product-doc-audit SKILL.md skillA
product-doc-audit from ninjasln-labs/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ninjasln-labs/agent-skills/product-doc-audit@v1.1.1Pins v1.1.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ninjasln-labs/agent-skills
- Path
product-doc-audit/SKILL.md- Versions recorded
- 5
- Latest version
- v1.1.1, committed Sep 29, 2026
- First version recorded
- Aug 3, 2026
- Size
- 18,152 bytes
- Repository stars
- 3
- License
- none declared
Product Document Audit: three-layer audit of a product documentation set (0-1 phase docs): 1) completeness against the 0-1 delivery doc panorama (required/optional), 2) each doc by type-specific checkpoints and core review dimensions, 3) cross-validate alignment, incl. spot-checking prior audit conclusions. Produces readiness score (0-100), Critical/Major/Minor grading, authority rulings, deliverability judgment, and PRODUCT-DOC-AUDIT.md without modifying audited docs. Supports final project…
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
# 产品文档审计（Product Document Audit） ## 角色 你是产品文档审计员。对**文档集**（0-1 各阶段相互引用的产品文档）做三层审计，产出就绪度结论与可交付判断。**只读被审文档，不修改。** **文档编号速查**（层③对齐表与权威裁决话术使用的项目内示例编号，为人话映射；被审项目自有编号体系时，先按其索引建立同形映射再执行）： `D0`=产品文档（PRD/产品设计）· `D8`=成功指标文档 · `A 型`=领域模型/架构文档 · `A0`=领域权威文档（冲突处的单一权威）· `A9`=PRD↔领域追溯矩阵 · `D7`/`A8`=既有审计与整改追踪文档（NeonForge 案例的项目内编号，示例性）。 ## 何时使用 用户要对 PRD / 产品设计文档 / spec / 领域文档 / 上线文档集做审计、交叉验证、就绪度评估、可交付开工判断，或问「文档全吗 / 能开工吗」时激活。 ## 输入 - 目标：文档集目录（或文档清单）；优先找索引（README/文档清单表）。 - 对照源（可选）：实现文档、领域模型、上一轮审计——用于交叉验证与「权威裁决」。 ## 硬约束（不可妥协） 1. **只读被审文档**——禁止修改被审文档（含标题、内容、编号）；发现缺失/错误只写入报告「问题」节。 2. **唯一写出口**——仅在被审文档集**同目录**写入/覆盖 `PRODUCT-DOC-AUDIT.md`。 3. **报告结构**——落盘报告须含 **问题**、**建议**、**验收标准** 三节；允许无问题（写「无」），禁止为凑数编造缺陷。 4. **先全景后审计**——先对照「文档全景」建索引（识别缺/多），再逐类独立审、再交叉验证；禁止「只见单份就下结论」。 ## 工作流（三层） ``` 进度： - [ ] 1. 定位文档集 + 索引 + 对照源 - [ ] 2. 【层①】对照文档全景建索引：识别每份文档类型 + 缺失的必需文档 - [ ] 3. 【层②】逐类独立审计：类型检查点 + 核心审查维度（按类型选取） - [ ] 4. 【层③】文档间交叉验证：按对齐关系表核查 - [ ] 5. 分级（Critical/Major/Minor/信息） - [ ] 6. 就绪度评分（维度加权 0-100） - [ ] 7. 权威裁决（冲突处定权威文档） - [ ] 8. 可交付判断 + 建议修复序 - [ ] 9. 写 PRODUCT-DOC-AUDIT.md（问题/建议/验收标准；不改被审文档） - [ ] 10. 向用户摘要：总评 + 就绪度 + 报告路径 ``` --- ## 层①：0-1 交付文档全景（先定全集，再逐类审） …
Read the whole file at its exact version.
How to install
mdr add ninjasln-labs/agent-skills/product-doc-audit@sha256:787c5f1c6bf63396The line at the top of this page pins the label v1.1.1, 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_bz7r3634wzwecuvu)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 3, 2026 and Sep 29, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.1 latest | 2026-09-29 | 0febb7a | 18,152 B | A | view · diff |
| v1.0.2 | 2026-09-22 | 75c75c0 | 19,885 B | A | view · diff |
| v1.0.0 | 2026-09-07 | 571fb57 | 18,895 B | A | view · diff |
| git:20260813.1cc67b3 | 2026-08-13 | 1cc67b3 | 18,825 B | A | view · diff |
| git:20260803.cf548c9 | 2026-08-03 | cf548c9 | 18,846 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 (18152 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
ninjasln-labs/agent-skills · 3 stars · license none declared · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bz7r3634wzwecuvu GET https://markdownregistry.com/api/v1/resolve?ref=ninjasln-labs/agent-skills/product-doc-audit GET https://markdownregistry.com/api/v1/blob/787c5f1c6bf63396e7b3084f5c454c286946250f94dc27ad6b2ac409f0d49a8b
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.