Every Agent Skill,
One Registry
curl -fsSL askill.sh | shBrowse
Search the registry for skills built by the community.
AI Score
AI scores Safety, Clarity, Reusability, Completeness, and Actionability to filter risky skills.
Install
One command. Works with your agent automatically.
Works with 40+ agents
Perform comprehensive, deep analysis of a system and its subsystems to identify bugs, race conditions, stale documentation, dead code, and correctness issues. Use when asked to "audit this system", "exhaustive analysis of X", "analyze for correctness...
Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.
Use `discord` to manage messages, reactions, threads, polls, and moderation. You can disable groups via `discord.actions.*` (defaults to enabled, except roles/moderation). The tool uses the bot token configured for Moltbot.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Web application testing principles. E2E, Playwright, deep audit strategies.
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
Creates new Prowler cloud providers or adds services to existing providers. Trigger: When extending Prowler SDK provider architecture (adding a new provider or a new service to an existing provider).
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when i...
Vercel AI SDK 5 patterns. Trigger: When building AI features with AI SDK v5 (chat, streaming, tools/function calling, UIMessage parts), including migration from v4.
Solution selection and adversarial validation. Use when proposing solutions, evaluating build-vs-buy, reviewing designs, or finalizing architecture decisions.
Quality gate validation for agentic design artifacts (agents, subagents, prompts, skills). Apply when creating, reviewing, or validating .agent.md, .sub.agent.md, .prompt.md, or SKILL.md files. Covers A1-A9 (agent gates), SA1-SA7 (subagent addendum),...
Orchestrate Chinese LLMs (DeepSeek, Qwen, Yi, Moonshot) through OpenRouter API with LangChain. Use when: openrouter, chinese llm, deepseek, qwen, moonshot, yi model, model routing, auto router, llm orchestration.
Full desktop computer use for headless Linux servers and VPS. Creates a virtual display (Xvfb + XFCE) to control GUI applications without a physical monitor. Screenshots, mouse clicks, keyboard input, scrolling, dragging — all 17 standard actions. In...
Use for ideation, requirements clarification, and architectural design. Adapts to task complexity (Trivial/Medium/Complex).
Generate images from text prompts using fal.ai Gemini 3 Pro. Use when the user asks to create, generate, or make an image from a text description. Supports multiple aspect ratios and resolutions up to 4K.
Regras rígidas de segurança para Docker Compose - NUNCA expor variáveis de ambiente
Advanced performance profiling techniques for Urbit ships including CPU profiling with htop/perf, memory analysis, I/O tracing with iotop, network analysis, and systematic bottleneck identification. Use when diagnosing performance issues, identifying...
Binary tree addressing system using axis/slot notation for navigating noun structures. Covers axis encoding (1=root, 2=head, 3=tail, binary paths), slot calculation algorithms, and efficient tree traversal patterns. Use when implementing slot operati...
Docker and container security hardening for GroundSeg Urbit deployments including image scanning, runtime protection, network isolation, rootless containers, secrets management, and compliance. Use when securing Docker environments, hardening GroundS...
Design patterns and architectures for building Nock virtual machines including evaluation loops, pattern matching strategies, error handling, tail call optimization, and memory management. Use when building Nock interpreters, optimizing evaluation pe...
Expert Nock interpreter builder for implementing virtual machines in C, Python, Rust, Haskell, or JavaScript. Use when building Nock interpreters, porting between languages, implementing evaluation loops, or understanding Nock runtime behavior.
Canvas as an app platform. Build, store, and run rich visual apps on the OpenClaw Canvas.
Use OpenAI Codex CLI for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding agent, gpt-5-codex. Enables Clawdbot to delegate coding work to Codex CLI as a subagent or direct tool.
Showing 3793 to 3816 of 271.4k results
Command Palette
Search for a command to run...