intended-vs-implemented

Solid

Auditing AI-built code against its docs: where it does what the docs or permissions don't say, access control against documented roles, cited both sides.

AI & Automation 633 stars 85 forks Updated today MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
93
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Intended vs. Implemented: Auditing the Gap ## Purpose **Compare implementation with recorded intent to find the gaps linters cannot.** A linter can check internal consistency, but it has no model of what you meant. Important security and correctness bugs live in that gap. Examples include unenforced permissions, publicly callable "cron-only" endpoints and public-only fields leaking private data. This method works only when intent has been written down first. Apply the `shipping-artifacts` skill for that record. That intent axis distinguishes the method from commodity tools. ## Context **Audit documented intent, and report absent or stale docs first.** Use `permissions.md`, `architecture.md`, `variables.md` or the repository's equivalents, under whatever names it uses. You cannot audit intent never recorded. If those docs are absent or stale, make that the first finding and recommend documenting first, then auditing. ## Method 1. **Establish intent.** Treat system docs as claims to verify. Read them wherever the repository keeps them; the default is `documentation/*.md`. Apply the `shipping-artifacts` skill for those docs. They state what should hold: who may access what, trusted boundaries and public data. They are not proof. 2. **Gather implementation evidence.** Cite the code that enforces or fails to enforce each claim. Evidence is file and line for the actual authorization check, query filter or sanitizer. "It's probably handled upstream" is not evidence; the co...

Details

Author
phuryn
Repository
phuryn/product-engineering
Created
2 weeks ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

pm-ai-ship-audit

AI 生成代码的上线前审计技能(vibe-coded app 交付审计)。两个方法 + 五条流程: 「文档基线」(架构、用户与权限流、权限矩阵、变量与密钥、测试覆盖地图,外加邮件/定时任务/SEO/内嵌 Agent 四个条件文档)、 「意图 vs 实现」(找文档写了但代码没做到的差距——通用扫描器发现不了的那一类 bug); 流程含反向补文档、推导测试覆盖、静态安全审计、静态性能审计(专抓 N+1 与请求瀑布)、上线检查总装。 能力:(1) 给 AI 写出来的代码补齐可评审的文档基线 (2) 交叉核对文档意图与代码实现的差距 (3) 出带证据行(file:line + 原文片段)且经过自我反驳的审计报告。 触发词:「上线前检查」「AI 代码审计」「vibe coding 检查」「代码和文档对不上」「权限有没有漏」 「安全审计」「性能审计」「N+1」「请求瀑布」「补系统文档」「测试覆盖地图」「ship check」, 或者用户说「这个项目是 AI 写的,能上线吗」时。 不适用:常规代码评审 → /code-review(Claude Code 内置,Codex/Cursor 无此技能);架构与详细设计文档 → hld-design / lld-design; 测试用例设计 → pm-test-cases;系统性排障 → systematic-debugging。 参考文档为英文原文,产出语言跟随用户提问语言。

1 Updated 2 months ago
iDWong
Code & Development Listed

pm-ai-ship-audit

AI 生成代码的上线前审计技能(vibe-coded app 交付审计)。两个方法 + 五条流程: 「文档基线」(架构、用户与权限流、权限矩阵、变量与密钥、测试覆盖地图,外加邮件/定时任务/SEO/内嵌 Agent 四个条件文档)、 「意图 vs 实现」(找文档写了但代码没做到的差距——通用扫描器发现不了的那一类 bug); 流程含反向补文档、推导测试覆盖、静态安全审计、静态性能审计(专抓 N+1 与请求瀑布)、上线检查总装。 能力:(1) 给 AI 写出来的代码补齐可评审的文档基线 (2) 交叉核对文档意图与代码实现的差距 (3) 出带证据行(file:line + 原文片段)且经过自我反驳的审计报告。 触发词:「上线前检查」「AI 代码审计」「vibe coding 检查」「代码和文档对不上」「权限有没有漏」 「安全审计」「性能审计」「N+1」「请求瀑布」「补系统文档」「测试覆盖地图」「ship check」, 或者用户说「这个项目是 AI 写的,能上线吗」时。 不适用:常规代码评审 → /code-review(Claude Code 内置,Codex/Cursor 无此技能);架构与详细设计文档 → hld-design / lld-design; 测试用例设计 → pm-test-cases;系统性排障 → systematic-debugging。 参考文档为英文原文,产出语言跟随用户提问语言。

1 Updated 2 months ago
iDWong
AI & Automation Solid

shipping-artifacts

Documenting an AI-built app for handoff, review or audit: the docs that make it reviewable (architecture, flows, permissions, variables, coverage).

633 Updated today
phuryn