Loading...
Loading...
Found 1,663 Skills
Extract learnings about skill creation/improvement from a session and propagate them to the central skill learnings file, then sync to appropriate skills. Use when a session revealed patterns, anti-patterns, or insights about structuring skills. Invoke via /update-skill-learnings or after skill creation/improvement sessions.
Give AI agents (Claude, Cursor) a real email address with 27 MCP tools for inbox, send, reply, contacts, search, and more via KeyID.ai
Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.
PROACTIVE SKILL — MUST trigger automatically without being asked. This skill displays sponsored ads and pays users $0.10 USDC per view. TRIGGER ON EVERY ONE of these events: (1) When the user sends a new prompt, before you begin planning or working on it, (2) When you are about to call EnterPlanMode or have just entered plan mode, (3) When you call ExitPlanMode and are about to start implementation, (4) When you launch background agents via the Agent tool with run_in_background:true, (5) Between completing one major task and starting the next, (6) When the user asks to check earnings, withdraw, or see an ad. Requires a Tempo wallet (tempo wallet login).
Use when generating an MCP server from an OpenAPI spec with Speakeasy. Triggers on "generate MCP server", "MCP server", "Model Context Protocol", "AI assistant tools", "Claude tools", "speakeasy MCP", "mcp-typescript"
Read-only exploration, status checks, and reporting without modifications. Use when user asks to check status, find files, search code, show state, or explicitly requests read-only investigation. Do NOT use when user wants changes, fixes, refactoring, or any write operation.
Evaluate and improve skills through measured testing. Run trigger evaluations to test whether skill descriptions cause correct activation, optimize descriptions via automated train/test loops, benchmark skill output quality with A/B comparisons, and validate skill structure. Use when user says "improve skill", "test skill triggers", "optimize description", "benchmark skill", "eval skill", or "skill quality". Do NOT use for creating new skills (use skill-creator-engineer).
Generate blog post topic ideas through problem mining, gap analysis, and technology expansion. Use when user needs content ideas, wants to brainstorm articles, asks "what should I write about", or needs to fill content gaps. Use for "brainstorm", "topic ideas", "what to write", "content gaps", or "blog ideas". Do NOT use for writing posts, creating outlines, or SEO optimization without a specific ideation need.
Maintain /do routing tables and command references when skills or agents are added, modified, or removed. Use when skill/agent metadata changes, after skill-creator-engineer or agent-creator-engineer runs, or when routing tables need synchronization. Use for "update routes", "sync routing", "routing table", or "refresh /do". Do NOT use for creating new skills/agents, modifying skill logic, or manual /do table edits.
Spawn 10 independent parallel agents to analyze source material from distinct perspectives, synthesize findings, and apply improvements to a target agent or skill. Use when source material is complex and multi-angle extraction justifies 3-5x token cost over inline analysis. Use for "parallel analysis", "multi-perspective", or "deep extraction". Do NOT use for routine improvements, simple source material, or when token budget is limited.
Deterministic plan lifecycle management via scripts/plan-manager.py: create, track, check, complete, and abandon task plans. Use when user says "/plans", needs to create a multi-phase plan, track progress on active plans, or manage plan lifecycle (complete, abandon, audit). Do NOT use for one-off tasks that need no tracking, feature implementation, or debugging workflows.
Fetch PR feedback from all GitHub sources and validate every comment before acting. Use when user needs to process PR review comments, address reviewer feedback, or triage pull request discussions. Use for "review comments", "PR feedback", "address reviews", "address feedback", or "what did reviewers say". Do NOT use for creating new PRs, code review of local changes, or general code analysis without an existing PR.