| ### π§Ή neat-freak > *"If I don't run /neat before closing the window, I get itchy. Like there's something stuck in my throat."* After every session, run `/neat`. It reconciles whatever you changed in this conversation against three layers of project knowledge: **docs**, **root CLAUDE.md / AGENTS.md**, and the **agent's memory system**. Outputs a change summary at the end. **Why you'd want this** You've probably hit this: code has been through 7-8 iterations but the README is still v1.0.0. Memory says you're using SQLite when you actually switched to PostgreSQL months ago. CLAUDE.md lists routes that no longer match the actual server. The agent isn't getting dumber β your docs and memory are. neat-freak's job is to clean it up. **It touches three layers** - Project root CLAUDE.md / AGENTS.md (read by the AI in this project) - Project docs/ and README (read by teammates and downstream developers) - The agent's own memory system (read by future you across sessions) These three layers have different audiences and don't overlap. That's exactly why I wasn't satisfied with Claude Code's AutoDream β it only touched memory, leaving the docs to rot. **How to trigger** ``` /neat # direct command sync up # natural language tidy up docs # natural language ζ΄ηδΈδΈ # δΈζ ``` **π Cross-platform**: Claude Code Β· Codex Β· OpenCode Β· OpenClaw [](https://clawhub.ai) [](https://tessl.io/registry/khazix-skills/neat-freak) β [SKILL.md](./neat-freak/SKILL.md) Β· [Article (Chinese)](https://mp.weixin.qq.com/s/tg1wd-iN2gWHWhXdY0faeg) |
| ### π hv-analysis (Horizontal-Vertical Analysis) > *"Vertical axis chases time depth, horizontal axis chases simultaneous breadth. They cross to give you the verdict."* Want to actually understand what a product / company / concept / person is about? Hand it over. It runs two threads in parallel: **vertical** β tells the subject's story from inception to the present moment, like a narrative; **horizontal** β lays out every major competitor at the current moment for comparison. When the two cross, you see things that neither current-state nor history alone would show you. The output is a **typeset PDF research report**, 10,000β30,000 words. **Good for** - Competitor research / understanding a new concept / company background research - Front-loaded research before writing or strategy work - Wanting to understand a domain from scratch **Not good for** - A simple definition lookup β overkill, just ask in regular chat - Writing a long-form article β that's [khazix-writer](#-khazix-writer)'s job [](https://clawhub.ai) [](https://tessl.io/registry/khazix-skills/hv-analysis) β [SKILL.md](./hv-analysis/SKILL.md) Β· [Article (Chinese)](https://mp.weixin.qq.com/s/Y_uRMYBmdLWUPnz_ac7jWA) |
| ### βοΈ khazix-writer > *"A knowledgeable normal person earnestly talking about something that moved them."* The writing skill behind my own Chinese long-form articles. Once installed, the agent writes in **my voice, my rhythm, with my list of banned phrases** baked in. > β οΈ **Note for English readers**: This skill produces **Chinese** long-form articles (ε ¬δΌε· / WeChat-style). If your output language is English, this isn't for you. But you might find the methodology interesting as a reference for how to encode a personal voice into a skill. **Good for** You've read my Chinese articles, like the style, and want your AI to write in the same voice. Hand it a PDF, a transcript, or a news link β it'll turn it into a long-form piece. **Not good for** You want "good general writing." This skill takes a position. It **refuses** corporate jargon, **refuses** "first... second... finally" structures, **refuses** "in today's rapidly evolving AI landscape" openings. If your target reader actually likes that stuff, this skill isn't for you. **What's inside** - Complete style rules (rhythm, narrative, judgment, rhetoric) - A four-layer self-check system (structure, rhythm, content, language) - A curated style example library the AI can match against [](https://clawhub.ai) [](https://tessl.io/registry/khazix-skills/khazix-writer) β [SKILL.md](./khazix-writer/SKILL.md) Β· [Article (Chinese)](https://mp.weixin.qq.com/s/AtxGrii_K-nzkwUM9SNhEg) |
| ### π hv-analysis (Prompt edition) A **lighter version** of the hv-analysis skill above β a single prompt you paste into any Deep Research model (ChatGPT Deep Research, Gemini Deep Research, Grok Deep Search, Claude Research). No installation required. About 30 minutes to a 10k+ word research report. Good for people who haven't picked up Claude Code / Codex yet but still want to try the method. β [ζ¨ͺηΊ΅εζζ³.md](./prompts/ζ¨ͺηΊ΅εζζ³.md) Β· [Article (Chinese)](https://mp.weixin.qq.com/s/Y_uRMYBmdLWUPnz_ac7jWA) |