Skip to content
TrustedSkillsbeta

Browse skills

41,264 listings from across the agent ecosystem. None of them have been code-reviewed — check the source before you install.

Looking for what's new? See the repos gaining stars fastest.

Official

Official vercel-labs skill for AI agents — helps with software development workflows.

Claude Code
vlatest31
Official
Pinned

Captures agent learnings, errors, and corrections to enable continuous improvement. Logs to structured markdown files for review and pattern detection.

OpenClaw
v1.0.0980
Pinned

Create Agents Md

siviter-xyz

Checked

Generates Markdown files detailing new AI agents, including purpose, capabilities, and configuration instructions.

Claude Code
vlatest98
Checked

Claude Code History Files Finder — provides AI agent assistance for software development workflows.

Claude Code
vlatest138
Doesn't install
Listed
Checked

Generates detailed agent profiles, including roles, skills, motivations, and backstories, for simulations and creative projects.

Claude Code
vlatest10
Checked
Checked

Creates detailed markdown files describing PC-style agents, including stats, abilities, and background stories.

Claude Code
vlatest3
Checked

Automatically deploys microservices to cloud environments based on configuration files and defined workflows.

Claude Code
vlatest9
Listed
Checked

Coordinate multi-agent development pipelines using shared JSON task files. Supports Linear, DAG, and Debate modes for AI agent orchestration across code, test, docs, and monitor agents.

OpenClaw
v1.0.0
Checked

Claw Memory

siddontang

Unverified

Shared memory service for AI agents (OpenClaw, KimiClaw, NanoClaw, etc). Use when user asks to store, retrieve, search, or share memories across agent instances. Also use for importing existing memory files (MEMORY.md, daily notes) into the shared service.

OpenClaw
v1.0.0
Unverified

Rss Agent

shiquda

Unverified

A powerful RSS subscription manager and reader. Use it to (1) Import/export OPML files, (2) Manage RSS feeds (add, remove, categorize), (3) Validate feed connectivity, (4) Schedule periodic updates via cron, (5) Fetch and summarize articles with a progressive disclosure approach.

OpenClaw
v1.0.0
Unverified

Deepsafe Scan

XiaoYiWeio

Unverified

Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced semantic analysis. Works with OpenClaw, Claude Code, Cursor, and Codex. Use when a user asks for a security audit, health check, or wants to scan their AI agent setup for vulnerabilities.

OpenClaw
v1.0.0
Unverified

Can't find what you need?