Hermes Neat Freak

Hermes-native end-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (AGENTS.md, README.md, docs/), Hermes memory, session recall, and reusable skills against the real code so nothing rots. 会话结束后对 Hermes 项目的文档、记忆和技能进行洁癖级审查与同步。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", or asks for a clean handoff after development work.

11 starsWriting & Content

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add chqchshj/hermes-neat-freak --skill hermes-neat-freak

Manual install

git clone --depth 1 https://github.com/chqchshj/hermes-neat-freak.git /tmp/hermes-neat-freak
mkdir -p ~/.claude/skills
cp -r /tmp/hermes-neat-freak/. ~/.claude/skills/hermes-neat-freak

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Hermes 洁癖 — Knowledge Base Neat-Freak

你是一个**知识库编辑**，不是记录员。你的目标不是追加更多内容，而是让 Hermes 项目的知识体系保持**干净、准确、对新人友好**。

## 适用对象

这个版本专门针对 **Hermes Agent** 及其工作方式：

- 长期事实 → `memory`
- 可复用流程 → `skill_manage`
- 跨会话回顾 → `session_search`
- 项目级指令 → `AGENTS.md`
- 对外文档 → `README.md`、`docs/`、网站文档

## 核心原则

### 三类知识，三种去处

| 类型 | 放哪里 | 不该放哪里 |
|---|---|---|
| 稳定事实、偏好、环境约定 | `memory` | skill / 临时进度 |
| 可复用操作流程、排错方法 | skill | memory |
| 当前项目约定、结构、红线 | `AGENTS.md` | memory |
| 给同事/用户/下游看的说明 | `README.md` / `docs/` | 只写进 AGENTS.md |
| 历史任务过程 | `session_search` 可回顾 | memory |

**不要混用。** 这是 Hermes 最容易“脑腐”的地方。

## 执行流程

### 第一步：盘点现状（必须机械枚举）

1. 对当前项目：
   - 列根目录
   - 枚举 `docs/`（若有）
   - 找出散落的 `.md`
   - 读 `README.md`、`AGENTS.md`、相关 docs
2. 读全局 Hermes 相关配置（如需要）
3. 用 `session_search` 回顾相关历史会话（如果这能减少用户重复背景）
4. 回顾本次对话全部内容
5. 输出内部文件清单：每个文件标记为「评估过 / 要改 / 不用改」

### 第二步：识别变更影响

不要只看“新增了什么”，要看“会波及哪层文档”。

常见映射：
- 新命令 / 新路由 → `AGENTS.md` + 对应使用文档 + reference 文档
- 新配置项 / 新超时 / 新 provider 行为 → `AGENTS.md` + configuration / integrations docs
- 新工作流 / 新平台特性 → README + user-guide + reference
- 技能或记忆机制变化 → skills docs + `AGENTS.md` + 相关 skill
- 跨项目改动 → 上下游两边文档都补

不确定时查 `references/sync-matrix.md`。

### 第三步：实际修改

必须真的改文件或调用工具，不接受“我会怎么改”的口头收尾。

推荐顺序：
1. 对外 docs
2. `AGENTS.md`
3. `memory`
4. `skill_manage`

### 第四步：编辑原则

- **合并优于追加**
- **删除优于保留**
- **精确优于冗长**
- **绝对时间**：写 `2026-04-30`，不要写“今天”
- **区分事实与流程**：事实进 memory，流程进 skill
- **先确认再写高风险外部系统**：数据库批量写入、线上配置变更等，没有确认不能在文档里写成“已执行”

Read the full skill on GitHub

Details

Skill name: hermes-neat-freak
Repository: chqchshj/hermes-neat-freak
License: MIT
Repo updated: 30 April 2026

FAQ

What does the Hermes Neat Freak skill do?

How do I install the Hermes Neat Freak skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add chqchshj/hermes-neat-freak --skill hermes-neat-freak. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Hermes Neat Freak popular?

It lives in chqchshj/hermes-neat-freak, which has 11 GitHub stars and 0 forks.

Related skills

Daily Newsletter

zinan92/daily-newsletter

Operate, verify, or improve a local-first Daily Inbox pipeline that turns source feeds, X, media, manual links, and saved items into Chinese Markdown/HTML/PNG artifacts plus Feishu delivery receipts. Use when a user asks to run, debug, review, package, or extend the daily-newsletter / Daily Inbox workflow.

Writing & Content

PheroPath

zi-yue-1129/PheroPath

A filesystem-based stigmergy communication protocol. Use this to leave invisible "pheromones" (signals) on files to communicate context, risks, or status to other agents or your future self without modifying file content.

Writing & Content

Humanizer Svenska

nordefors-max/claude-humanizer-svenska

Remove signs of AI-generated writing from Swedish professional text. Covers business writing, report writing, article writing, and social media posts. Detects and fixes patterns specific to Swedish AI output including: significance inflation, passive voice as false formality, nominalization overuse, anglification, vague attribution, structural tells, sycophancy, filler phrases, excessive hedging, knowledge-cutoff disclaimers, copula avoidance, bullet/emoji formatting, and soulless register.

Writing & Content

Novel Creation Omnibus

limingnanyue/novel-creation-omnibus

小说创作全能工坊v10.0——46套工具，从0到完本一条龙。覆盖：长篇正文写作、大纲细纲规划、世界观搭建与人物塑造、短篇故事、虐心BE发刀、玩梗热梗、去AI味反套话（含Claude/DeepSeek/GPT/Qwen/Kimi/豆包各策略+DeepSeek句式黑名单734条+51意象词+白名单系统+L1-L4四层硬门禁+L3方法论三节+6类逐句审查判据+段落功能二分法）、衔接修复与因果分析、状态追踪与伏笔管理、质量门控、同人创作与OOC控制、网文生产流水线、番茄爆文与系统流爽文、白描克制与现实主义平庸、模型适配优化、通感痛觉描写、规则怪谈、无限流、直播文、末世废土、悬疑推理、种田日常、细节真实感体系（五感/口语化/小动作/食物/环境）、对话写作大师（潜台词/声线/群像/吵架表白告别专项+MBTI 16型对白声线档案+4气质组对照+群戏冲突设计+MBTI情绪表达契合）、开篇钩子工坊（12种爆款开篇/300字生死线/章末钩子库）、情节工程（番茄循环/反转7式/冲突6级/节奏曲线+Dramatica 11拍节拍结构+钩子真假4维判定+伪因果5大典型+节拍×伏笔×角色协同矩阵+章末钩子4型）、读者心理学（代入感/爽点/虐点/弃书TOP10对策）、场景写作（场景四要素/6大类型/进出衔接技巧）、人物弧光（正向弧7阶段/负向弧/关系弧）、长篇连载管理（存稿策略/断更恢复/读者留存）、平台写作规

Writing & Content

Hw Review

ericshang98/hw-review

Use when reviewing hardware projects, verifying schematics against datasheets, managing chip documentation, checking pin connections, or aligning firmware with hardware design. Triggers on .epro2 .kicad_sch .SchDoc files, BOM review, datasheet lookup, pin verification, schematic review, PCB review, hardware-firmware alignment.

Writing & Content

Cnipa Patent Writer

fnjialun/cnipa-patent-writer

撰写中国发明专利申请文档（.docx）：有模板时严格套用模板版式（页眉页脚、分节、字体字号、缩进、行距、分页、附图编排），无模板时按 CNIPA 标准版式生成——但**只借格式、绝不抄模板的技术内容**，内容/配图全部据待保护的技术方案重新生成。覆盖说明书摘要 / 权利要求书 / 说明书（技术领域·背景技术· 发明内容·有益效果·附图说明·具体实施方式/实施例）/ 说明书附图，并生成白底黑线配图（数量与类型按内容定）。 Use this skill whenever the user asks to write / draft / 写 / 起草 a patent, 专利, 发明专利, 专利交底书, 权利要求书, 说明书, or to turn a system / feature / algorithm into a patent application "套用模板"/ "参照模板格式" —— even if they only say "把这个项目写成一篇专利" or hand you a template .docx and a codebase. Also triggers for editing an existing patent .docx to match a template's format, regenerating patent figures, or

Writing & Content

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.