huang2he/prompt-lab
End-to-end Claude Code skill for iterating agent prompts through automated eval-improve-eval rounds
End-to-end Claude Code skill for iterating agent prompts through automated eval-improve-eval rounds
npx skills add huang2he/prompt-labEnd-to-end Claude Code skill for iterating agent prompts through automated eval-improve-eval rounds
Claude Code plugin: m_* toolkit (m_plan plan->execute->verify, deploy/infra commands, Playwright full-test loop, m_code quality framework)
A Claude Code skill that coaches you through building a personal thought leadership strategy and 90-day execution plan
Deterministic firewall for MCP agent tool calls. YAML policies, hash-chained audit, blast-radius scoring, multi-cloud cost intelligence.
KO-first bilingual (KO/EN) LLM output-compression skill for AI coding agents. Tokens are money — spend them like a miser.
Best-effort pre-publish PII and secret check for npm packages, OpenClaw skills, and local repos.
Unified Campus Intelligence Dashboard with AI Assistant