Audit Report

Organization

devcodex-labs

audit-report

报告审查维度 RA-1~RA-6 — 分析报告/审查报告质量专属审查层

Overview

Publisher	devcodex-labs
Repository	`devcodex`
Skill name	`audit-report`
Stars	433
Forks	44
Bundled files	1
License	AGPL-3.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by devcodex-labs on GitHub. Read the source before you install it.

Installation

Install the Audit Report AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/devcodex-labs/devcodex/tree/main/content/skills/audit-report
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/devcodex-labs/devcodex.git /tmp/devcodex
mkdir -p .claude/skills
cp -r /tmp/devcodex/content/skills/audit-report .claude/skills/audit-report

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Audit Report in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Audit Report on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Audit Report is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Audit Report Skill

适用范围

审查目标为报告文档（分析报告、审查报告、开发报告、修复报告）时，叠加本 Skill（在 G1~G5 之后）。

维度总览（RA-1~RA-6）

分组	维度	优先级
A — 内容质量	RA-1 内容完整性 · RA-2 事实准确性	🔴
B — 格式与追溯	RA-3 格式规范性 · RA-4 结论可追溯	🟡/🔴
C — 行动与关联	RA-5 行动项可执行 · RA-6 关联一致性	🟡/🔴

核心检查维度

RA-1 内容完整性 🔴

报告头部必填字段完整（项目/日期/类型/状态）
正文必需章节齐全（参照对应模板）
无空白章节或仅含"TBD"/"待填写"
audit 类报告包含审查轮次摘要（🔴 必填）
问题清单包含完整列（级别/维度/位置/描述/已验证/发现轮次/状态）
汇总型问题清单默认采用“两层结构”：先列根因级问题，再展开逐文件完整落点；边界/非缺陷结论单列，不混入缺陷编号

RA-2 事实准确性 🔴

结论有证据支撑（引用文件/终端输出/工具结果）
问题描述有具体位置（文件名+行号或章节标题）
无无法验证的断言
若报告把外部审查报告、AI review finding 或 audit issue 作为输入，需检查 ReviewFindingIntakeGate：报告是否仅作为线索、每条 finding 是否有本地证据和分类、是否误把设计/文档/测试缺口写成 must-fix runtime bug

RA-4 结论可追溯 🔴

每条结论可追溯到具体证据
问题状态准确（已修复的标注已验证轮次）
若存在“根因级归并”，必须能从根因项反查到逐文件落点，避免在汇总阶段吞掉文件级异常

ExternalReviewClaimVerificationGate（PF-164 · 外部审阅复核）

当报告是对外部审阅 / 他 Agent 审阅 / AI review finding 包的复核或转写时（不仅是普通 audit），必须额外满足主张级颗粒度，禁止“总评正确但比输入更难定位”：

必填	说明
`inputClaims`	外部输入主张列表（可编号）
`ClaimVerificationMatrix`	主张 → 项目证据 → verificationStatus → disposition（采纳/部分采纳/拒绝）
`projectEvidence`	repo path / 命令 / 运行结果，不得只复述外部原文
`unverifiedBoundaries`	未验证/UNVERIFIED 边界与推断边界
`detailReportLink`	用户可打开的详细报告链接（最终回复不得只有口头总评）
`EscapeAbsorptionQueue`	外部 finding → 本地证据 → disposition → 目标产物 / owner / status
`EvidenceFreshness`	对采纳、拒绝、已验证、可确认等 strong claim 记录 `StaleEvidenceLintDecisionV1.status/mode`；外部原文和历史报告只能是 hint

机器分类：scripts/lib/external-review-claim-verification.js（claim-ready / claim-thin / not-external-review）
证据新鲜度分类：scripts/lib/evidence-freshness-receipt.js（ClaimEvidenceIndexV1 / EvidenceFreshnessReceiptV1 / StaleEvidenceLintDecisionV1），生产入口 npm run test:evidence-freshness
负向：只写总评/建议、无矩阵、无 UNVERIFIED、无详细报告链接 → claim-thin，审查不通过
负向：把外部审查 finding 直接并入需求或技术方案，没有 EscapeAbsorptionQueue、本地证据、disposition 和 freshness decision → 审查不通过
非外部审阅场景：N/A + skipReason=not-external-review-recap

N/A 规则

纯信息性报告无行动项：RA-5 标 N/A
无关联外部文件：RA-6 标 N/A
非外部审阅复核：ExternalReviewClaimVerificationGate 标 N/A

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

intent.json1 KB

Frequently asked questions

What does the Audit Report AI skill do?

报告审查维度 RA-1~RA-6 — 分析报告/审查报告质量专属审查层

Why use Audit Report on TypingMind?

Because you install it once and use it with any model. Audit Report is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Audit Report in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devcodex-labs/devcodex/tree/main/content/skills/audit-report. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Audit Report?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Audit Report?

As many as you like. As long as a model supports skills, you can use Audit Report with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Audit Report AI skill free?

Yes. It is published on GitHub by devcodex-labs under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Backend Code Review

langgenius

OrganizationPopular

Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests,…

Frontend Code Review

Use only when the user explicitly requests a review or audit of frontend code under `web/` or `packages/dify-ui/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for…

Command Development

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create…

Discord E2e

Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Audit Report Skill

适用范围

维度总览（RA-1~RA-6）

核心检查维度

ExternalReviewClaimVerificationGate（PF-164 · 外部审阅复核）

N/A 规则

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now