DESIGN.md@spec/docsA
DESIGN.md@spec/docs from kerberosclaw/kc_ai_skills is a DESIGN.md file: the design rules coding agents follow in that repo.
mdr add kerberosclaw/kc_ai_skills/spec/docs/DESIGN.md@git:20261015.be10792Pins git:20261015.be10792 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- DESIGN.md file
- Repository
- kerberosclaw/kc_ai_skills
- Path
spec/docs/DESIGN.md- Versions recorded
- 2
- Latest version
- git:20261015.be10792, committed Oct 15, 2026
- First version recorded
- Mar 29, 2026
- Size
- 5,311 bytes
- Repository stars
- 79
- License
- MIT
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
> **English summary:** Design document for the `/spec` skill — a spec-driven development workflow that guides users from fuzzy requirements to verified deliverables. One entry point, auto-detects project state, handles both small features and large multi-module projects. # /spec Skill — 設計文件 > 現況註記（2026-10-15）：以下保留早期設計背景；目前 spec 1.9.0 對簡單功能將計畫內嵌在 spec.md，複雜功能才獨立 plan.md，tasks.md 仍保留。下文「用 plan.md 作骨架」應理解為讀取已選定的計畫位置；task 數量也不以 5–10 為硬門檻。現行判準見 [review.md](../references/review.md)。 ## 解決什麼問題？ 用 AI agent 寫 code 最常見的災難： 1. **需求沒想清楚就開工** → 做到一半發現方向錯，砍掉重來 2. **換一個對話就失憶** → 重新解釋一次上下文，浪費時間 3. **做完沒驗收** → 自以為做完了，其實漏了一堆邊界條件 4. **沒有紀錄** → 三個月後回來看 code，忘記當初為什麼這樣設計 這套流程用檔案把每個階段的產出持久化，讓 agent 跨對話也能接著做。 ## 為什麼是一個 skill 而不是多個？ 早期設計考慮過拆成 4 個 skill（spec-init / spec-review / spec-check / spec-report），但： - User 要記多個指令，認知負擔高 - 不清楚「現在該打哪一個」 - 開源後新 user 學習成本更高 最終決定：**一個 `/spec` 入口，靠檔案狀態自動判斷階段**。User 只要記一個指令。 ## 為什麼需要 Discovery Stage？ 不是每個需求都適合直接產 spec。判斷標準： | 情況 | 例子 | 處理方式 | |------|------|---------| | 明確的單一功能 | 「做一個 Markdown loader」 | 直接 Spec Stage | | 模糊的大系統 | 「做一個 RAG pipeline」 | 先 Discovery → DESIGN.md → 再拆 spec | Discovery 的產出是 `docs/DESIGN.md`，這份文件會被後續所有 spec 引用作為上下文。 ## 審查機制的設計 …
Read the whole file at its exact version.
How to install
mdr add kerberosclaw/kc_ai_skills/spec/docs/DESIGN.md@sha256:f13690a1208d80cdThe line at the top of this page pins the label git:20261015.be10792, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6sd6mlspo23ywkqv)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Mar 29, 2026 and Oct 15, 2026, about one every 200 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.be10792 latest | 2026-10-15 | be10792 | 5,311 B | A | view · diff |
| git:20260329.186f525 | 2026-03-29 | 186f525 | 4,952 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (5311 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kerberosclaw/kc_ai_skills · 79 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6sd6mlspo23ywkqv GET https://markdownregistry.com/api/v1/resolve?ref=kerberosclaw/kc_ai_skills/spec/docs/DESIGN.md GET https://markdownregistry.com/api/v1/blob/f13690a1208d80cd55c2d05eb441d6d698b402b8c07685587be3dc7da3e17a82
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: what DESIGN.md is and how agents use it · which agent file does what.