, correctly triggered, and portable to its target host.
minsight-ai-info/AI-Search-Hub
Skill Codex
Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax. Use this skill when the user wants to ask one of those sites a prompt, auto-start or attach to a Chrome DevTools session on port 9222, seed an isolated debug browser profile from the user's local browser…
Skill Claude CodeCodex
Use, configure, diagnose, and retrieve exact evidence with the Hermes-LCM lossless context plugin.
Skill Claude CodeCodex
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
Skill Claude CodeCodex needs its repo
Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…
Skill Codex
Review generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WooCommerce APIs: wcgetorder, wcgetorders, wcgetproduct, WC() cart or session…
Skill Claude CodeCodex needs its repo
A lifecycle system for managing an Obsidian knowledge base, which is a folder of linked notes. It organizes raw material, AI-maintained wiki pages, and generated views into separate layers.
Skill Claude CodeCodex
Implements data loss prevention policies using Microsoft Purview to protect sensitive information across Exchange Online, SharePoint, OneDrive, Teams, endpoint devices, and Power BI. The analyst configures sensitivity labels with encryption and content marking, creates DLP policies using built-in and custom sensitive…
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Skill Claude CodeCodex
Scaffold a TanStack app with tanstack create using --framework, --build-tool, --template, --toolchain, --deployment, --add-ons, --blank, and --router-only. Covers flag compatibility, non-interactive defaults, and intent-preserving command construction.
Skill Claude CodeCodex
Fix failing tests in a GitHub repo or PR. Use when the brief skill is fix-tests or the user wants the named test command to exit 0.
Skill Claude CodeCodex
Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects. Trigger on "fizz", "generate fuzz suite", "build fuzz harness", "stateful fuzzing", "fuzzing harness", "property testing", and "invariant suite".
Skill Claude CodeCodex
INVOKE WHEN: Starting any task — query first (cq catches blind spots your training data missed: stale versions, integration gotchas, undocumented quirks) You just resolved a non-obvious error, confusing error message, or surprising tool behavior — present a draft KU to the user and call propose if they approve…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: