neat-freak

Reconciles project documentation and agent memory against code after development sessions.

2|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/Nzettodess/Awesome-Agent-Skills --skill neat-freak-nzettodess
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: neat-freak
Source: https://github.com/Nzettodess/Awesome-Agent-Skills/tree/main/Skills/Engineering%20Skills/skills/neat-freak
Command: npx skills add https://github.com/Nzettodess/Awesome-Agent-Skills --skill neat-freak-nzettodess

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? After a development session, project docs (CLAUDE.md, README.md, docs/) and agent memory drift out of sync with the actual code, causing future AI sessions and human teammates to act on stale or conflicting information. ## Core Features & Use Cases - Three-layer knowledge reconciliation: Audits agent memory, project-root markdown (CLAUDE.md/AGENTS.md), and docs/ as separate audiences with distinct responsibilities. - Anti-bloat enforcement: Applies size limits and a "rules not changelog" policy to keep CLAUDE.md lean, migrating historical narrative to docs or deleting it. - Change-impact matrix: Maps code changes (new APIs, env vars, database tables, cross-project changes) to the exact documents that must be updated, including downstream integration guides. - Use Case: After shipping a new API flow across two projects, trigger the skill to enumerate every doc, update the integration guide, architecture doc, runbook, and handoff notes on both sides, prune stale memory entries, and produce a change summary. ## Quick Start Ask the agent to sync up the docs and memory after this development session so everything matches the current code.

Frequently Asked Questions about neat-freak

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I keep CLAUDE.md and project docs in sync with code changes?▼

Run an end-of-session documentation sync that enumerates every markdown file, maps code changes to affected docs, and edits files directly. The skill updates CLAUDE.md, docs/, README, and agent memory, then verifies each file against a completeness checklist.

What should and should not go into CLAUDE.md or AGENTS.md?▼

Include hard boundary rules, prohibited actions, command cheatsheets, environment variables, and pointer tables to deeper docs. Exclude historical narratives, detailed mechanism explanations, one-off incident retrospectives, and bug-fix logs, which belong in git history or docs/.

Does this documentation sync work with Codex, OpenCode, and OpenClaw?▼

Yes, the skill is cross-platform and covers Claude Code, OpenAI Codex, OpenCode, and OpenClaw. A reference file lists each platform's memory and config paths, and agents without a dedicated memory system simply skip that layer.

How do I handle documentation when a change affects multiple projects?▼

Run the full enumeration step for every affected project, not just the one that changed. Cross-project changes like shared APIs, SDKs, subdomains, or environment variables require updating integration guides on both the upstream and downstream sides.

Why does CLAUDE.md keep growing and how do I prevent bloat?▼

Bloat comes from appending session narratives as blockquotes instead of maintaining rules. The skill enforces a roughly 300-line soft limit, deletes or migrates historical entries to docs, and treats any net growth over 30 lines per sync as a red flag.