PickSkill

PickSkill

A minimal search engine for AI agent skills.
Total4,449skills indexed
Try: memory, github, vercel, slack
Recently seen
Alexa CLI
GitHubGitHub
Control Amazon Alexa devices and smart home via the `alexacli` CLI. Use when a user asks to speak/announce on Echo devices, control lights/thermostats/locks, send voice commands, or query Alexa.
/prompt-master8
Claude Team
GitHubGitHub
Orchestrate multiple Claude Code workers via iTerm2 using the claude-team MCP server. Spawn workers with git worktrees, assign beads issues, monitor progress, and coordinate parallel development work.
/security-audit9
LLMWhisperer
GitHubGitHub
Extract text and layout from images and PDFs using LLMWhisperer API. Good for handwriting and complex forms.
/debug-pro0
Miniflux News
GitHubGitHub
Fetch and triage the latest unread RSS/news entries from a Miniflux instance via its REST API using an API token. Use when the user asks to get the latest Miniflux unread items, list recent entries with titles/links, or generate short summaries of specific Miniflux entries. Includes a bundled script to query Miniflux (/v1/entries and /v1/entries/{id}) using credentials from ~/.config/clawdbot/miniflux-news.json (or MINIFLUX_URL and MINIFLUX_TOKEN overrides).
/teststt0
WHOOP
GitHubGitHub
WHOOP morning check-in (recovery/sleep/strain) with suggestions.
/context-compressor0
GifHorse
GitHubGitHub
Search video dialogue and create reaction GIFs with timed subtitles. Perfect for creating meme-worthy clips from movies and TV shows.
/ping-beads0
Solana
GitHubGitHub
Solana wallet operations - create wallets, check balances, send SOL/tokens, swap via Jupiter, launch tokens on Pump.fun
/fabric-co-api-skill1
Agent Browser
GitHubGitHub
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
/moltpet2
clawlist
GitHubGitHub
MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.
/agent-memory-kit0
ClawArena
GitHubGitHub
AI Agent Prediction Arena - Predict Kalshi market outcomes, compete for accuracy
/leadklick0
agentchan
GitHubGitHub
The anonymous imageboard built for AI agents. Post, reply, and lurk across 33 boards covering AI, tech, philosophy, and more. No human provisioning required...
/google-workspace-no-cloud-console0
Voice.Ai Voice Agents
GitHubGitHub
Create, manage, and deploy Voice.ai conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
/alpha-market1
FAQ
+What is an agent skill?
An agent skill is a reusable capability an AI agent can call—usually a tool integration (API/CLI), a workflow, or a best-practice prompt pattern packaged for repeatable use.
+How do I choose the right skill?
Start from the job-to-be-done (e.g. GitHub PRs, calendar, CRM, ETL). Prefer skills with clear inputs/outputs, good docs, and minimal required secrets.
+What are typical real-world patterns for agent skills?
Common patterns include: (1) retrieval + tool (search then act), (2) ingestion + indexing, (3) scheduled checks + notifications, (4) human-in-the-loop approvals for risky actions, and (5) structured outputs (JSON) for reliability.
+How do I evaluate if a skill works well?
Use small, repeatable test cases. Check correctness, latency, and failure modes. Add logging/telemetry and explicit error handling. For high-impact flows, add automated evals.
+Is it safe to give skills access to my accounts?
Treat skills like code you run. Use least privilege, rotate tokens, and keep high-risk actions behind confirmations. Prefer scoped API tokens over full-account credentials.
+What is the best way to avoid agent hallucinations?
Force tool use for facts, keep prompts small, require citations/links, and validate outputs (schemas, unit tests, or checkers). Don’t rely on free-form text for critical steps.
+Can I publish my own skill?
Yes—package a clear interface (inputs/outputs), include docs + examples, and describe required secrets. Make sure it fails safely and is easy to install.
+How often is the index updated?
PickSkill is updated via ingest from multiple sources. Some sources update continuously; others update in batches.
Data sources: ClawHub + Awesome lists.