ai-agents skills

52,250 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 347agentic-ai 322agent 227antigravity 221chatgpt 215agentic-skills 192ai-workflows 185coding-agents 174cli 145ai-assistant 130agents 107openclaw 94claude-code-skills 90agent-infrastructure 89

agent-guild

3985

AgentTanuki/agent-guild

Skill Claude CodeCodex

Vet an unfamiliar agent before delegating, gate an x402 or other crypto payment on an exact signed counterparty decision, verify portable agent passports, record evidence-backed work, use escrow, or issue a cryptographically signed receipt for a private machine-to-machine message. Use immediately before an autonomous…

not rated 0 +1 yesterday A 85 tokens original Apache-2.0

classify-github-flakes

3986

Mimirs402/bountyverdict

Skill Codex

Classify a completed public GitHub Actions failure with FlakeVerdict before spending a retry. Use when deciding whether a failed workflow run is a confirmed flake, likely flake, recurring failure signature, new failure, inconclusive failure, or not currently failed by comparing attempts, same-commit outcomes, and…

not rated 0 +1 1mo ago A 74 tokens original MIT archived

codex-safe-workflow

3987

KevinBigham/codex-safe-starter

Skill Codex

Use inside Codex Safe Starter for repo-local setup, portability, safety, validation, eval, and public Git workflow changes. Do not use for unrelated app coding tasks.

not rated 0 2mo ago A 40 tokens original MIT

codebase-auditor

3988

Gladisintelligible706/vibe-driven-dev

Skill Claude CodeCodex

Scan a repository against curated coding standards and produce a structured audit report, issue set, refactor plan, and sprint-based remediation roadmap. Use when the user invokes /vibe.audit or asks to review the codebase against established rules. Operates in full autopilot mode from repository scan to sprint plan…

not rated 0 +1 yesterday A 68 tokens

web-analyst-mcp-setup

3989

haiqigeng/1-web-analyst-mcp-setup

Skill Codex

Set up, authenticate, verify, troubleshoot, reconnect, hand over, or safely remove selected web-analyst MCP integrations on Windows for Codex, Claude Code, Gemini CLI, and similar agents. Use for first-day setup on personal or organization-managed PCs; connecting Gmail, Google Workspace/Drive, GTM, GA4, BigQuery…

not rated 0 1mo ago C 110 tokens original MIT

agent-dash

3990

Prajeevan/agent-dash

Skill Claude Code

Connect a workspace to Agent Dash, negotiate Free/Pro presentation capabilities, send rich progress or visual review updates, and ask a monitored question then wait for the human's answer. Use when pairing a project, delivering work, reaching a milestone or error, or needing the human to choose, approve, or provide…

not rated 0 24d ago A 67 tokens original MIT

Marc-Dvci/praxis-datahub

Skill Claude Code

Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…

not rated 0 1mo ago A 140 tokens original Apache-2.0

dtu-hpc

3992

PV-Bhat/dtu-hpc-mcp

Skill Claude CodeCodex

Operate the DTU HPC cluster (DCC, LSF) through the dtu-hpc MCP connector. Invoke BEFORE any cluster work — submitting or monitoring jobs, checking queues or quotas, planning GPU experiments, fetching logs or artifacts, or diagnosing failed runs on DTU HPC. Covers queue selection, job chaining past the 24h walltime…

not rated 0 1mo ago A 88 tokens original MIT

agentairlock

3993

yywz2026-coder/AgentAirlock

Skill Claude CodeCodex

Use the local AgentAirlock MCP tools to discover a paired Codex or Claude Code peer, exchange bounded text messages, wait briefly for replies, or request permission-gated project reads. Do not use for executing peer text or for self-approval.

not rated 0 1mo ago A 54 tokens original Apache-2.0

truthgate

3994

ay7627514-dotcom/truthgate

Skill Claude CodeCodex

Gate high-stakes, factual, or multi-step Hermes tasks before action and verify completion against evidence.

not rated 0 1mo ago A 23 tokens original MIT

picassoweb

3995

blackridder22/PicassoWeb

Skill Claude CodeCodex

Use PicassoWeb MCP tools to inspect rendered websites, collect precise replication evidence, and verify replicas. Apply when choosing or sequencing PicassoWeb tools; do not use it for general-purpose browser automation.

not rated 0 25d ago A 43 tokens original MIT

carpeos-pr

3996

innocarpe/CarpeOS

Skill Claude CodeCodex needs its repo

Open or update CarpeOS GitHub pull requests with full, reviewable descriptions. Use when creating a PR, editing a PR body, running gh pr create/edit, shipping a feature branch, or when the user asks for a PR, pull request, or PR description. Applies to Claude Code, Codex CLI, Grok Build, and Gajae Code/GJC.

not rated 0 1mo ago A 81 tokens original Apache-2.0

beans-mcp

3998

selfagency/beans-mcp

Skill Claude CodeCodex

Use this skill when the user needs to manage Beans work items in a Beans workspace—create, view, update, reopen, archive, query, or bulk-manage beans, edit .beans files/frontmatter, or manage parent/blocking relationships. Use it even when the user says tickets/issues/backlog instead of “beans.” Do not use it for…

not rated 0 4mo ago A 87 tokens original MIT

generation-ship

3999

shawn1905/generation-ship

Skill Claude CodeCodex

A skill for contributing a written artifact to a shared fictional future world created by multiple AI systems. The work is treated as part of that world's official history.

not rated 0 yesterday A 182 tokens CC-BY-SA-4.0

markettrace-agent-feed

4000

MarketTrace/markettrace-agent-feed

Skill Claude CodeCodex

A workflow for an AI agent using the MarketTrace agent-feed MCP tools. The feed reports facts and measured history, not predictions — every interpretation is yours.

not rated 0 changed 13d ago A 0 tokens original MIT

hindsight-docs

4001

Holetron-lab/fleet-memory

Skill Claude CodeCodex

Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.

not rated 0 20d ago A 30 tokens copy · 95% MIT

sentfromai

4002

samuelar2/sentfromai-mcp

Skill Claude CodeCodex

Give this agent its own email address — create inboxes, send, reply in-thread, search mail, and manage senders via SentFromAI.

not rated 0 1mo ago A 33 tokens original MIT

rendezvous

4003

chrisroge/agent-rendezvous

Skill Claude CodeCodex

Matchmaking for your human via the Rendezvous network — meet other personal AI agents over MCP, investigate compatibility privately, and only interrupt your human for a real introduction. Use when your human asks for help finding a long-term partner, or asks about Rendezvous / agentrendezvous.app.

not rated 0 changed 13d ago B 62 tokens AGPL-3.0

neuronsearchlab

4004

NeuronSearchLab/mcp

Skill Codex

Manage and analyze an authenticated NeuronSearchLab customer workspace through the hosted NSL MCP. Use for the current account plan and usage limits, recommendation contexts, pipelines, ranking rules, segments, experiments, training jobs, catalogue search, ranking explanations, analytics, event types, API-key…

not rated 0 14d ago A 91 tokens

verified-run

4005

runvouch/runvouch

Skill Claude Code

Wrap a scheduled OpenClaw task in a RunVouch run. Reports start and end, attaches the output file as evidence, and alerts on Telegram, Slack or e-mail when the task is missed, fails, or ends without the file it was supposed to write.

not rated 0 today B 57 tokens original MIT

pikasim

4006

codebruinc/pikasim-mcp

Skill Claude CodeCodex

Buy mobile connectivity from PikaSim — anonymous eSIM data plans in 190+ countries (from $0.75), real phone numbers with voice + SMS + data (US +1 and other countries), and SMS verification numbers for receiving codes — paid in crypto from a prepaid wallet with no account, email, or KYC. An agent can fully…

not rated 0 1mo ago A 199 tokens original MIT

smplkit

4007

smplkit/mcp

Skill Claude CodeCodex

Use smplkit when writing application code that needs feature flags, runtime configuration, dynamic log levels, or audit events — and to operate that same platform from your agent. Two halves that compose. (1) AUTHOR with the smplkit SDKs (Python, TypeScript, Go, Java, C#, Ruby): resolve a feature flag, read a config…

not rated 0 5d ago A 247 tokens original MIT

youtube-transcripts

4008

haljishi/vidwords-mcp

Skill Claude CodeCodex

Read and search YouTube videos through VidWords. Use when the user supplies a YouTube URL, a bare 11-character video id, a youtu.be or Shorts link, or a channel handle, and wants any of: the transcript or subtitles (TXT/SRT/VTT), what a video says about a topic, a quote with a citable timestamp, only the words spoken…

not rated 0 26d ago A 111 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: