Neat-Freak Knowledge Closeout

What it does

When your agent uses it

• Wrapping up a development session so docs and rules match the code
• Fixing a stale or conflicting CLAUDE.md or AGENTS.md
• Handing a project to a teammate or a fresh agent session
• Auditing whether workspace rules are actually followed

Example prompts

• “Wrap up this session: sync the README and CLAUDE.md with what the code does now.”
• “Run neat-freak on this project before I hand it to a teammate.”
• “The docs no longer match the code, so find the contradictions and fix them.”
• “List the leftover plan files and old backups in this repo as deletion candidates.”

Requirements

• Read access to the project files
• Git and `rg`, which improve verification but are optional
• Bash for `scripts/audit-inventory.sh`; without it the checks are done by hand
• Compatibility (from SKILL.md): Requires filesystem read access. Writes and destructive actions follow the active agent, workspace, and user authorization rules. Git and rg improve verification; scripts/audit-inventory.sh needs Bash — without it, do the equivalent checks manually. Works on any Agent Skills platform.

Workflow steps

8 steps, taken from the step headings in SKILL.md.

1. 1发现平台、规则和体量
2. 2建立现役事实矩阵
3. 3审计规则和实践
4. 4路由受影响知识面
5. 5先减后加地修改
6. 6谨慎处理记忆
7. 7验证并完成发布闭环
8. 8分两阶段用结果汇报

What it can do on your machine

Read from SKILL.md and the folder at commit 322346d. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • git
  • bash

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires filesystem read access. Writes and destructive actions follow the active agent, workspace, and user authorization rules. Git and rg improve verification; scripts/audit-inventory.sh needs Bash — without it, do the equivalent checks manually. Works on any Agent Skills platform.

  From compatibility in the SKILL.md frontmatter.

Context cost

Neat-Freak Knowledge Closeout loads about 1.9k tokens when it runs, and up to ~6.5k if it reads all its reference files. Until then it costs about 203 tokens; SKILL.md has 296 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~203

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from KKKKhazix/khazix-skills at commit 322346d, republished under its MIT licence (© KKKKhazix). 296 words, ~1,903 tokens.

name

neat-freak

description

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout intent without the name: syncing or tidying project docs/rules/memory after development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.

compatibility

Requires filesystem read access. Writes and destructive actions follow the active agent, workspace, and user authorization rules. Git and rg improve verification; scripts/audit-inventory.sh needs Bash — without it, do the equivalent checks manually. Works on any Agent Skills platform.

metadata.version

3.0.0

metadata.category

knowledge-governance

## 洁癖收尾完成

**影响**：<消除了哪些误导、风险或交接成本>

**改动 / 新建**
- <文件> — <改了什么，为什么>

**待你确认**
- 删除候选：<文件 + 理由>；未确认前一个都没删
- 无法裁决：<矛盾 + 两边证据>

**遗留**：<pending / out-of-scope / 未消除 warning；没有就写「无」>

© KKKKhazix, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 158 other files (scripts, references) in neat-freak of KKKKhazix/khazix-skills.

• SKILL.md
• evals/evals.json
• evals/fixtures/eval-1-routine-dev-sync/agent-memory/taskflow/memory/MEMORY.md
• evals/fixtures/eval-1-routine-dev-sync/agent-memory/taskflow/memory/project_api-design.md
• evals/fixtures/eval-1-routine-dev-sync/agent-memory/taskflow/memory/project_deploy.md
• evals/fixtures/eval-1-routine-dev-sync/workspace/CLAUDE.md
• evals/fixtures/eval-1-routine-dev-sync/workspace/taskflow/AGENTS.md
• evals/fixtures/eval-1-routine-dev-sync/workspace/taskflow/CLAUDE.md
• evals/fixtures/eval-1-routine-dev-sync/workspace/taskflow/README.md
• evals/fixtures/eval-1-routine-dev-sync/workspace/taskflow/docs/architecture.md
• evals/fixtures/eval-1-routine-dev-sync/workspace/taskflow/package.json
• evals/fixtures/eval-1-routine-dev-sync/workspace/taskflow/src
• … and 147 more

Open the folder on GitHubat commit 322346d