request-pr-review SKILL.md skillA
request-pr-review from hsuanyulee/polaris is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hsuanyulee/polaris/request-pr-review@v4.0.0Pins v4.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hsuanyulee/polaris
- Path
.claude/skills/request-pr-review/SKILL.md- Versions recorded
- 7
- Latest version
- v4.0.0, committed Oct 20, 2026
- First version recorded
- Aug 28, 2026
- Size
- 12,861 bytes
- Repository stars
- 5
- License
- MIT
"把使用者名下已經開好的 PR 蒐集起來、帶回每一個的 review 狀態、列出來讓他決定要請誰看，然後通知對的人。Trigger: '我的 PR', 'request PR review', 'ask someone to review my PR', 'PR 狀態', '催 review', '催 PR', 'PR 被 approve 了嗎', '幫我掃我的 PR', '請同仁 review', '請同仁幫我 review', '請大家 review', '請大家幫我 review', '請大家幫忙看一下', '找人 review', '找誰 review', '請[人名/角色]幫我 review', '請[人名/角色]幫忙看 PR'. 主語為同仁/大家/人名/角色的「請X幫我 review」屬於催 review 範疇，不要 route 到 review-pr。" 使用者問**自己的** PR 現在怎麼樣，或想找人來看。例如「我的 PR」「PR 狀態」 「催 review」「PR 被 approve 了嗎」「請同仁幫我 review」。 「請〈某人/大家〉幫我…
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
# request-pr-review — 請人來看已經開好的 PR
實作做完、PR 開出來了，缺的是最後一步：**請同事看**。這支 skill 承載那一步的全部——這批
總共有多少、分在哪些 repo、每一個現在被誰看了、要通知誰。
三步，順序固定，**中間那一步是人**：
1. **query** 名下所有 open PR，帶回每一個的 review 狀態。
2. **列出來問使用者要怎麼處理**——列的東西要足夠讓他當場決定，不用再去 GitHub 翻一遍。
3. **照他的決定通知對的人**。
## 這支 skill 不知道的三件事
**要看哪個 org、哪個 repo 通知誰、一張單長什麼樣。** 三者都由認領那個 org 的 skill 在
自己的 `SKILL.md` 宣告，這裡掃所有 skill 找那一行：
```
<!-- {任意前綴}-PR-CONTEXT-{org}: {命令} -->
```
鍵裡那一段就是 org 名，所以掃一次同時回答「要 query 誰」與「拿到之後問誰」。一個宣告都
沒有時說出來並停下——**不猜一個 org，不用占位字串當預設值**。
**命令裡的相對路徑，錨是宣告它的那份 `SKILL.md` 所在的目錄**，不是呼叫者當下的 cwd——核心
跑它之前會先切過去。宣告行寫得出來的只有相對路徑，而「相對於我自己」在 skill 被單獨帶到
別的環境時仍然成立，「這個 workspace 的 root 在哪」在那裡沒有答案。
宣告的命令要認得兩個模式，第一個參數就是模式名：
| 模式 | 進 | 出 |
|---|---|---|
| `notify --repo R` | 參數 | 這個 repo 的 PR 通知誰，格式由那一層自己定 |
| `ticket` | stdin：`repo⇥number⇥title⇥branch` | `repo⇥number⇥單號⇥單的 URL` |
`ticket` 走 TSV 而不是把 PR 的 JSON 丟過去：那個資料結構是這支 skill 的事，交出去等於逼
每一家公司的知識層都得認得它。**這裡不認得任何一家公司的單號長什麼樣**，也不該認得。
所以這裡沒有前置設定要人先準備，也不需要任何環境變數。author 沒指定時自己偵測：
```bash
MY_USER="$(gh api user --jq '.login')"
```
approval threshold 是公司 pack 的知識，不是這支 skill 的：幾票算看過了由那家公司說，寫在它自己
的 pack 裡（repo-notes 那支的 PR 與 review 慣例那一份）。`check-pr-approval-status.sh` 的
…Read the whole file at its exact version.
How to install
mdr add hsuanyulee/polaris/request-pr-review@sha256:4641a450f32bb0deThe line at the top of this page pins the label v4.0.0, 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_lzgsu5nwnkdcbbif)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 28, 2026 and Oct 20, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v4.0.0 latest | 2026-10-20 | 1870cae | 12,861 B | A | view · diff |
| v4.0.0 | 2026-10-20 | 51562a5 | 12,231 B | A | view · diff |
| v4.0.0 | 2026-09-04 | 0500cde | 11,625 B | A | view · diff |
| v4.0.0 | 2026-09-03 | 910b3a3 | 11,442 B | A | view · diff |
| v4.0.0 | 2026-09-02 | 19b87ef | 10,497 B | A | view · diff |
| v4.0.0 | 2026-08-31 | ce59123 | 9,943 B | A | view · diff |
| v4.0.0 | 2026-08-28 | a2bd2a4 | 9,595 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 (12861 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
hsuanyulee/polaris · 5 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lzgsu5nwnkdcbbif GET https://markdownregistry.com/api/v1/resolve?ref=hsuanyulee/polaris/request-pr-review GET https://markdownregistry.com/api/v1/blob/4641a450f32bb0defcf987480a8fca3cfa9b288ef1709cc4b90603807571aef2
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.