菜单
Use when auditing the test surface through the evaluation platform with mandatory research, coordinated test audit workers, and structured summaries.
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。
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 ln-630-test-auditor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。
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
基于 SOC 职业分类
正在显示 SKILL.md
| name | ln-630-test-auditor |
| description | Use when auditing the test surface through the evaluation platform with mandatory research, coordinated test audit workers, and structured summaries. |
| license | MIT |
Paths: File paths (
references/,../ln-*) are relative to this skill directory.
Type: L2 Coordinator Category: 6XX Audit
MANDATORY READ: Load references/evaluation_coordinator_runtime_contract.md, references/evaluation_summary_contract.md, references/evaluation_research_contract.md
MANDATORY READ: Load references/audit_final_report_contract.md
MANDATORY READ: Load references/test_audit_worker_boundaries.md
MANDATORY READ: Load references/risk_based_testing_guide.md, references/research_tool_fallback.md
Conditional read: load references/risk_based_testing_methodology.md only when worker findings require full methodology examples or anti-pattern detail.
Conditional read: load references/epistemic_protocol.md only when source confidence or claim uncertainty affects issue validation.
ln-631 through ln-638Runtime family:
evaluation-runtimeIdentifier:
test-auditPhase order:
PHASE_0_CONFIGPHASE_1_DISCOVERYPHASE_2_RESEARCHPHASE_3_DELEGATEPHASE_4_AGGREGATEPHASE_5_REPORTPHASE_6_SELF_CHECKln-631-test-business-logic-auditorln-632-test-e2e-priority-auditorln-633-test-value-auditorln-634-test-coverage-auditorln-635-test-isolation-auditorln-636-manual-test-auditorln-637-test-structure-auditorln-638-test-oracle-effectiveness-auditorHost Skill Invocation: Skill(skill: "...", args: "...") is mandatory delegation.
SKILL.md, treat args as $ARGUMENTS, execute that skill workflow, then return here with its result/artifact.Use the Skill tool for delegated workers. Do not inline worker logic inside the coordinator.
TodoWrite format (mandatory):
Resolve audit scope and build manifestLoad test infrastructure and coverageRun best-practice researchDelegate to domain audit workersAggregate worker findingsGenerate final audit report and remediation planVerify cleanup and self-checkRepresentative invocations:
Skill(skill: "ln-631-test-business-logic-auditor", args: "{scope}")
Skill(skill: "ln-632-test-e2e-priority-auditor", args: "{scope}")
Skill(skill: "ln-633-test-value-auditor", args: "{scope}")
Skill(skill: "ln-634-test-coverage-auditor", args: "{scope}")
Skill(skill: "ln-635-test-isolation-auditor", args: "{scope}")
Skill(skill: "ln-636-manual-test-auditor", args: "{scope}")
Skill(skill: "ln-637-test-structure-auditor", args: "{scope}")
Skill(skill: "ln-638-test-oracle-effectiveness-auditor", args: "{scope}")
evaluation-runtime.report_path, normalizing actions from references/test_audit_worker_boundaries.md, deduplicating issues, resolving worker conflicts, and validating actionable problems against references/evaluation_research_contract.md..hex-skills/runtime-artifacts/runs/{run_id}/audit-report/ln-630--final-report.md with remediation plan per references/audit_final_report_contract.md.evaluation-coordinator summary with report_path set to the final report.test_audit_worker_boundaries.mdevaluation-coordinator summary writtenOptional reference: load references/meta_analysis_protocol.md only when the user asks for post-run meta-analysis or protocol-formatted run reflection.
When requested after the coordinator run, analyze the session per protocol section 7 and include the protocol-formatted output with the final test audit result.
../ln-631-test-business-logic-auditor/SKILL.md, ../ln-632-test-e2e-priority-auditor/SKILL.md, ../ln-633-test-value-auditor/SKILL.md, ../ln-634-test-coverage-auditor/SKILL.md, ../ln-635-test-isolation-auditor/SKILL.md, ../ln-636-manual-test-auditor/SKILL.md, ../ln-637-test-structure-auditor/SKILL.md, ../ln-638-test-oracle-effectiveness-auditor/SKILL.mdVersion: 4.0.0 Last Updated: 2025-12-23