Loading...
Loading...
Found 5,775 Skills
Produces a concrete eval suite plan grounded in Microsoft's Eval Scenario Library and MS Learn agent evaluation guidance — scenario types, evaluation methods, quality signals, thresholds, and priority order — before any test cases are generated or evals are run.
An advanced SEO agent skill for deep, comprehensive single-page SEO audits. Performs full technical SEO analysis, on-page SEO review, structured data validation, content quality assessment, and canonical/crawlability checks. Outputs an advanced full SEO audit report. Use when the user says "deep audit", "advanced audit", "technical SEO audit", "full SEO audit", "full report", "key report", "comprehensive SEO review", or explicitly asks for more than a basic check. Powered by OpenClaw and Claude.
This skill should be used when the user wants to "login to GitHub", "store an API key", "get authentication headers", "export credentials to the shell", "run a command with API keys injected", "register a custom OAuth provider", "manage tool tokens", or "authenticate to a third-party application". Also triggers for requests involving authenticating AI agents or securely storing/retrieving credentials using the authsome CLI.
Audit all installed agent skills across global and project scopes to find and remove duplicate skills. Use when asked to audit my skills, deduplicate skills, clean up skills, or find duplicate skill installations. Don't use for creating or improving a single skill, running skill evals, or packaging/publishing skills.
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
Claude Shannon's Six Techniques for Creative Problem Transformation. Spawns a team of specialist agents — Simplifier, Analogist, Reframer, Decomposer, Inverter — who each apply one of Shannon's problem-solving techniques to your stuck problem. The lead synthesizes into a transformation assessment: which reframings opened paths, which analogies map, and the honest Shannon verdict on whether the problem has been cracked open. Use when stuck on any problem — engineering, strategy, design, math, business. Works standalone or after other analysis skills surface a hard sub-problem.
Summarize the last N agent sessions for the current project, grouped by date. Use when the user asks "recap", "what have we been doing", "this week", "today", or wants a rollup of recent work.
Update ElevenLabs agent skills from a merged weekly changelog in elevenlabs-dx, then open a pull request in elevenlabs/skills. Trigger after a changelog merges to main on elevenlabs-dx, or when asked to update skills from changelog YYYY-MM-DD.
Routes human attention to decisions that matter in agent-generated code. Active during planning, implementing, fixing. Defines when and how to place DECISION markers in code comments. Also applies when reviewing a diff/PR on request.
Use when creating, updating, or improving agent skills.
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context infrastructure to an existing repo, user asks to set up AGENTS.md, add intent layer, make agents understand the codebase, or scaffolding AI-friendly project documentation.