Loading...
Loading...
Found 6,359 Skills
Create a new skill. When to use: When the user says "create skill", "new skill", "add skill", "initialize skill".
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.
improve a CLAUDE.md file using <important if> blocks to improve instruction adherence
Conduct deep codebase research and produce a written report. Use when the user says "Research ...", "start a research for", "deeply investigate", or "fully understand how X works". Do not use for quick questions or simple code lookups.
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm
Agent skill for security-manager - invoke with $agent-security-manager
Use when batch-resolving approved todos, especially after code review or triage sessions
Unified CLI entry point for the entire Skill System. One command (sk) to operate all skills, run configurable gate validation, and execute discoverable project scripts via CLI-Anything style scan/run workflows.
Use when searching codebases (text, structural/AST, files by name, PDFs/archives, code stats) or building context before a task.
Use when the system needs to track its own effectiveness, learn from errors, adapt workflows, and continuously improve performance - activates automatically every session to collect metrics, classify errors, recognize patterns, and implement evidence-based workflow improvements
OSINT-based technology stack identification. Discovers company tech stacks using passive reconnaissance across 17 intelligence domains. Given a company name (and optional domain hint), infers frontend, backend, infrastructure, and security technologies using publicly available signals.
Retrieve a GitHub issue using the `gh` CLI, analyze it, and spawn a PM + developer team to address it. Accepts an issue URL, issue number, or `owner/repo#number`.