review-tests SKILL.md skillA
review-tests from mukiwu/muki-ai-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mukiwu/muki-ai-plugins/review-tests@git:20260705.11bc9b8Pins git:20260705.11bc9b8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mukiwu/muki-ai-plugins
- Path
plugins/review-tests/skills/review-tests/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260705.11bc9b8, committed Jul 5, 2026
- First version recorded
- Jun 3, 2026
- Size
- 9,086 bytes
- Repository stars
- 73
- License
- none declared
測試體檢診斷器（test review / audit existing tests / find test blind spots）——讀一份既有測試，找出盲點與建議，產出一份 self-contained HTML 報告（不修改任何 source／測試／設定）。報告每條 finding 帶嚴重度，可 toggle 展開被測 source 的關鍵幾行。只診斷不寫測試：要補測試或自動改善測試，請改走 tdd 或你的測試改善 skill。.
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
# 測試體檢診斷器 (Review Tests) ## 定位 純診斷工具。讀一份既有測試，找出盲點、列出建議，**產出一份 HTML 報告**。 這個 skill 不寫測試、不改測試、不碰 source 與設定。它只負責「指出問題」並把結果呈現成報告，要不要補、怎麼補，由使用者決定。 ## 三條硬規則（最優先） 1. **只診斷，不改既有檔案**：不修改任何 source、測試檔或設定檔。唯一允許的寫入是**產生一份新的 HTML 報告檔**到 `.review-tests/`。 2. **補測試走 `tdd`**：報告列出的缺漏，請使用者改用 `tdd` skill 一次一個 red-green 補上，不要在這裡批次補。 3. **只列行為層級盲點**：建議的測試一律用「應該驗證什麼行為」描述。嚴禁為了衝覆蓋率而建議貼著實作細節的測試——那種測試會在 refactor 時誤報，違反 tdd「測行為不測實作」的原則。 ## 語言與輸出規範 - 報告內容使用繁體中文（台灣用語）。 - 技術術語保留英文，例如 Vitest、TypeScript、mock、coverage。 - 程式碼區塊、檔案名稱、identifier 嚴禁修改或翻譯。 - **用邏輯通順的中文表達，不要逐字英翻中**：保留 function 名、API 欄位、enum 值等專有名詞的英文原文，但句子要自然、讓使用者一看就懂，重點放在「為什麼是問題」，不要堆術語或生硬直譯。 ## 輸入 - **無參數**：詢問使用者目標檔案路徑。 - **指定檔案**：`review-tests <path>`。可給測試檔，或給 source 檔由本工具找出對應的測試檔。 ## 流程 1. **定位測試與 source**：讀取目標。若給的是 source 檔，找出對應測試檔；若給測試檔，找出它 import 的 source 檔。若找不到測試檔，回報「尚無測試」並建議改走 `tdd` 從頭建立，流程結束。 2. **檢查**：對照下方五類維度，逐項檢視測試內容，產出 findings，並為每條標嚴重度（`high`＝會產生假綠燈或掩蓋真 bug、`med`＝驗證力不足、`low`＝可讀性與慣例）。 3. **定位關鍵 source 片段**：為**每一條 finding** 找出被測的那個 source 函式（不是 spec 裡的 test，語言不限 TS），記下：函式名稱、source 檔路徑、以及**與這條 finding 真正相關的關鍵行範圍**（通常 3～8 行，不是整個 function——展整個 function 重點會被淹沒、不好找）。 4. **產生 HTML 報告**：依下方規格寫出單檔 HTML 到 `.review-tests/`，自動開啟。 …
Read the whole file at its exact version.
How to install
mdr add mukiwu/muki-ai-plugins/review-tests@sha256:2ab4c561ffb492b9The line at the top of this page pins the label git:20260705.11bc9b8, 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_h56rt7xkib77qj5n)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 3, 2026 and Jul 5, 2026, about one every 33 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260705.11bc9b8 latest | 2026-07-05 | 11bc9b8 | 9,086 B | A | view · diff |
| git:20260603.eb1107d | 2026-06-03 | eb1107d | 7,226 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9086 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
mukiwu/muki-ai-plugins · 73 stars · license none declared · pushed 2026-10-20 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_h56rt7xkib77qj5n GET https://markdownregistry.com/api/v1/resolve?ref=mukiwu/muki-ai-plugins/review-tests GET https://markdownregistry.com/api/v1/blob/2ab4c561ffb492b9d7ca57dbcd8b6e6f93abfc836425698b0e16465e47632457
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: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from mukiwu/muki-ai-plugins
Every file in mukiwu/muki-ai-plugins