SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

huuuuuuho-skills
Turn raw notes or drafts into a long-form WeChat/少数派 style article with outline, draft, fact-checking, and self-check workflow.

brain-in-the-fish
Evaluates documents against criteria using multi-agent, ontology-grounded scoring to produce evidence-backed, auditable evaluation reports.

research-mode
Enforces strict citation-first behavior: require local or external citations, prefer direct quotes, and respond "I don't know" when unsupported — useful for fac

claude-ai-music-skills
Validate research outputs: check source accessibility, verify quotes, cross-check dates and facts, archive sources, and produce a verification report for human

medical-research-skills
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.

fact-check-skill
Semi-automated verification of claims using evidence ledgers, source credibility analysis, and HTML fact-check cards.

brave-search-skills
High-performance web search and RAG grounding tool optimized for AI agents with token-budgeted content and custom ranking.