菜单
Hyperflow code review. Use when the user wants the current diff, a commit, branch, or PR reviewed — verbs like audit, review, "check for issues", "security check", "code review". Multi-level review (L1 quick → L5 exhaustive), writes findings to .hyperflow/audits/, then a fix-gate.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/TuYv/ccpm --skill hyperflow-audit命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS评分
Use when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix — message-matched to the destination landing page. Not for scoring an ad account — use ad-account-auditor; not for the post-click page — use landing-optimizer; not for organic articles — use content-writer. 广告创意/广告文案/RSA标题
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试
| name | hyperflow-audit |
| description | Hyperflow code review. Use when the user wants the current diff, a commit, branch, or PR reviewed — verbs like audit, review, "check for issues", "security check", "code review". Multi-level review (L1 quick → L5 exhaustive), writes findings to .hyperflow/audits/, then a fix-gate. |
Multi-level review over a target (default: git diff HEAD + staged). Follow the hyperflow doctrine. Security scan is mandatory at L3+.
| L | Checks |
|---|---|
| 1 | syntax, obvious bugs, formatting |
| 2 | L1 + spec compliance, naming, edge cases |
| 3 | L2 + cross-file consistency, integration risks, security (secrets, injection, path traversal, XSS, missing validation) |
| 4 | L3 + architecture, scalability, accessibility |
| 5 | L4 + adversarial probing, perf profiling, alternatives |
Default to L2; elevate to L3 when the diff touches auth, data, money, or external input.
[Critical] / [Important] / [Suggestion] / [Praise] with file:line + a concrete fix..hyperflow/audits/<YYYY-MM-DD-HHmm>-<scope>.md (status table → TL;DR → findings → security-scan table). Print a one-line summary pointing at the file.Fix all (Recommended) / Critical+Important / Critical only / No. On a fix choice, route the findings into hyperflow-plan → hyperflow-dispatch. On SECURITY_VIOLATION, skip the gate and surface immediately.Audit clean and still writes the file for history.