一键导入
review-findings
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification.
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。
菜单
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification.
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。
基于 SOC 职业分类
Post-implementation business assessment by Prometeo (PM). Verifies success metrics achievement, scope compliance, acceptance criteria business interpretation, risk materialization, and product decision closure. Outputs structured report with verdict and confidence score.
Analyzes checklist effectiveness by tracking hit rates, identifying stale items, and finding coverage gaps. Generates evolution suggestions following Boorman's principles. Use periodically to keep checklists field-tested and relevant.
Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Use periodically or before releases to maintain code hygiene.
Creates a complete product feature specification. Use when defining new features, writing user stories, or planning product work. Generates structured specs in docs/specs/.
Generates test cases for a module or function following FIRST principles and Arrange-Act-Assert pattern. Detects test framework from project config. Use to bootstrap test coverage for existing code or as the Red phase of TDD.
Create and manage git worktrees for isolated feature work. Use when starting implementation that should not touch the main workspace, or for parallel development. Handles creation, baseline verification, and cleanup.
| name | review-findings |
| description | Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification. |
| context | fork |
| agent | forja-dev |
Fix the findings from the QA review: $ARGUMENTS
If no specific review is mentioned, look for the most recent review in docs/reviews/.
Follow these steps:
SIGN IN:
Every finding in the review report must have a severity:
Each finding tracks its status through the Centinela > Forja > Centinela loop:
Open (Centinela identifies in review)
> Assigned (handoff to Forja via review-findings)
> Implemented (Forja completes fix)
> Verified (Centinela re-verifies)
> Closed
When reading the review report, update each finding's status from Open to Assigned.
When fixing is complete, update status to Implemented.
Centinela re-verification updates to Verified then Closed.
Entry criteria (must be true before starting fixes):
docs/reviews/{feature-name}-review.mdExit criteria (must be true before handoff back to Centinela):
ImplementedTECH_DEBT.md with justificationEach finding in the review report must include:
| Field | Description |
|---|---|
| ID | F-{NNN} sequential |
| Severity | Critical / Major / Medium / Minor |
| Status | Open / Assigned / Implemented / Verified / Closed |
| Category | Code Quality / Architecture / Spec Compliance |
| Description | What the issue is |
| Location | file:line reference |
| Recommendation | How to fix |
| Verified-By | Agent that verified the fix (populated during re-verification) |
Reference: O'Regan (2019), Ch. 7, sections 7.3-7.5
⏸️ TIME OUT — Pre-Fix Preparation (READ-DO):
docs/reviews/FIX (using Clean Code principles): 5. For each finding:
⏸️ TIME OUT — Run Implementation Complete + Pre-Delivery Checklists (DO-CONFIRM): 7. Run the Implementation Complete checklist from your agent file 8. Run the Pre-Delivery checklist from your agent file Additionally verify:
SIGN OUT: 9. Write a Fix Report using the Fix Report checklist from your agent file 10. Run the SIGN OUT checklist from your agent file