Borrowing it
Nothing to install: this file belongs to SilenceInsect/AIDocxWorkFlow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SilenceInsect/AIDocxWorkFlow/main/.cursor/skills/aidocx-s7-review/SKILL.mdgit clone --depth 1 https://github.com/SilenceInsect/AIDocxWorkFlowWrote 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/silenceinsect/aidocxworkflow/aidocx-s7-review)<a href="https://agentmods.dev/skills/silenceinsect/aidocxworkflow/aidocx-s7-review"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/aidocx-s7-review/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/silenceinsect/aidocxworkflow/aidocx-s7-review"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/aidocx-s7-review.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 | $0.00150 | $0.08935 |
| Opus 5 | $0.00075 | $0.04467 |
| Sonnet 5 | $0.00030 | $0.01787 |
| Haiku 4.5 | $0.00015 | $0.00894 |
Grade A, and why
aidocx-s7-review 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 10d 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 — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow S7 — 用例审查
独立阶段:可单独调用。上游材料(S6 test_cases.json + coverage/omission 账本)审查合格后开始,失败写失败报告。
⚠️ 模块定义见
.cursor/MODULES.md(项目级唯一真相源)。 本文件不重写模块表。所有"模块"字段取值集合见MODULES.md§1 总表,{Module}占位符 实际取值集合 = 8 模块之一(CONFIG / UI / BIZ / UTIL / LINK / LOG / SPECIAL / HINT)。HINT vs UI 边界判定(误标高发区)见
MODULES.md§4.11.2。
阶段入口
触发:/aidocx-s7-review 或粘贴 S6 test_cases.json
前置材料:S6 test_cases.json + S5 test_points.json + S4 business_flow.md + coverage_ledger.json + omission_ledger.json。详见 §1.4。
材料缺失时:生成失败报告,停止 S7。
§1.4 必读材料与违规认定
⚠️ 违反本节禁令 → 产出不合格,必须补读后重新生成。
违规认定(满足任一 → 产出不合格)
- ❌ 未读取本节材料,直接凭印象生成
- ❌ 跳过标注"强制"的材料,用其他来源替代
- ❌ 产出的 module / s4_reference 与材料内容明显不符
- ❌ 用"业务常识"替代必须读取的材料
必读材料清单
审查前,必须先 Read 以下材料。
| # | 材料 | 路径 | 必读原因 |
|---|---|---|---|
| ① | 8 模块总表 | .cursor/MODULES.md(§1 总表) |
覆盖率按模块统计;审查员 B 的 module_coverage 以 8 模块为分母 |
| ② | 模块边界区分 | .cursor/MODULES.md(§4 各模块 O_boundary.md) |
判断 TP 模块归属是否正确;HINT vs UI 是最高误标区 |
| ③ | S6 test_cases(强制) | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/test_cases.json |
审查对象;未读取 → 无法审查 |
| ④ | S5 test_points(强制) | workflow_assets/<req_name>/<version>/「S5 测试点生成」/test_points.json |
S4 风险点覆盖率对比基准 |
| ⑤ | S4 business_flow(强制) | workflow_assets/<req_name>/<version>/「S4 流程图导出」/business_flow.md |
S7 覆盖率指标 = S4 风险点全量覆盖(100%)是硬约束 |
§1.6 强制写文件(不可跳过,禁止询问)
S7 审查的产出是文件,不是对话窗口内的文字。
执行顺序(强制):
步骤 1:调用 auto_reviewer.snapshot() 获取事实数字(不可跳过)
↓
步骤 2:LLM 读取 snap 输出,做语义审查
↓
步骤 3:调用 save_review_report() 写入文件(强制,不可跳过)
步骤 1:调用 auto_reviewer(必须先执行)
from ai_workflow.auto_reviewer import snapshot, save_review_report
from pathlib import Path
req_dir = Path("workflow_assets/<req_name>")
snap = snapshot(
test_cases_path=req_dir / "<version>/「S6 测试用例生成」/test_cases.json",
backlog_path=req_dir / "<version>/「S2 需求拆解」/backlog.json",
test_points_path=req_dir / "<version>/「S5 测试点生成」/test_points.json",
)
# 输出事实数字供 LLM 使用(禁止跳过此步骤)
print(snap.ai_input_summary)
print(f"[S7] TC 填写率: {snap.structure.fill_rate:.1%}")
print(f"[S7] S5 TP 填写率: {snap.s5_structure.fill_rate:.1%}" if snap.s5_structure else "")
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.
- 10d ago First seen · 666 lines · 150 tokens per session scan A 81934525d8cf
aidocx-s7-review is a skill published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 8,935 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.