============================================================
SELF-HEALING VALIDATION (max 3 iterations)
After completing all phases, validate the combined output:
- Re-run the specific checks that originally found issues to confirm fixes.
- Run the project's test suite to verify fixes didn't introduce regressions.
- Run build/compile to confirm no breakage.
- If new issues surfaced from fixes, add them to the fix queue.
- Repeat the fix-validate cycle up to 3 iterations total.
STOP when:
- Zero Critical/High issues remain
- Build and tests pass
- No new issues introduced by fixes
IF STILL FAILING after 3 iterations:
- Document remaining issues with full context
- Classify as requiring manual intervention or architectural changes
============================================================
SELF-EVOLUTION TELEMETRY
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
- Look for the project path in
~/.claude/projects/
- If found, append to
skill-telemetry.md in that memory directory
Entry format:
### /review-implement — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}
Only log if the memory directory exists. Skip silently if not found.
Keep entries concise — /evolve will parse these for skill improvement signals.
1---2name: review-implement3description: Review then build — chains architecture review into implementation. Accepts any spec format (ticket, PRD, engineering spec, feature description, screenshot) and autonomously reviews the design, resolves gaps, then implements with tests and a PR.4version: "2.0.0"5category: combo6instructions: |7 You are an autonomous review-to-implementation agent. Do NOT ask the user questions.8 Run the full pipeline below without pausing between phases.910 INPUT:11 $ARGUMENTS1213 The user will provide a spec in any format: ticket, PRD, engineering spec, feature14 description, bullet points, screenshot, or conversation summary.1516 ============================================================17 PHASE 1: ARCHITECTURE REVIEW (/arch-review)18 ============================================================1920 Follow the instructions defined in the `/arch-review` skill exactly.21 Run in Design Review mode (pre-implementation).2223 Produce the full review output: feasibility, completeness, codebase impact,24 schema design, API design, business logic, risks, and gaps.2526 End with the verdict: READY TO IMPLEMENT, NEEDS CLARIFICATION, or SIGNIFICANT GAPS.2728 **If NEEDS CLARIFICATION or SIGNIFICANT GAPS:**29 - Resolve all identified issues yourself. Make reasonable decisions.30 - Amend the spec with your resolutions.31 - Document what you decided and why.32 - Produce a revised, implementation-ready spec.3334 Do NOT stop here. Continue immediately to Phase 2 with the35 reviewed (and possibly amended) spec.3637 ============================================================38 PHASE 2: IMPLEMENTATION (/story-implementer)39 ============================================================4041 Follow the instructions defined in the `/story-implementer` skill exactly.4243 Use the reviewed and resolved spec from Phase 1 as input — NOT the original44 raw input. This ensures all design decisions and gap fixes from the review45 are reflected in the implementation.4647 - Implement the feature with production-ready code48 - Write unit tests49 - Create a commit and PR50 - Check for and address bot review comments5152 ============================================================53 OUTPUT54 ============================================================5556 When both phases are complete, print a summary:5758 ---59 ## Review & Implement Complete606162 PARALLEL EXECUTION: When review findings span both backend and frontend, use the Agent tool to fix them concurrently.63 - Agent A (Backend Fixes): "Fix the following backend review findings: [backend findings]. Run backend tests after each fix. Return: files modified, tests pass/fail."64 - Agent B (Frontend Fixes): "Fix the following frontend review findings: [frontend findings]. Run frontend tests after each fix. Return: files modified, tests pass/fail."65 - Wait for both agents to complete.66 - Run the full test suite to verify integration.676869 **Feature:** [title]70 **Review verdict:** [READY / NEEDS CLARIFICATION / SIGNIFICANT GAPS]71 **Resolutions made:** [N issues resolved during review, or "None needed"]72 **PR:** [PR URL]7374 **What was built:**75 - [bullet summary of implementation]7677 **Next steps:**78 - Run `/e2e` or `/walkthrough` to verify with automated tests79 - Run `/qa` for full QA verification80 - Run `/manual-test-plan` to generate a manual test plan for the PR81 ---8283 STRICT RULES:8485 - Do NOT implement without reviewing first. Phase 1 always runs.86 - Do NOT ask the user to resolve review findings. Resolve them yourself.87 - If the review found gaps, the implementation MUST address them.88 - All rules from `/arch-review` and `/story-implementer` apply to their respective phases.89platforms:90 - CLAUDE_CODE91metadata:92 source: https://skillmd.com/skills/tinh2/review-implement93---949596============================================================97SELF-HEALING VALIDATION (max 3 iterations)98============================================================99100After completing all phases, validate the combined output:1011021. Re-run the specific checks that originally found issues to confirm fixes.1032. Run the project's test suite to verify fixes didn't introduce regressions.1043. Run build/compile to confirm no breakage.1054. If new issues surfaced from fixes, add them to the fix queue.1065. Repeat the fix-validate cycle up to 3 iterations total.107108STOP when:109- Zero Critical/High issues remain110- Build and tests pass111- No new issues introduced by fixes112113IF STILL FAILING after 3 iterations:114- Document remaining issues with full context115- Classify as requiring manual intervention or architectural changes116117118============================================================119SELF-EVOLUTION TELEMETRY120============================================================121122After producing output, record execution metadata for the /evolve pipeline.123124Check if a project memory directory exists:125- Look for the project path in `~/.claude/projects/`126- If found, append to `skill-telemetry.md` in that memory directory127128Entry format:129```130### /review-implement — {{YYYY-MM-DD}}131- Outcome: {{SUCCESS | PARTIAL | FAILED}}132- Self-healed: {{yes — what was healed | no}}133- Iterations used: {{N}} / {{N max}}134- Bottleneck: {{phase that struggled or "none"}}135- Suggestion: {{one-line improvement idea for /evolve, or "none"}}136```137138Only log if the memory directory exists. Skip silently if not found.139Keep entries concise — /evolve will parse these for skill improvement signals.