Best fit
- 追踪每个面向用户的按钮/触点的完整状态变化序列,以发现功能单独工作但相互抵消、产生错误最终状态或使UI处于不一致状态的错误。适用于:系统调试未发现错误但用户报告按钮失效,或在任何涉及共享状态存储的重大重构之后。
affaan-m/ECC
追踪每个面向用户的按钮/触点的完整状态变化序列,以发现功能单独工作但相互抵消、产生错误最终状态或使UI处于不一致状态的错误。适用于:系统调试未发现错误但用户报告按钮失效,或在任何涉及共享状态存储的重大重构之后。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/click-path-audit"Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
According to the pinned SKILL.md from affaan-m/ECC: 发现静态代码审查遗漏的缺陷:状态交互副作用、顺序调用间的竞态条件,以及相互静默撤销的处理程序。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/click-path-audit"Best fit
Bring this context
Expected outputs
Key source sections
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
函数是否存在?(缺少连接) 是否崩溃?(运行时错误) 是否返回正确类型?(数据流)
Review the “工作原理” section in the pinned source before continuing.
在审计任何触点之前,构建每个状态存储操作的副作用映射:
在审计任何触点之前,构建每个状态存储操作的副作用映射:
Review the “步骤 2:审计每个触点” section in the pinned source before continuing.
SkillSignal prompt templates
These prompts were written by SkillSignal from the source structure; they are not upstream text.
Task-start prompt
Confirm source fit, inputs, and outputs before acting.
Use click-path-audit to help me with: [specific task]. Context: [files, data, or background]. Constraints: [environment, scope, and prohibited actions]. Before acting, check the pinned SKILL.md and explain which sections apply, what inputs are still missing, and what you will deliver.
Source-guided execution
Make the Agent explicitly follow the key extracted sections.
Apply the pinned click-path-audit source to [task]. Pay particular attention to these source sections: “解决的问题”, “工作原理”, “执行步骤”, “步骤 1:映射状态存储”, “步骤 2:审计每个触点”. Preserve the important decision at each step. Mark facts not covered by the source as “needs confirmation” instead of inventing them. Then verify the result against my acceptance criteria: [criteria].
Result-review prompt
Check omissions, permissions, and source drift before delivery.
Review the current click-path-audit result: (1) does it satisfy the original task; (2) were any applicable steps or limits in the pinned SKILL.md missed; (3) did it perform any unauthorized file, command, network, or data action; and (4) which conclusions remain unverified? List issues first, then fix only what the source or user authorization supports.
Output checklist
The task matches the purpose documented in the SKILL.md.
The source section “解决的问题” has been checked.
The source section “工作原理” has been checked.
The source section “执行步骤” has been checked.
The source section “步骤 1:映射状态存储” has been checked.
Inputs, constraints, and acceptance criteria are explicit.
Unverified facts, compatibility, and outcome claims are clearly marked.
Any file, command, network, or data action has been reviewed.
Choose a different workflow
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailユーザー向けボタン/タッチポイントを完全な状態変更シーケンスを通して追跡し、機能が個別に機能するが互いにキャンセルされたり、間違った最終状態を生成したり、UIを矛盾した状態にしたままにするバグを見つけます。次の場合に使用します:体系的なデバッグがバグを見つけたが、ユーザーは壊れたボタンを報告する場合、または共有状態ストアに触れる主要なリファクター後。
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
A separate implementation from coreyhaines31/marketingskills; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
发现静态代码审查遗漏的缺陷:状态交互副作用、顺序调用间的竞态条件,以及相互静默撤销的处理程序。
The catalog detected this source-specific install command: npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/click-path-audit". Inspect the command and pinned source before running it.
No dedicated Agent platform is declared in the pinned source record.
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Compare before choosing
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.
ユーザー向けボタン/タッチポイントを完全な状態変更シーケンスを通して追跡し、機能が個別に機能するが互いにキャンセルされたり、間違った最終状態を生成したり、UIを矛盾した状態にしたままにするバグを見つけます。次の場合に使用します:体系的なデバッグがバグを見つけたが、ユーザーは壊れたボタンを報告する場合、または共有状態ストアに触れる主要なリファクター後。
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o
Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.
发现静态代码审查遗漏的缺陷:状态交互副作用、顺序调用间的竞态条件,以及相互静默撤销的处理程序。
传统调试检查:
但未检查:
真实案例:一个"新邮件"按钮依次调用了 setComposeMode(true) 和 selectThread(null)。两者单独工作正常。但 selectThread 有一个副作用重置了 composeMode: false。按钮毫无反应。系统化调试发现了 54 个缺陷——这个被遗漏了。
针对目标区域内的每个交互触点:
1. 识别处理函数(onClick、onSubmit、onChange 等)
2. 按顺序追踪处理函数中的每个函数调用
3. 对于每个函数调用:
a. 它读取了哪些状态?
b. 它写入了哪些状态?
c. 它是否对共享状态产生了副作用?
d. 它是否作为副作用重置/清除了任何状态?
4. 检查:后续调用是否会撤销前面调用的状态变更?
5. 检查:最终状态是否符合用户对按钮标签的预期?
6. 检查:是否存在竞态条件(异步调用以错误顺序解析)?
在审计任何触点之前,构建每个状态存储操作的副作用映射:
对于作用域内的每个 Zustand 存储 / React 上下文:
对于每个操作/设置器:
- 它设置了哪些字段?
- 它是否作为副作用重置了其他字段?
- 文档:actionName → {sets: [...], resets: [...]}
这是关键参考。"新邮件"缺陷在不知道 selectThread 重置了 composeMode 的情况下是不可见的。
输出格式:
STORE: emailStore
setComposeMode(bool) → 设置: {composeMode}
selectThread(thread|null) → 设置: {selectedThread, selectedThreadId, messages, drafts, selectedDraft, summary} 重置: {composeMode: false, composeData: null, redraftOpen: false}
setDraftGenerating(bool) → 设置: {draftGenerating}
...
危险的重置(清除不属于自身状态的操作):
selectThread → 重置 composeMode(由 setComposeMode 拥有)
reset → 重置所有内容
针对目标区域内的每个按钮/开关/表单提交:
TOUCHPOINT: [按钮标签] 在 [组件:行]
HANDLER: onClick → {
调用 1: functionA() → 设置 {X: true}
调用 2: functionB() → 设置 {Y: null} 重置 {X: false} ← 冲突
}
EXPECTED: 用户看到 [按钮标签所承诺的描述]
ACTUAL: X 为 false,因为 functionB 重置了它
VERDICT: BUG — [描述]
检查以下每种缺陷模式:
handler() {
setState_A(true) // 设置 X = true
setState_B(null) // 副作用:重置 X = false
}
// 结果:X 为 false。第一次调用毫无意义。
handler() {
fetchA().then(() => setState({ loading: false }))
fetchB().then(() => setState({ loading: true }))
}
// 结果:最终的 loading 状态取决于哪个先完成
const [count, setCount] = useState(0)
const handler = useCallback(() => {
setCount(count + 1) // 捕获了过时的 count
setCount(count + 1) // 同样的过时 count — 只增加 1,而不是 2
}, [count])
// 按钮显示"保存",但处理程序仅验证,从未实际保存
// 按钮显示"删除",但处理程序设置了一个标志而未调用API
// 按钮显示"发送",但API端点已被移除/损坏
handler() {
if (someState) { // 此时 someState 始终为 false
doTheActualThing() // 永远不会执行到
}
}
// Button 设置 stateX = true
// useEffect 监听 stateX 并将其重置为 false
// 用户看不到任何变化
针对发现的每个缺陷:
CLICK-PATH-NNN: [严重性: 严重/高/中/低]
触点: [按钮标签] 位于 [文件:行号]
模式: [顺序撤销 / 异步竞态 / 过期闭包 / 缺失过渡 / 死路径 / useEffect 干扰]
处理函数: [函数名或内联]
追踪:
1. [调用] → 设置 {字段: 值}
2. [调用] → 重置 {字段: 值} ← 冲突
预期: [用户期望的结果]
实际: [实际发生的结果]
修复: [具体修复方案]
此审计成本较高。请适当限定范围:
Agent 1:映射所有状态存储(步骤 1)——这是所有其他代理的共享上下文
Agent 2:仪表盘(任务、笔记、日志、想法)
Agent 3:聊天(DanteChatColumn、JustChatPage)
Agent 4:邮件(ThreadList、DraftArea、EmailsPage)
Agent 5:项目(ProjectsPage、ProjectOverviewTab、NewProjectWizard)
Agent 6:CRM(所有子标签页)
Agent 7:个人资料、设置、保险库、通知
Agent 8:管理套件(所有页面)
代理 1 必须首先完成。其输出是所有其他代理的输入。
/superpowers:systematic-debugging(发现其他 54 种缺陷类型)之后运行/superpowers:verification-before-completion(验证修复是否有效)之前运行/superpowers:test-driven-development——此处发现的每个缺陷都应添加测试ThreadList.tsx "新邮件"按钮:
onClick={() => {
useEmailStore.getState().setComposeMode(true) // ✓ 设置 composeMode = true
useEmailStore.getState().selectThread(null) // ✗ 重置 composeMode = false
}}
存储定义:
selectThread: (thread) => set({
selectedThread: thread,
selectedThreadId: thread?.id ?? null,
messages: [],
drafts: [],
selectedDraft: null,
summary: null,
composeMode: false, // ← 这个静默重置导致按钮失效
composeData: null,
redraftOpen: false,
})
系统化调试遗漏了它,因为:
点击路径审计捕获了它,因为:
selectThread 重置了 composeMode