multica-review-backend SKILL.md skillA
multica-review-backend from it235/multica-best-practices is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add it235/multica-best-practices/multica-review-backend@git:20260910.699a593Pins git:20260910.699a593 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- it235/multica-best-practices
- Path
templates/zh_CN/skills/reviewer/multica-review-backend/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260910.699a593, committed Sep 10, 2026
- First version recorded
- Sep 10, 2026
- Size
- 2,193 bytes
- Repository stars
- 237
- License
- MIT
后端实现专属评审框架。由 BackendReviewer 调用，对 BackendDev 产出的 API 契约与后端实现做专业分析（契约质量/设计吻合/错误处理/单测充分性/验收对照），输出 PASS/FAIL 与修改清单，汇报 Leader。.
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
# 后端实现专业评审（BackendReviewer） 本 skill 提供对 **后端实现产物（API 契约 + 实现）**的结构化专业评审框架。调用方为 `BackendReviewer`，评审对象为 `BackendDev` 经 `multica-artifact-backend` 回传的链接与变更文件列表，以及 Leader 派活时给的架构设计引用。 ## 什么时候用 - BackendReviewer 收到 Leader 派发的「评审 API 契约 / 后端实现」任务时。 - 产物修改后进入复审轮次时（对照上一轮修改清单逐条核对）。 ## 评审维度（逐项给结论） 1. **契约质量**：字段命名、状态码、错误模型、版本策略是否清晰自洽。 2. **设计吻合度**：实现是否对齐 Architect 方案，偏离须有说明。 3. **错误处理**：异常分支、超时、幂等、边界条件是否覆盖。 4. **单测充分性**：关键路径、边界、异常分支是否覆盖；有无无效测试（标记并阻断）。 5. **TDD 与测试映射**：契约中的 API-ID 是否有对应单元测试；关键路径与异常是否覆盖。 6. **验收对照**：实现是否真正满足每条 AC-。 ## 输出格式 ```text 【后端实现评审】<变更链接> 结论：PASS / FAIL 阻断项（FAIL 时必填，每项含 理由 / 涉及点 / 修改方向）： - ... 建议项（非阻断）： - ... 与上一轮修改清单核对（复审时）：已解决 X 项 / 未解决 Y 项 轮次：第 N / 3 轮 ``` 结论与修改清单**汇报给 Leader**，不自行改代码、不自行通知 BackendDev。 ## 边界 - 只评后端契约与实现、单测，不评前端、UI、需求、架构设计本身、测试用例。 - 不替代 Leader 的通用门禁（`multica-verification` skill）。 - 架构层面分歧交 ArchReviewer，你只管实现层质量。 - 第 3 轮仍 FAIL → 标注「升级人类」，交 Leader 处理，停止循环。
Read the whole file at its exact version.
How to install
mdr add it235/multica-best-practices/multica-review-backend@sha256:718ac516910a6117The line at the top of this page pins the label git:20260910.699a593, 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_ky7z2e7iuzv7ead2)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 10, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260910.699a593 latest | 2026-09-10 | 699a593 | 2,193 B | A | view · diff |
| git:20260910.8db057c | 2026-09-10 | 8db057c | 2,194 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 (2193 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
it235/multica-best-practices · 237 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ky7z2e7iuzv7ead2 GET https://markdownregistry.com/api/v1/resolve?ref=it235/multica-best-practices/multica-review-backend GET https://markdownregistry.com/api/v1/blob/718ac516910a6117b7c7405eda90a8711b8e63b5b1b4743afee695432c05b0e0
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 it235/multica-best-practices
Every file in it235/multica-best-practices