audit-issues

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/audit-issues

Audit the current working directory for the Issue Detection dimension.

Paths in this file are relative to this skill's own directory (the folder that contains this SKILL.md), not to the repository being audited. Run all detection commands in the repository being audited (the current working directory).

对当前工作目录进行“问题检测”维度的审计。

本文件中的路径相对于该 skill 自身的目录（包含此 SKILL.md 的文件夹），而非被审计的仓库。所有检测命令都在被审计的仓库（当前工作目录）中运行。

Inputs

输入

Optional
```
discovery_context
```
(JSON) injected by the orchestrator.
Optional output path (from the orchestrator): write the JSON there instead of printing it.
Flags:
```
--json
```
(emit JSON only, no markdown summary).

可选的
```
discovery_context
```
（JSON），由 orchestrator 注入。
可选的输出路径（来自 orchestrator）：将 JSON 写入该路径，而不是打印输出。
标志：
```
--json
```
（仅输出 JSON，不输出 markdown 摘要）。

Steps

步骤

Discovery: if
```
discovery_context
```
was NOT injected, follow
```
references/discovery.md
```
and build it. If injected, use it as-is (do not re-run discovery).

Filter: read

references/detection/04-issues.md

. Drop any checklist item whose

applies_to

shares no archetype with

discovery_context.archetypes

→ emit it with

status: "skipped"

Detect (two-stage, spec §5a.2 / §9a.4): a. For each applicable item, run its
```
signals
```
(ripgrep) to get candidate
```
file:line
```
. Prefer external-tool output if available. Do NOT read the whole repo. b. Read only candidate snippets; apply each item's
```
confirm
```
rule. Assign severity honoring any severity floors. Consult
```
references/detection/examples/04-issues.md
```
only when a candidate is ambiguous.
Emit: produce one
```
AuditResult
```
JSON object conforming to
```
references/schema.json
```
with
```
audit: "issues"
```
,
```
iso_characteristic: "Maintainability"
```
, the checklist (with statuses), and findings. Leave
```
score
```
as
```
0
```
— the engine computes it.
- If an output path was given: write ONLY the JSON object to it (UTF-8), then reply with one line:
```
<audit key>: <n> findings -> <path>
```
  .
- With
```
--json
```
  or as a subagent without an output path: output ONLY the JSON.
- Standalone: also print a short markdown summary (counts + top findings).

When invoked as a subagent, return only valid JSON — or, when an output path was given, only the one-line confirmation.

发现（Discovery）：如果未注入
```
discovery_context
```
，则遵循
```
references/discovery.md
```
并构建它。若已注入，则原样使用（不要重新运行发现流程）。
过滤（Filter）：读取
```
references/detection/04-issues.md
```
。丢弃任何
```
applies_to
```
与
```
discovery_context.archetypes
```
没有共同原型的检查项 → 以
```
status: "skipped"
```
输出。
检测（两阶段，spec §5a.2 / §9a.4）： a. 对每个适用项，运行其
```
signals
```
（ripgrep）以获得候选
```
file:line
```
。优先使用外部工具输出（如可用）。不要读取整个仓库。 b. 仅读取候选代码片段；应用每个项的
```
confirm
```
规则。分配严重级别时需遵守严重级别下限。仅在候选存在歧义时查阅
```
references/detection/examples/04-issues.md
```
。
输出（Emit）：生成一个符合
```
references/schema.json
```
的
```
AuditResult
```
JSON 对象，其中包含
```
audit: "issues"
```
、
```
iso_characteristic: "Maintainability"
```
、检查清单（带状态）以及 findings。将
```
score
```
留为
```
0
```
—— 由引擎计算。
- 如果给出了输出路径：仅将 JSON 对象写入该文件（UTF-8），然后回复一行：
```
<audit key>: <n> findings -> <path>
```
  。
- 使用
```
--json
```
  或作为 subagent 且无输出路径时：仅输出 JSON。
- 独立运行（standalone）：同时打印一份简短的 markdown 摘要（计数 + 最重要的 findings）。

作为 subagent 被调用时，仅返回有效的 JSON —— 或者，当给出了输出路径时，仅返回那一行确认信息。