Loading...
Loading...
Found 7,373 Skills
Bootstrap the openspec/ directory structure for Spec-Driven Development in any project. Trigger: When user wants to initialize SDD in a project, or says "sdd init", "iniciar sdd", "openspec init".
Execute plan files by launching multiple parallel subagents to complete tasks simultaneously. Triggers on explicit "/parallel-task" commands.
Use this to verify whether the work meets requirements when completing tasks, implementing main features, or before merging.
When reporting that work is completed, fixed, or ready for use before submitting or creating a PR - you need to run verification commands and confirm the output before making any success claims; evidence always precedes assertion
This skill should be used when the user asks to "apply skill improvements", "update skill from plan", "execute improvement plan", "fix skill issues", "implement skill recommendations", or mentions applying improvements from quality review reports. Reads improvement-plan-{name}.md files generated by skill-quality-reviewer and intelligently merges and executes the suggested changes to improve Claude Skills quality.
Write documentation with real, validated examples. Executes commands through the user to capture actual output. Use for any new documentation or major doc updates.
Complete development with structured merge/PR options. Use when ready to merge or submit work.
Skills retrospective and improvement. Use when: - User asks to "review", "retrospect", "summarize" or "复盘" skills - User wants to analyze skills issues from the conversation - User requests skills optimization or improvement - End of conversation or after significant skill usage
Finds and qualifies B2B leads from X/Twitter conversations using keyword search, profile analysis, and intent scoring. Combines MCP tools for automated prospecting pipelines. Use when prospecting, finding potential customers, or mining social conversations for leads.
Run tests for Keychat packages
The human project owner and final authority. Does not write code or run tools -- resolves tie-breaks, approves or denies major decisions, and unblocks deadlocks.
Gauntlet for absolute claims (always/never/guaranteed/optimal); pressure-test, then refine with explicit boundaries. Use when users ask to prove or disprove strong certainty claims, request devil's-advocate challenge rounds, or want the $prove-it gauntlet to run in default autoloop/full-auto style.