TuYv
TuYv/ccpm
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-314-review-repair-worker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-314-review-repair-worker |
| description | Use when accepted findings require bounded repair changes and a structured repair summary. |
| license | MIT |
Paths: File paths (
references/,../ln-*) are relative to this skill directory.
Type: L3 Worker Category: 3XX Planning
MANDATORY READ: Load references/evaluation_worker_runtime_contract.md, references/evaluation_summary_contract.md
MANDATORY READ: Load ../ln-310-multi-agent-validator/references/plan_review_pipeline.md, ../ln-310-multi-agent-validator/references/penalty_points.md
Conditional read: in mode=story, load only the validation checklist files for groups present in accepted findings before applying those group repairs. Load references/cleanup_evidence_contract.md only if background tools or processes are launched.
mode=story: full 11-group repair using findings from ln-312mode=plan_review: apply accepted corrections only (max 5 corrections per ../ln-310-multi-agent-validator/references/plan_review_pipeline.md Compare & Correct Safety Rules)The table below is a routing map. Load a checklist only when accepted findings include that group; do not preload unrelated validation catalogs.
| # | Group | Criteria | Checklist |
|---|---|---|---|
| 1 | Structural | #1-#4, #23-#24 | ../ln-310-multi-agent-validator/references/structural_validation.md |
| 2 | Standards | #5 | ../ln-310-multi-agent-validator/references/standards_validation.md |
| 3 | Solution | #6, #21, #28 | ../ln-310-multi-agent-validator/references/solution_validation.md |
| 4 | Workflow | #7-#13 | ../ln-310-multi-agent-validator/references/workflow_validation.md |
| 5 | Quality | #14-#15 | ../ln-310-multi-agent-validator/references/quality_validation.md |
| 6 | Dependencies | #18-#19/#19b | ../ln-310-multi-agent-validator/references/dependency_validation.md |
| 7 | Cross-Reference | #25-#26 | ../ln-310-multi-agent-validator/references/cross_reference_validation.md |
| 8 | Risk | #20 | ../ln-310-multi-agent-validator/references/risk_validation.md |
| 9 | Pre-mortem | #27 | ../ln-310-multi-agent-validator/references/premortem_validation.md |
| 10 | Verification | #22 | ../ln-310-multi-agent-validator/references/traceability_validation.md |
| 11 | Traceability | #16-#17, #17b-#17c | ../ln-310-multi-agent-validator/references/traceability_validation.md |
FLAGGED only when human judgment is required and auto-fix cannot safely continue.../ln-310-multi-agent-validator/references/penalty_points.md (do not hardcode).Runtime family:
evaluation-worker-runtimeRequired manifest fields:
identifierphase_ordersummary_kind=review-repairoperation=repairRecommended phase_order:
PHASE_0_CONFIGPHASE_1_LOAD_FINDINGSPHASE_2_GROUP_STRUCTURAL (#1-#4, #23-#24)PHASE_3_GROUP_STANDARDS_SOLUTION (#5, #6, #21, #28)PHASE_4_GROUP_WORKFLOW_QUALITY (#7-#15)PHASE_5_GROUP_DEPS_XREF (#18-#19/#19b, #25-#26)PHASE_6_GROUP_RISK_PREMORTEM (#20, #27)PHASE_7_GROUP_VERIFICATION_TRACE (#22, #16-#17, #17b-#17c)PHASE_8_VERIFY_LOCAL_RESULTPHASE_9_WRITE_SUMMARYPHASE_10_SELF_CHECKEmit summary_kind=review-repair.
Payload must include:
worker=ln-314statusoperation=repairwarningsPrefer these fields when available:
penalty_before (from ln-312 findings)penalty_after (after repairs)flagged_items (list of items requiring human judgment)coverage_summary (AC coverage percentage)groups_processed (count)review-repair summary writtenVersion: 1.0.0 Last Updated: 2026-04-10