cs-audit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

cs-audit

cs-issue

等你报 bug，

cs-refactor

等你指优化点，

cs-explore

等你提问题——但"我也不知道哪有问题，你先扫一遍看看"这个诉求没人接。

cs-audit

补上这块：在用户限定的范围内主动扫描，产出一份按严重度 × 性质交叉分类的发现清单。

本技能只发现、不定修。修是

cs-issue

cs-refactor

的事。

cs-issue

waits for you to report bugs,

cs-refactor

waits for you to point out optimization points,

cs-explore

waits for you to raise questions—but the request "I don't know where the problems are, just scan through and check" had no one to handle it.

cs-audit

fills this gap: proactively scan within the scope defined by the user and generate a list of findings cross-classified by severity × nature.

This skill only identifies issues, not fixes them. Fixing is the responsibility of

cs-issue

cs-refactor

文件放哪儿

Where to Place Files

codestable/audits/{YYYY-MM-DD}-{slug}/
├── index.md           # 速览：范围、总评、发现清单交叉矩阵
├── finding-01.md
├── finding-02.md
└── ...

日期取审计当天。slug 短到一眼看出审计目标（

auth-module

、

order-flow

、

payment-security

）。

所有 audit 文档带 YAML frontmatter（

doc_type

分别为

audit-index

和

audit-finding

）便于

search-yaml.py

检索。

codestable/audits/{YYYY-MM-DD}-{slug}/
├── index.md           # Overview: scope, overall assessment, cross-matrix of findings list
├── finding-01.md
├── finding-02.md
└── ...

The date is the day of the audit. The slug should be short enough to identify the audit target at a glance (e.g.,

auth-module

order-flow

payment-security

All audit documents include YAML frontmatter (with

doc_type

set to

audit-index

and

audit-finding

respectively) to facilitate retrieval via

search-yaml.py

维度矩阵（交叉分类）

Dimension Matrix (Cross Classification)

每个发现打两个标签：

性质：

bug

security

performance

maintainability

arch-drift

严重度：

P0

（必须修）|

P1

（应该修）|

P2

（可以修）

交叉示例：

```
security
```
×
```
P0
```
：SQL 注入、明文存密码
```
bug
```
×
```
P1
```
：特定边界条件下空指针，实际触发概率低
```
performance
```
×
```
P2
```
：循环内多余的对象分配，热点路径才需要改

另外每个发现带 置信度（

high

medium

low

）和建议动作（

cs-issue

cs-refactor

）。

完整模板见

reference.md

。

Each finding is tagged with two labels:

Nature:

bug

security

performance

maintainability

arch-drift

Severity:

P0

(Must fix) |

P1

(Should fix) |

P2

(Could fix)

Cross examples:

```
security
```
×
```
P0
```
: SQL injection, storing passwords in plaintext
```
bug
```
×
```
P1
```
: Null pointer under specific boundary conditions, with low actual trigger probability
```
performance
```
×
```
P2
```
: Redundant object allocation in loops, only needs modification in hot paths

Additionally, each finding includes confidence level (

high

medium

low

) and suggested action (

cs-issue

cs-refactor

See

reference.md

for the complete template.

工作流

Workflow

Phase 1：范围收敛

Phase 1: Scope Convergence

审计不能全仓库盲扫——成本高、噪音大。先帮用户把范围收窄到可执行。

问用户三样（有一样就能起步）：

关键词："跟 auth / payment / upload 相关的"
模块 / 目录："
```
src/services/
```
下面"
一段话描述："最近用户反馈订单页慢，帮我扫一下订单相关代码"

用户描述已清楚直接进 Phase 2。用户说"整个项目都扫" → 推回去——建议先扫最常改的模块或最近出过问题的区域。

收敛后给用户确认："扫
src/services/order/
和
src/api/order.ts
，约 12 个文件，看安全 / 性能 / bug 隐患三个维度。范围 OK 吗？"

Blind scanning of the entire repository for audits is not allowed—it's costly and generates excessive noise. First, help the user narrow down the scope to an executable range.

Ask the user for one of the three (any one is sufficient to start):

Keywords: "Related to auth / payment / upload"
Module / Directory: "Under
```
src/services/
```
"
Paragraph description: "Recently users reported that the order page is slow, help me scan the order-related code"

If the user's description is clear, proceed directly to Phase 2. If the user says "scan the entire project" → push back—suggest scanning the most frequently modified modules or areas that have had issues recently.

After convergence, confirm with the user: "Scanning
src/services/order/
and
src/api/order.ts
, approximately 12 files, covering three dimensions: security / performance / bug risks. Is the scope OK?"

Phase 2：扫描

Phase 2: Scanning

按用户圈定的维度逐维扫描（用户没指定就全扫 5 维）：

bug 隐患：空值路径、边界条件缺失、竞态条件、错误处理吞异常、类型断言无保护
安全：注入风险、敏感数据暴露、权限校验缺失、不安全依赖
性能：N+1 查询、重复计算、无缓存热点路径、内存泄漏、无分页全量加载
可维护性：超长函数（> 80 行）、圈复杂度 > 15、重复逻辑块、神秘常量、循环依赖
架构偏离：代码与
```
codestable/architecture/
```
记录不一致、分层泄漏、跨模块隐式耦合

扫描时用 Glob / Grep / Read 真实读代码。每条发现必须记录

文件:行号

+ 具体代码片段。

上限：每种维度最多报 5 条。不是凑数——够了就停，不够也不硬凑。

置信度口径：

```
high
```
：代码路径可确认触发，影响明确
```
medium
```
：静态分析能定位问题，但触发条件不确定
```
low
```
：线索可疑，需要进一步确认但值得标记

Scan dimension by dimension according to the scope defined by the user (scan all 5 dimensions if not specified):

Bug risks: Null value paths, missing boundary conditions, race conditions, swallowed exceptions in error handling, unprotected type assertions
Security: Injection risks, exposure of sensitive data, missing permission checks, insecure dependencies
Performance: N+1 queries, repeated calculations, hot paths without caching, memory leaks, full loading without pagination
Maintainability: Extra-long functions (>80 lines), cyclomatic complexity >15, duplicate logic blocks, magic constants, circular dependencies
Architecture drift: Inconsistencies between code and records in
```
codestable/architecture/
```
, layer leakage, implicit cross-module coupling

Use Glob / Grep / Read to actually read the code during scanning. Each finding must record

file:line number

+ specific code snippet.

Upper Limit: Report a maximum of 5 findings per dimension. Don't fill in numbers—stop when enough are found, don't force it if not enough.

Confidence Level Definition:

```
high
```
: The code path can be confirmed to trigger, with clear impact
```
medium
```
: The issue can be located via static analysis, but the trigger conditions are uncertain
```
low
```
: Suspicious clues, need further confirmation but worth marking

Phase 3：定级 + 产出

Phase 3: Rating + Output

每个发现打性质 + 严重度 + 置信度 + 建议动作
写
```
index.md
```
：范围、总评、发现清单表格（交叉分类）
逐条写
```
finding-NN.md
```

先写 index 再写 finding——这个顺序让 AI 先做整体判断再展开细节，避免陷入单条发现迷失全局。

Tag each finding with nature + severity + confidence level + suggested action
Write
```
index.md
```
: scope, overall assessment, findings list table (cross-classified)
Write
```
finding-NN.md
```
one by one

Write index first, then findings—this order allows the AI to make an overall judgment first before expanding details, avoiding getting lost in individual findings.

Phase 4：建议下一步

Phase 4: Suggest Next Steps

index.md 末尾给优先级建议：

"P0 的 3 条建议立刻开 issue 修"
"P1 的 5 条可以排下个迭代"
"P2 的 4 条有空再看"

用户选哪条 → 路由到

cs-issue

或

cs-refactor

。

cs-audit

自己不修。

At the end of index.md, provide priority suggestions:

"It is recommended to immediately create issues for the 3 P0 findings"
"The 5 P1 findings can be scheduled for the next iteration"
"The 4 P2 findings can be reviewed when there is time"

Whichever option the user selects → route to

cs-issue

cs-refactor

cs-audit

does not fix issues itself.

与相邻技能的边界

Boundaries with Adjacent Skills

技能	触发	cs-audit 怎么对待
`cs-issue`	用户报已知 bug	audit 发现 bug 后建议开 `cs-issue`
`cs-refactor`	用户指已知优化点	audit 发现可优化点后建议开 `cs-refactor`
`cs-explore`	围绕一个问题查代码	audit 是批量扫多个维度，不等同于 explore
`cs-arch`	维护架构文档	cs-arch 维护文档，cs-audit 检查代码是否偏离文档
`cs-security-review`	安全审查	audit 的安全维度是轻量扫描，深度安全审查走专项

Skill	Trigger	How cs-audit Handles It
`cs-issue`	User reports a known bug	After identifying a bug during audit, suggest creating a `cs-issue`
`cs-refactor`	User points out a known optimization point	After identifying an optimization point during audit, suggest creating a `cs-refactor`
`cs-explore`	Investigate code around a specific question	Audit involves batch scanning across multiple dimensions, which is not equivalent to explore
`cs-arch`	Maintain architecture documents	cs-arch maintains documents, while cs-audit checks if code deviates from documents
`cs-security-review`	Security review	The security dimension of audit is lightweight scanning; in-depth security review requires a special process

守护规则

Guardrails

不盲扫全仓库——Phase 1 必须收敛范围，没范围不动手
每条发现必有证据——file:line + 代码片段 + 为什么构成问题。不准出现"感觉不好"、"可能有问题"类无证据发现
置信度必标——不准所有发现都标
```
high
```
每种维度上限 5 条——逼 AI 挑最值得报的，不是 dump 所有发现
只发现不定修——cs-audit 不出代码改动。出现"顺便修了"就算越界
架构偏离引用当前文档——不准凭记忆判断架构应该长什么样，必须读
```
codestable/architecture/
```
对照
旧审计标注过期——同名模块新审计覆盖旧审计时，旧 index 标
```
status: superseded
```
+
```
superseded-by: {新目录}
```

No blind scanning of the entire repository—Phase 1 must converge the scope; do not start without a scope
Every finding must have evidence—file:line + code snippet + why it constitutes a problem. No findings like "feels wrong" or "might have issues" without evidence are allowed
Confidence level must be marked—do not mark all findings as
```
high
```
Maximum 5 findings per dimension—force the AI to select the most worthy findings, not dump all findings
Only identify, do not fix—cs-audit does not produce code changes. It is considered out of bounds if "fix it by the way" appears
Architecture drift references current documents—do not judge what the architecture should look like based on memory; must read and compare with
```
codestable/architecture/
```
Mark old audits as expired—when a new audit for the same module covers an old one, mark the old index with
```
status: superseded
```
+
```
superseded-by: {new directory}
```

cs-audit

Original

Translation

cs-audit

cs-audit

文件放哪儿

Where to Place Files

维度矩阵（交叉分类）

Dimension Matrix (Cross Classification)

工作流

Workflow

Phase 1：范围收敛

Phase 1: Scope Convergence

Phase 2：扫描

Phase 2: Scanning

Phase 3：定级 + 产出

Phase 3: Rating + Output

Phase 4：建议下一步

Phase 4: Suggest Next Steps

与相邻技能的边界

Boundaries with Adjacent Skills

守护规则

Guardrails

退出条件

Exit Criteria

相关文档

Related Documents