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-s6-test-cases/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-s6-test-cases)<a href="https://agentmods.dev/skills/silenceinsect/aidocxworkflow/aidocx-s6-test-cases"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/aidocx-s6-test-cases/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-s6-test-cases"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/aidocx-s6-test-cases.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 | $0.00130 | $0.28111 |
| Opus 5 | $0.00065 | $0.14056 |
| Sonnet 5 | $0.00026 | $0.05622 |
| Haiku 4.5 | $0.00013 | $0.02811 |
Grade A, and why
aidocx-s6-test-cases 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 — 1,711 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔴 命名继承一致性铁律（字段溯源版 — 最高优先级，违反直接 L1 打回）
NAME-FIELD-001：本节是命名追溯性修复的核心约束。S6 TC 必须从 S5 TP 继承正式 OBJ/FP 名称字段，且必须有显式字段，继承链路才算完整。 校验精度：字段溯源版（字段精准匹配——obj_name == 源 TP）+ LLM 自由文本溯源（test_scenario 不带锚点）
v28 修订注：约束①
fp_name必须 100% 等于 S2fp_desc（v26 §判定 ①）已于 Round 15 F-F 删除 fp_name 字段（约束已变空对象，本节规则 1/3 已同步注明）；约束④s5_ref必填单值（v26 §判定 ④）放宽为s5_ref单值 或tp_references[]数组二选一；约束②steps[]结构化数组强制（v26 §判定 ②）放宽为允许字符串数组；约束③test_method[]字符串数组强制（v26 §判定 ③）放宽为允许单字符串 或 字符串数组。约束⑤preconditions[]维持。详见governance/design_iter/plans/v28/GOAL.md。
一、核心基准规则
规则 1：TC 必须包含显式字段 obj_name 和 feature_point_ref
每条 TC 必须有以下两个字段，从源 TP 原样继承：
obj_name：从源 TP.obj_name 取值（100% 原样继承，最终来源 = S2 obj_name）feature_point_ref：从源 TP.feature_point_ref 取值（100% 原样继承，最终来源 = S2 FP ID）fp_name字段已 Round 15 F-F 删除（feature_point_ref已结构化足以反查 FP）——历史字段，仅作 v3.01 legacy 兼容
规则 2：test_scenario 不带锚点（纯场景文本）
格式：纯场景一句话描述
- 禁止 test_scenario 以
【OBJ - FP】锚点开头 - 锚点仅存 JSON 字段（obj_name / feature_point_ref），不重复进文本
- TC.obj_name 必须 == TP.obj_name（继承性）
规则 3：名称必须继承，不得改写
- TC.obj_name 必须从源 TP.obj_name 原样继承（最终来源 = S2 obj_name，100% 逐字相等）
- TC.feature_point_ref 必须从源 TP.feature_point_ref 原样继承（结构化 FP ID，反查 FP 元数据）
- 禁止在生成过程中"优化"、简化、意译
- 禁止从 TP 到 TC 的过程中丢失正式名称字段
fp_name字段已 Round 15 F-F 删除（不再要求继承）——历史字段治理
二、字段格式模板
test_scenario 字段
{纯场景一句话描述}（不带锚点）
示例：
- 源 TP.obj_name = "商城首页道具列表"，TP.fp_name = "首页销量排序展示"
- 生成 TC：test_scenario = "玩家进入商城首页，验证道具列表按销量降序排列"
三、自检流程（输出前必须执行）
生成完所有 TC 后，逐条检查：
| 检查项 | 通过标准 |
|---|---|
| obj_name 字段存在 | TC.obj_name == 源 TP.obj_name（继承性，最终 == S2 obj_name） |
| feature_point_ref 字段存在 | TC.feature_point_ref == 源 TP.feature_point_ref（继承性，反查 FP） |
| assertion 字段 ≥ 1（Round 15 F-E 新增） | TC.assertion 数组长度 ≥ 1，每项含 assertion_type 必填字段 |
| test_scenario 无锚点 | 开头不是【xxx - xxx】格式 |
| OBJ 字段正确 | TC.obj_name = S2 obj_name（逐字相等，继承自 TP） |
| FP 字段正确 | TC.feature_point_ref = TP.feature_point_ref（继承自 TP，结构化 FP ID） |
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 · 1,711 lines · 130 tokens per session scan A e9bb86281253
aidocx-s6-test-cases is a skill published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 28,111 once invoked, about $0.0006 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.