ai skills

26,182 tagged ai, measured the same way as everything else here.

Browse within: LLM 535agent 470cli 369chatgpt 286agents 197ml 140agentic 121chatbot 117LangChain 116bun 116generative-ai 102cybersecurity 100hacking 96mcp-server 83

google_workspace

793

ericwang915/PythonClaw

Skill Claude CodeCodex

Google Workspace via gog CLI — Gmail, Calendar, Drive, Contacts, Sheets, and Docs. Use when: the user asks to send/search Gmail, check calendar, manage Drive files, read or edit Sheets, export Docs, or look up contacts. NOT for: Google Cloud APIs, Firebase, or services outside Workspace.

not rated 42 +2 4d ago A SkillSpector: warn 67 tokens original MIT

qi-cli

794

itsmostafa/qi

Skill Claude CodeCodex

Guide for using qi, a local knowledge search CLI for macOS and Linux. Use this skill when the user wants to index documents into a searchable knowledge base, search or retrieve from one, configure qi's collections or embedding providers (Ollama, OpenAI-compatible), choose between its search modes (BM25, hybrid…

not rated 42 +1 changed 5d ago A SkillSpector: warn 88 tokens original MIT

Pantani/tdmcp

Skill Claude CodeCodex

Drive a whole tdmcp feature BACKLOG to completion as resumable, wave-by-wave releases — the campaign layer ABOVE tdmcp-pipeline/tdmcp-feature-lead. Use whenever the user wants to implement an ENTIRE backlog or discovery file (e.g. workspace/discovery/FEATUREBACKLOG.md), 'all the features', many features across…

not rated 42 +3 28d ago A SkillSpector: pass 185 tokens original MIT

plotting

796

swarm-ai-research/swarm

Skill Claude CodeCodex

Generate publication-quality visualizations from SWARM simulation data.

not rated 42 +1 2d ago A SkillSpector: pass 13 tokens original MIT

manual

797

yaodub/cast

Skill Claude CodeCodex

Texting as a person's proxy — reading threads, sending irreversibly, and watching conversations without over-answering.

not rated 41 21d ago B 22 tokens original MIT

git-iris

798

hyperb1iss/git-iris

Skill Claude CodeCodex

Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when…

not rated 41 6d ago A 81 tokens original Apache-2.0

llms-visibility

799

evilmartians/agent-skills

Skill Claude CodeCodex

Make websites, docs, blogs, or landing pages visible and readable to LLMs and AI agents — ChatGPT, Claude, Perplexity, Cursor, Claude Code, and other coding agents that fetch URLs. Use this for any request involving llms.txt, llms-full.txt, serving .md/Markdown versions of pages, Accept text/markdown content…

not rated 41 +2 1mo ago A SkillSpector: pass 214 tokens original MIT

NickCrew/Claude-Cortex

Skill Claude CodeCodex

Build a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODEOFCONDUCT), and a self-contained press kit. This skill should be used when the user asks…

not rated 41 +3 2mo ago A 158 tokens original MIT

find-skills

801

Eldergenix/Proofloop

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

not rated 40 +1 3mo ago A 67 tokens copy · 91% MIT

skill-creator

802

levante-hub/levante

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 40 4mo ago A 64 tokens

extension-authoring

803

HaseebKhalid1507/SynapsCLI

Skill Claude CodeCodex

Step-by-step guide to building, installing, and testing a SynapsCLI extension — manifest, handshake, tool, hook, install, and test.

not rated 40 today A SkillSpector: warn 34 tokens original Apache-2.0

code-review

804

anthroos/claude-code-review-skill

Skill Claude CodeCodex

AI code review for PR or local changes. 280+ checks across security, architecture, performance, testing, and code quality. Posts findings as GitHub PR comments with confidence scores.

not rated 40 6mo ago A 40 tokens copy · 97% MIT

theam/limina

Skill Codex needs its repo

Challenge the current Limina research direction and next-step plan. Use for step-back reviews, pre-commitment checkpoints, plateau reviews, contradictory findings, or pivot/continue/stop recommendations when evidence or framing may be weak.

not rated 40 +1 1mo ago A SkillSpector: pass 52 tokens original Apache-2.0

aliengiraffe/vigilante

Skill Codex

Help a human author write an implementation-ready GitHub issue that Vigilante can execute reliably.

not rated 40 +1 4d ago A SkillSpector: pass 25 tokens original Apache-2.0

maestro-extension

808

neuron-core/maestro

Skill Claude CodeCodex

Help developers create and implement extensions for the Maestro CLI application. Use this skill whenever the user mentions creating a Maestro extension, adding custom tools or commands, building UI components for Maestro, registering memory files or event handlers, packaging a Composer package with Maestro extensions…

not rated 39 +1 2mo ago A 99 tokens

kdpa-llc/local-skills-mcp

Skill Claude CodeCodex

Repository implementation guide for the local-skills-mcp codebase. Use when asked: how src/index.ts and src/skill-loader.ts work together; where MCP tool handlers are defined and registered; how getAllSkillsDirectories priority and override behavior works; how local-skills-mcp discovers skills and merges metadata…

not rated 39 today A SkillSpector: pass 98 tokens original MIT

crawl-data

811

ea-toolkit/architecture-catalog

Skill Claude Code

Scan a target codebase for data model definitions (SQL schemas, ORM models, TypeScript interfaces, Pydantic models) and propose dataconcept, dataaggregate, and dataentity registry entries. Presents findings for review before writing files.

not rated 38 4mo ago A 52 tokens original MIT

graphify

812

Choeng-Rayu/rayu-cli

Skill

Turn any folder of files (code, docs, papers, images, video) into a queryable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md. Use when asked to analyze a codebase, understand architecture, map dependencies…

not rated 38 yesterday A SkillSpector: warn 0 tokens original MIT

ai-session-search

813

ahundt/ai-session-search

Skill Claude CodeCodex

Search, recover, inspect, export, and analyze local AI session history with AI Session Search (aise) across Claude Code, Claude Desktop local agent, Codex, Cursor, Antigravity, Pi coding agent, Prime Agent, Google AI Studio, and Gemini CLI. Use when asked to "find prior AI work", "recover context after compaction"…

not rated 38 +1 6d ago B SkillSpector: warn 108 tokens original Apache-2.0

handoff

814

ToolMonsters/handoff-skill

Skill Claude CodeCodex

Generate a complete handoff document of the current conversation so another LLM (ChatGPT, a fresh Claude, Gemini...) can pick up exactly where this one left off. Use when the user types "handoff", says the session is almost full, mentions hitting the context/usage limit, or wants to continue this conversation in…

not rated 38 1mo ago A 71 tokens original MIT

coding-agent

815

memgrafter/flatmachines

Skill Claude CodeCodex

AI coding agent that plans, implements, and verifies code changes with human approval gates. Built on FlatAgents.

not rated 37 3mo ago A 25 tokens original Apache-2.0

soul-agent

816

kitephp/soul-agent

Skill Claude CodeCodex

Dual-runtime companion skill for Hermes and OpenClaw. Adds heartbeat-driven life logs, moods, relationship evolution, daily planning, and independent memory. Use when building a persistent digital companion or automating companion-style outreach.

not rated 37 4mo ago A 47 tokens

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: