ci-review SKILL.md skillA
ci-review from hanzhangzzz/agent-skills-zh is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hanzhangzzz/agent-skills-zh/ci-review@git:20261028.7206195Pins git:20261028.7206195 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hanzhangzzz/agent-skills-zh
- Path
ci-review/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261028.7206195, committed Oct 28, 2026
- First version recorded
- Sep 2, 2026
- Size
- 10,461 bytes
- Repository stars
- 1
- License
- MIT
Install a CI-triggered LLM code reviewer into the current repo: on every push to a PR/MR, Claude Code runs headless, reproduces every claim the change makes, hunts correctness bugs with concrete failure scenarios, and posts a machine-readable execution verdict. For configured bot branches (do/* by default), it also requires a separate value verdict before auto-merge, rejecting bookkeeping-only work and incomplete outcomes. Detects GitHub vs GitLab, installs a deterministic verdict gate, and…
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
# ci-review 给仓库装一个审查机器人：所有 PR 都回答**这次改动宣称做到的事，真的做到了吗？**； 对配置的机器人分支再回答**这件事值得自动进入默认分支吗？** 它不替人类评价普通 PR 的方向；但 `do/*` 没有人实时把关，必须额外通过价值门， 避免验证账本、重复 sweep 和未完成产物仅因"技术上没错"就自动合入。 配合 do-something 的 MR 模式即成飞轮：do-something 提出方向并实践，ci-review 验证实践质量， do-something 下一轮先回应它的评论。开"通过即合并"档后，机器人分支的收割也由机器完成，人类只在想否决时出现。 ## 触发条件 - `/ci-review`：装进当前仓库（幂等，已存在的文件不覆盖；`/ci-review --force` 覆盖）。 - `/ci-review status`：检查文件、合并档位、secrets/variables、最近运行。 - `/ci-review merge on|off`：改合并档位。 ## 安装流程 脚本只做确定性的事（识别平台、写文件、改档位、报状态）；问用户、设变量由你做。 ### 1. 依赖检查 当前目录是 git 仓库且有 origin，否则停下说明。GitHub 需要 `gh auth status` 通过，GitLab 需要 `glab auth status` 通过； 未登录就只装文件，变量留给用户手设。 ### 2. 装文件 ```bash bash <本 SKILL.md 所在目录>/scripts/install.sh [仓库路径] [--force] [--platform github|gitlab] [--merge on|off] ``` 脚本按 origin 主机名判平台：含 `github.com` → GitHub；含 `gitlab` → GitLab（自建实例也算）； 判不出退出码 2。此时用 AskUserQuestion 问"这个仓库托管在哪"（GitHub / GitLab），带 `--platform` 重跑。 | 平台 | CI 配置 | 审查规范 | |---|---|---| | GitHub | `.github/workflows/ci-review.yml`（官方 `anthropics/claude-code-action@v1`） | `.github/ci-review.md` + `.github/scripts/ci-review-verdict.sh` | …
Read the whole file at its exact version.
How to install
mdr add hanzhangzzz/agent-skills-zh/ci-review@sha256:cd95c7b0e25aaf1fThe line at the top of this page pins the label git:20261028.7206195, 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_mgdcjw2qk63etxof)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Sep 2, 2026 and Oct 28, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.7206195 latest | 2026-10-28 | 7206195 | 10,461 B | A | view · diff |
| git:20260904.43bb55f | 2026-09-04 | 43bb55f | 10,037 B | A | view · diff |
| git:20260903.ba8990e | 2026-09-03 | ba8990e | 9,464 B | A | view · diff |
| git:20260902.7e9351b | 2026-09-02 | 7e9351b | 5,031 B | A | view · diff |
| git:20260902.a1cf333 | 2026-09-02 | a1cf333 | 4,279 B | A | view · diff |
| git:20260902.5ded76a | 2026-09-02 | 5ded76a | 4,127 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 (10461 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
hanzhangzzz/agent-skills-zh · 1 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mgdcjw2qk63etxof GET https://markdownregistry.com/api/v1/resolve?ref=hanzhangzzz/agent-skills-zh/ci-review GET https://markdownregistry.com/api/v1/blob/cd95c7b0e25aaf1f8c3cc4c197e397d25cac256b45f1099b1f15f1e601120126
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 hanzhangzzz/agent-skills-zh
Every file in hanzhangzzz/agent-skills-zh