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

han
Guidelines for agents to prioritise technical accuracy and direct, evidence-based communication instead of excessive agreeableness.

talk-normal
A tested, bilingual system-prompt installer that reduces verbose, corporate-sounding LLM output while preserving information.

claude-reflect
Capture user corrections during sessions and manage a /reflect flow to apply learnings to CLAUDE.md for future behavior improvements.

skills_all-in-one
Guides agents on how to receive and handle code review feedback: verify, ask clarifying questions, prioritize fixes, and avoid performative agreement.