Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add BlueprintOS/analysis-to-delivery --skill qa-auditgit clone --depth 1 https://github.com/BlueprintOS/analysis-to-deliveryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/blueprintos/analysis-to-delivery/qa-audit)<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/qa-audit"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/qa-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/qa-audit"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/qa-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.01276 |
| Opus 5 | $0.00034 | $0.00638 |
| Sonnet 5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
qa-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA-Audit — 文档质量审计
Contract
- 输入: 已完成的 01-09 编号文档,项目配置文件,知识库 / 合规 / 技术栈指针
- 输出:
09-QA审计报告.md - 门控:
python3 scripts/full-qa-audit.py <project>返回 P0=0;整改循环闭环;用户签字 - Required rules:
stage-gate,no-field-guessing,no-self-invent,sql-dialect,doc-numbering,goal-boundary - Required paths:
knowledge-path,tech-stack-path,compliance-path,doc-naming-path - 下一步:
/handoff
适用场景
- dev-design 全部产出已签字
- 设计回测已通过
- 进入代码交接前的最后一道闸
流程步骤
1. 跑全量审计
python3 <SKILL_ROOT>/analysis-to-delivery/scripts/full-qa-audit.py <项目目录>
2. 审计维度(6 大类)
| # | 维度 | 工具 |
|---|---|---|
| 1 | 文档格式(frontmatter / H1 / 章节 / 链接 / 占位符) | doc-validate.py |
| 2 | 文档编号冲突 | full-qa-audit.py |
| 3 | 核心文档完整性(01/05/07 必备) | full-qa-audit.py |
| 4 | SQL 方言一致性 | sql-dialect-check.py |
| 5 | 字段映射一致性 | field-alignment-check.py |
| 6 | 删除/修改的精度 | 人工 + field-alignment-check.py |
3. 分级处理
| 等级 | 含义 | 处理方式 |
|---|---|---|
| P0 | 致命:导致交接后开发返工 | 必须修复 |
| P1 | 重要:影响开发效率 | 建议修复 |
| P2 | 提示:锦上添花 | 可选 |
4. 修复迭代
- 首次失败 → 读错误输出 → 定位问题文件/行号 → 修复 → 重新跑
- 二次失败 → 扩大搜索范围,检查关联文件 → 修复 → 重新跑
- 三次失败 → 停止自动修复,输出完整错误报告,等用户决策
5. 写审计报告
输出 09-QA审计报告.md:
# QA 审计报告:{项目名}
> 审计时间:{日期}
> 审计人:{name}
## 审计概览
- 文档总数:{N}
- P0:{N} ❌ 必须修复
- P1:{N} ⚠️ 建议修复
- P2:{N} 💡 可选
## 6 大类审计结果
### 1. 文档格式
✅/⚠️/❌
### 2. 文档编号
✅/⚠️/❌
### 3. 核心文档完整性
✅/⚠️/❌
### 4. SQL 方言
✅/⚠️/❌
### 5. 字段映射
✅/⚠️/❌
### 6. 删除/修改精度
✅/⚠️/❌
## P0 问题清单
| 文件 | 行号 | 问题 | 修复方案 |
|---|---|---|---|
| | | | |
## 修复完成确认
- [ ] P0 全部修复
- [ ] 重新跑审计,P0=0
- [ ] 用户签字进入 `/handoff`
调用的 rule
rules/stage-gate— 阶段 8 门控rules/sql-dialect— SQL 方言rules/doc-numbering— 文档编号
结束条件
- 6 大类审计全部跑过
- P0=0
- 审计报告签字(用户 + 接收方)
反模式
- ❌ P0 不修复就交付 — P0 必须=0 才能签字进入交接
- ❌ 只查 1 类(只查文档/只查代码) — 必须 6 大类(文档/流程/字段/合规/代码/性能)全跑
- ❌ 审计结果"看起来 OK" — 必须有证据(具体文件 + 行号 + 引用规范)
- ❌ 不分 P0/P1/P2 — 必须按严重程度分级,否则后续修复无法排期
- ❌ 跳过代码 vs 设计对比 — 必须检查"代码实现是否偏离设计"
- ❌ 审计报告无签字栏 — 必须含用户 + 接收方两栏(参考 rules/stage-gate.md 第 8 门)
- 进入
/handoff
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 131 lines · 67 tokens per session scan A 0c613156c86c
qa-audit is a skill published in the GitHub repository BlueprintOS/analysis-to-delivery (26 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,276 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pdf-text-replace
Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.
suede-product-marketing
Suede-owned product-marketing context discipline. Use when a project needs a shared record of product, audience, ICP, positioning, objections, customer language, proof, and goals, or when that record needs updating. NOT FOR: writing a campaign (use suede-campaign-in-a-box), conducting new customer interviews (use…
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
design-export-repair
Fixes broken decks/PDFs exported from Claude's "Design" feature (or similar AI deck generators) — cut-off or clipped text, wrong/substituted fonts, and corrupted .pptx package structure that shows up only once you export to PDF, not while looking at it in the app. Use this skill whenever the user uploads a zip, .pptx…
financial-document-parser
Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.
csv-excel-merger
Merge multiple CSV/Excel files with intelligent column matching, data deduplication, and conflict resolution. Handles different schemas, formats, and combines data sources. Use when users need to merge spreadsheets, combine data exports, or consolidate multiple files into one.