Mine years of PR feedback into evidence-backed AI assistant context files automatically.
4 files for Claude Code: exporters, extraction-prompts, llm-providers, repo_mind CLAUDE.md — 968 tokens loaded in every session.
CLAUDE.md A 968 tok .claude/skills/exporters/SKILL.md A 48 tok .claude/skills/extraction-prompts/SKILL.md A 50 tok .claude/skills/llm-providers/SKILL.md A 49 tok These files are adnan4k/repo_mind's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.