Reconcile CLAUDE.md, AGENTS.md, docs/, and agent memory after sessions.
npx skills add https://github.com/KKKKhazix/khazix-skills --skill neat-freak
Please help me install this Agent Skill. Skill: neat-freak Source: https://github.com/KKKKhazix/khazix-skills/tree/main/neat-freak Command: npx skills add https://github.com/KKKKhazix/khazix-skills --skill neat-freak
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, AGENTS.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. Bare "整理" / "tidy" with prior dev context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.
This Skill acts as a dedicated knowledge custodian that audits and harmonizes project-level documentation and agent memory to ensure consistency across teams and sessions. It ensures the three layers of knowledge (Agent memory, root CLAUDE.md / AGENTS.md, and docs/README) stay aligned with the latest codebase changes. Key concepts include separation of audiences (Agent memory, project docs, and developer docs) and a disciplined workflow for updating or removing stale information.
Trigger a full knowledge reconciliation across CLAUDE.md, AGENTS.md, docs/, and agent memory to ensure consistency after a session.
High-intent search queries and answers about installing and using this skill.
To reconcile project docs and agent memory, align CLAUDE.md, AGENTS.md, docs/, and memory stores against the latest codebase changes. This updates facts with absolute dates, removes outdated entries, and preserves a single, conflict-free knowledge baseline across all outputs.
Cleaning up stale documentation and conflicting memories before a developer handoff requires auditing root documents and agent memory against the code. This ensures onboarding drafts and runbooks stay aligned so teammates and other agents see the same facts.
Updating onboarding docs and runbooks involves synchronizing project-level documentation and agent memory with recent codebase changes. This harmonizes the knowledge layers so new developers can directly start coding with accurate, conflict-free information.
Yes, this documentation reconciliation tool is cross-platform and works with OpenAI Codex, Claude Code, OpenCode, and OpenClaw. It audits and harmonizes project-level documentation and agent memory across these environments to ensure consistency.
You should trigger a knowledge reconciliation workflow when a development milestone finishes, before teammate handoffs, or when you notice stale docs and conflicting memories. It aligns your project knowledge baseline to prevent information drift across sessions.
mgratzerCreate CLAUDE.md, AGENTS.md, docs/, README, and CHANGELOG.md for Forge projects.
nikkogiblerCreate date-stamped markdown handoff documents with decisions and next steps.
a-ariffSynchronize task outputs to mem0-memory-mcp and obsidian-memory stores.
jrmatherlyRebuild project documentation and Serena memories to correct drift after code changes.
