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 Code needs its repo
Scaffold a conforming AI-layer artifact — a rule, skill, hook, agent, or output style — that already passes the format checks, then verify it. Use when adding any new AI-layer artifact — a shared one under .agents/ or a Claude-only one under .claude/ — so it matches the existing shape instead of drifting.
Skill Claude CodeCodex needs its repo
Sync selected WeChat desktop chats to JSON on the host, generate an optional LLM report, and answer questions from the captured messages.
Skill Claude Code
2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection.
Adam-Bull/Codex-thread-toolkit
Skill Codex
Relink Codex threads to a new workspace folder path after a local folder rename. Use when chats appear under an old folder, show "working directory missing", or jump folders after opening due to stale state/index. Performs safe backup-first migration of JSONL cwd fields plus SQLite thread cwd index and verifies…
Skill Claude CodeCodex
Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.
Skill Claude CodeCodex
A Chinese-language skill for running SBTI, an informal 30-question personality test with 27 humorous personality types, for a person or an AI agent.
Skill Claude CodeCodex
A tool that scans a code project and creates guidance documents for both AI coding agents and human developers, including AGENTS.md and Cursor rule files.
ocbunknown/fastapi-claude-template
Skill Claude Code
Use when integrating an external HTTP API (Stripe, GitHub, Twilio, a payment provider, etc.) into the project. Enforces the Client + Service split — Client lives in infrastructure and returns raw vendor-shaped Pydantic responses, Service lives in application and maps raw responses to application Result types. Covers…
Skill Claude CodeCodex
Summarizes long text into key bullet points.
Skill Claude CodeCodex
Technical SEO auditor for programmatic pages, landing pages, and content clusters. Use when user says "seo audit", "check seo", "seo review", "technical seo", "schema.org check", "sitemap review", "indexability", "seo skill", or when reviewing any plan/code that involves search engine optimization, programmatic page…
Skill Claude CodeCodex
Invoke when writing tests, reviewing test quality, or setting up test infrastructure. Contains project-specific testing framework conventions, fixture patterns, and coverage expectations.
Skill Claude CodeCodex
Create or edit Python routines for market analysis, monitoring, and data visualization. Use when the user asks to create, modify, or fix a routine in the routines/ folder.
Skill Claude CodeCodex
Helps set up C# library projects that provide nodes to vvvv gamma — project directory structure, Initialization.cs with AssemblyInitializer, service registration via RegisterService, IResourceProvider factories, ImportAsIs / ImportNamespace / ImportType selection, category organization, aspects…
Skill Claude CodeCodex
Writes text in ASD-STE100 Simplified Technical English (STE), Issue 9, the controlled language standard for technical documentation. Use it when the user asks for STE, Simplified Technical English, ASD-STE100, or a controlled language, or wants clear technical documentation, procedures, or manuals.
Skill Claude CodeCodex
Quality assurance for web accessibility and usability, particularly for users with disabilities. Use when involved in any web project.
aliyun/alibabacloud-adb-mysql-mcp-server
Skill Claude CodeCodex
A data-analysis assistant for Alibaba Cloud AnalyticDB MySQL, a cloud database service. It can use SQL or Alibaba Cloud interfaces to work with semantic views and explore table metadata.
tbdavid2019/openclaw-docs-skill
Skill Codex
Find authoritative guidance for installing, configuring, operating, securing, and troubleshooting OpenClaw, including channels, model providers, Gateway operations, tools, plugins, automation, nodes, multi-agent routing, and CLI errors. Use for any question or maintenance task involving an OpenClaw installation…
Skill Claude CodeCodex
Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this'…
Skill Claude CodeCodex
Systematically debug failing n8n workflows — expression errors, node type mismatches, pinned data issues, sub-workflow failures, authentication problems, rate limit errors, and silent data loss. Use this skill whenever the user reports an n8n workflow problem — phrases like "my n8n workflow is failing", "this…
Skill Claude CodeCodex
Use when: finding public software developer profiles by skill, language, or location; inspecting a DevGlobe profile; or requesting a consent-gated introduction through the DevGlobe MCP server.
ArogyaReddy/alirezarezvani-claude-skills
Skill Gemini CLI
../../../agents/personas/TEMPLATE.md.
Skill Claude Code
SDD step 5. Reviews the implemented feature code against language and framework best practices, checks for code duplication, security vulnerabilities, performance issues, test coverage, and alignment with feature.md acceptance criteria. Use after /sdd-implement or on any existing feature implementation.
joeseesun/qiaomu-xinzhiyuan-title
Skill Claude CodeCodex
A Chinese-language headline rewriting skill for AI and technology articles, source material, and drafts in the style of the Chinese AI publication 新智元 (Xinzhiyuan). It produces headline options while preserving the supplied facts.
zhouwei713/facial-expression-prompting
Skill Codex
Direct believable character performance and generate complete AI video prompts for text-to-video models. Use for facial acting, microexpressions, emotional transitions, dialogue performance, or vague character ideas such as “an ancient beauty breaks down.” When the brief is vague or asks for a video prompt, expand it…
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: