dev-design — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited dev-design (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
templates/AGENTS.md加载 templates/FSD.md,生成 02-功能规格说明书 FSD.md:
加载 templates/数据模型设计.md,生成 03-数据模型设计.md:
加载 templates/开发设计说明书.md,生成 06-开发设计说明书.md:
关键纪律:
触发条件(满足任一即必做):
field-alignment-check.py 报错4 大类回测(详见 disciplines/stage-gate):
输出:08-设计回测报告.md
HARD GATE:回测不通过(❌)禁止进入阶段 9。
加载 templates/开发设计说明书.md §六,记录:
| 子流程 | 状态 | 签字 / 时间 |
|---|---|---|
| brainstorming 设计稿 | ⬜ | |
| spec 自检 | ⬜ | |
| writing-plans 完成 | ⬜ | |
| TDD RED 测试 | ⬜ | |
| 全部子任务 GREEN | ⬜ |
仅在用户明确进入实施扩展模式(走 /using-superpowers 之后)才需要填。每个子任务完成后,按 disciplines/stage-gate 的 5 问复盘写到 commit / PR。 此处汇总关键沉淀到 07-任务复盘汇总.md(可选)。
disciplines/no-field-guessing — 字段名必须查知识库disciplines/no-self-invent — 严禁自创字段/表名disciplines/sql-dialect-discipline — SQL 方言对齐 Target_DBdisciplines/stage-gate — 3 层门控 + 设计回测 + 任务复盘方法disciplines/doc-numbering — 文档编号 02/03/06/08AGENTS.md(项目根)02-功能规格说明书 FSD.md03-数据模型设计.md06-开发设计说明书.md08-设计回测报告.md07-任务复盘汇总.md(可选,实施扩展模式才需要)field-alignment-check.py 通过sql-dialect-check.py 通过/qa-audit~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.