ai-agents skills

51,527 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 336agentic-ai 282antigravity 211agent 210chatgpt 199agentic-skills 192ai-workflows 185coding-agents 152cli 144ai-assistant 126agents 105openclaw 95claude-code-skills 90agent-infrastructure 89

go

1609

samibs/skillfoundry

Skill Claude CodeCodex needs its repo

Project Kickstart - PRD-First Orchestrator.

not rated 12 8d ago A SkillSpector: warn 13 tokens original MIT

crystal-kb

1610

memorycrystal/memorycrystal

Skill Claude CodeCodex

Create, import, enumerate, maintain, and share Memory Crystal knowledge bases. Use when importing reference material, syncing a corpus, cleaning or auditing a KB, or managing which agents can read a KB.

not rated 12 12d ago A 45 tokens original MIT

langchain-agents

1611

jackjin1997/ClawForge

Skill Claude CodeCodex

Use this skill for ANY coding question involving LangChain products (LangChain, LangGraph, LangSmith SDK). Covers agent development patterns, primitives, context management, multi-agent systems, and when to use createagent vs createdeepagent vs raw LangGraph. Consult this BEFORE writing any LangChain-related code.

not rated 12 2mo ago A 67 tokens

teamwork-collaborate

1612

JinPLu/Teamwork

Skill Codex

Use when the user explicitly wants to discuss, brainstorm, compare options, or make a material preference decision, or when unclear intent needs guided clarification; do not use for clear execution or a single discoverable detail.

not rated 12 18d ago A 49 tokens original MIT

sol-luna-setup

1613

Yuri-NagaSaki/subagent-skills

Skill Codex

A setup guide for configuring a team of coding agents, with one agent planning work and others scouting, building, reviewing, or testing it. It can also configure Claude Code and Pi tools for a new machine or project.

not rated 12 1mo ago D 159 tokens original MIT

dory-wake

1614

deeflect/dory

Skill Claude CodeCodex

Use Dory wake once at the start of a new agent session, after context compaction, or at a real task switch to load bounded hot context with the right profile before substantive work.

not rated 12 +1 3mo ago A 43 tokens original MIT

autonomous-learning-os

1615

gquthier/autonomous-learning-os

Skill Codex

Construit à l'utilisateur son propre dashboard d'apprentissage sur mesure — entretien de setup, deep research multi-agents sur son sujet, génération du curriculum, app Next.js au design BizOS, brief Telegram optionnel. À utiliser quand l'utilisateur veut apprendre un sujet sérieusement, se construire un cursus, ou…

not rated 12 1mo ago A 71 tokens original MIT

greendesertsnow/pocketbase-skills

Skill Claude CodeCodex

PocketBase development best practices covering collection design, API rules, authentication, SDK usage, query optimization, realtime subscriptions, file handling, deployment, and server-side extending (Go + JSVM). Current as of PocketBase v0.40 and JS SDK v0.28. Use when building PocketBase backends, designing…

not rated 12 21d ago A Socket: passSnyk: pass 87 tokens original MIT

pr

1617

thkt/dotclaude

Skill Claude Code

A workflow for analyzing branch changes and creating a draft pull request, including a screenshot step when the changes affect the user interface.

not rated 12 changed 8d ago A SkillSpector: warn 67 tokens original MIT

add-test

1618

open-metadata/ai-sdk

Skill Claude Code

Use when adding unit or integration tests. Provides test patterns, naming conventions, and fixtures for Python (pytest), TypeScript (vitest), Java (JUnit/Mockito), and Rust.

not rated 12 3d ago A 40 tokens

opensci-skill

1619

HughYau/opensci-skill

Skill Claude CodeCodex

Help an agent familiarize itself with any scientific Python library or codebase so it can write a high-quality opensci skill for that library. Use when creating, auditing, or refactoring opensci skills for published packages, source-only repositories, namespace packages, or mixed-layout projects. Content is optimized…

not rated 13 +1 6mo ago A 0 tokens

ctx

1620

agentis-tools/ctx

Skill Claude CodeCodex needs its repo

Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…

not rated 12 6d ago A 60 tokens copy · 100% Apache-2.0

image-to-cad

1621

autonomous-ai/autonomous-workshop

Skill Codex

Turn a reference image (photo, render, screenshot, sketch, or orthographic drawing) into a structured, buildable CAD spec — overall read, top/front/side views, real-world size, part and feature decomposition, per-feature detail, and the exact build123d operation each feature is built with. Use when the user attaches…

not rated 13 +1 changed 3d ago A SkillSpector: pass 125 tokens original Apache-2.0

speckit-archive-run

1622

racecraft-lab/Paddock

Skill Claude Code

Archive merged feature specs into project memory with provenance, sweep discovery, and gated cleanup.

not rated 12 +1 2mo ago A 23 tokens original MIT

jarviscore

1623

Prescott-Data/jarviscore-framework

Skill Claude CodeCodex

Build multi-agent AI systems with the JarvisCore Python framework. Use when writing, reviewing, or debugging code that imports jarviscore, defines AutoAgent or CustomAgent classes, runs a Mesh, or configures agent memory (Athena), P2P, Nexus credentials, or tracing.

not rated 12 changed yesterday A 63 tokens

competitor-x-ray

1624

Mahanaicoach/competitor-x-ray

Skill Claude CodeCodex

Decode any set of competitors into their ICP (ideal customer profile), their funnel (how a stranger becomes a customer), and their monetization (every revenue stream and price point). Researches each competitor against real sources and synthesizes a cross-competitor comparison. Use whenever the user wants to research…

not rated 12 +1 3mo ago C 221 tokens original MIT

openreview-cli

1625

mohamed-benoughidene/openreview-cli

Skill Claude CodeCodex

Use when a user wants to review, compare, search, or analyze legal/contract documents (PDF/DOCX) locally — produce review memos, compare two versions, search indexed clauses, run negotiation analysis, manage LLM gateway slots/playbooks, or audit/delete stored PII mappings. This is the local openreview CLI, NOT the…

not rated 12 +1 changed 4d ago A 81 tokens AGPL-3.0

dcc-mcp-houdini-setup

1626

dcc-mcp/dcc-mcp-houdini

Skill Claude Code

Set up dcc-mcp-houdini for an agent or operator: install Houdini Python dependencies with hython, generate MCP host configuration, guide the user through the Houdini package / 123.py autostart load step, and run a first live-tool smoke prompt.

not rated 12 today A SkillSpector: pass 68 tokens original MIT

titanclip

1627

CES-Ltd/TitanClip

Skill Claude CodeCodex

Interact with the TitanClip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any TitanClip API endpoint. Do NOT use for…

not rated 12 5mo ago A 87 tokens

codex-rehome

1628

CalebYcj/codex-rehome-skill

Skill Codex

Advanced workflow for migrating, backing up, restoring, or reproducing a Codex Desktop workspace between Mac and Windows computers; use for automation, verification, no-GUI environments, and recovery when ReHome Desktop is not the right entry point.

not rated 12 +1 1mo ago A 53 tokens original MIT

awiki-save

1629

TacoTakumi/agent-wiki

Skill Claude CodeCodex

Save content from the current conversation to the Agent Wiki. Use when research, decisions, or valuable findings should be preserved.

not rated 12 +1 yesterday A 28 tokens

add-simulator

1630

nimrodfisher/agent-think-map

Skill Claude CodeCodex

Install Agent Think Map into this NanoClaw checkout — live skill/tool/MCP visualization over SSE. Additive copies only; never merge channels or providers.

not rated 12 7d ago A SkillSpector: pass 35 tokens original MIT

sol-foreman

1631

olsenbrands/sol-foreman

Skill Codex

Sol-led economical orchestration for delegated builds, coding sprints, independent review, and stalled-work recovery. Use when Sol Foreman is requested or a Sol-led crew needs outcome-focused coordination; keep one foreman policy per run.

not rated 12 changed 7d ago A 51 tokens original MIT

codebase-second-brain

1632

Mallikarjun-Roddannavar/playwright-agentic-automation

Skill Codex needs its repo

Retrieve, verify, and refresh the persistent Open Knowledge Format v0.2 codebase memory for playwright-agentic-automation. Use when an agent needs architecture discovery, source ownership, page/API/fixture relationships, static AST graph queries, knowledge freshness checks, Mermaid/Obsidian navigation, or durable…

not rated 12 +1 7d ago A SkillSpector: pass 72 tokens original MIT

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: