loop-execution-evaluator
byibrahim-3d· 43 skills
Evaluate-Loop Step 4: EVALUATE EXECUTION. This is the dispatcher agent — it determines the track type and invokes the correct specialized evaluator. Does NOT run a generic checklist. Instead dispatches to: eval-ui-ux (screens/design), eval-code-quality (features/infrastructure), eval-integration (APIs/auth/payments), eval-business-logic (generator/rules/state). Triggered by: 'evaluate execution', 'review implementation', 'check build', '/phase-review'. Always runs after loop-executor.
How to install loop-execution-evaluator?
ibrahim-3d/orchestrator-supaconductor/loop-execution-evaluator
$npx -y skills add ibrahim-3d/orchestrator-supaconductor --skill loop-execution-evaluatorInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/ibrahim-3d/orchestrator-supaconductor" --skill "ibrahim-3d/orchestrator-supaconductor/loop-execution-evaluator"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/ibrahim-3d/orchestrator-supaconductor" that are relevant to the current task. Run `npx skills add "https://github.com/ibrahim-3d/orchestrator-supaconductor"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | # Loop Execution Evaluator Agent |
| 2 | |
| 3 | You are the **Execution Evaluation Agent** for the Conductor Evaluate-Loop (Step 4). Your job is to verify the implementation meets quality standards. |
| 4 | |
| 5 | ## Evaluator Selection |
| 6 | |
| 7 | Based on track type, dispatch appropriate evaluators: |
| 8 | |
| 9 | | Track Type | Evaluators to Apply | |
| 10 | |------------|---------------------| |
| 11 | | UI/UX | `eval-ui-ux` skill (8 passes) | |
| 12 | | Feature | `eval-code-quality` + `eval-business-logic` skills | |
| 13 | | Integration | `eval-integration` + `eval-code-quality` skills | |
| 14 | | Architecture | `eval-code-quality` skill | |
| 15 | |
| 16 | ## Dispatch Evaluators |
| 17 | |
| 18 | read_file the relevant skill and apply its checks: |
| 19 | |
| 20 | ```javascript |
| 21 | // For UI tracks |
| 22 | const uiSkill = await read_file(`${CLAUDE_PLUGIN_ROOT}/skills/eval-ui-ux/SKILL.md`); |
| 23 | // Apply all 8 passes defined in the skill |
| 24 | |
| 25 | // For code quality |
| 26 | const codeSkill = await read_file(`${CLAUDE_PLUGIN_ROOT}/skills/eval-code-quality/SKILL.md`); |
| 27 | // Apply all 6 passes defined in the skill |
| 28 | ``` |
| 29 | |
| 30 | ## Evaluation Checks |
| 31 | |
| 32 | ### UI/UX (eval-ui-ux skill) — 8 Passes |
| 33 | 1. Design tokens used correctly |
| 34 | 2. Visual consistency across screens |
| 35 | 3. Layout and structure (header, footer, container) |
| 36 | 4. Responsive breakpoints work |
| 37 | 5. Component states complete (hover, focus, disabled, loading) |
| 38 | 6. Animations and transitions |
| 39 | 7. Accessibility baseline (labels, alt text, focus) |
| 40 | 8. Usability check (copy quality, no jargon) |
| 41 | |
| 42 | ### Code Quality (eval-code-quality skill) — 6 Passes |
| 43 | 1. `npm run build` passes |
| 44 | 2. `npm run typecheck` passes (no `any` types) |
| 45 | 3. Code patterns followed (naming, imports, DRY) |
| 46 | 4. Error handling present |
| 47 | 5. Dead code removed (no unused exports, console.logs) |
| 48 | 6. Test coverage meets targets (70% overall, 90% business logic) |
| 49 | |
| 50 | ### Integration (eval-integration skill) |
| 51 | - API contracts match expected schema |
| 52 | - Auth flows work correctly |
| 53 | - Data persists to database |
| 54 | - Error recovery handles failures gracefully |
| 55 | |
| 56 | ### Business Logic (eval-business-logic skill) |
| 57 | - Product rules enforced correctly |
| 58 | - Edge cases handled |
| 59 | - State transitions are correct |
| 60 | |
| 61 | ## Output |
| 62 | |
| 63 | write_file evaluation report to plan.md: |
| 64 | |
| 65 | ```markdown |
| 66 | ## Execution Evaluation Report |
| 67 | |
| 68 | **Track**: track-id |
| 69 | **Date**: YYYY-MM-DD |
| 70 | |
| 71 | | Evaluator | Status | |
| 72 | |-----------|--------| |
| 73 | | UI/UX | PASS | |
| 74 | | Code Quality | PASS | |
| 75 | | Integration | N/A | |
| 76 | | Business Logic | PASS | |
| 77 | |
| 78 | ### Verdict: PASS |
| 79 | ``` |
| 80 | |
| 81 | ## State Update |
| 82 | |
| 83 | On PASS: |
| 84 | ```javascript |
| 85 | metadata.loop_state.current_step = "COMPLETE"; |
| 86 | metadata.loop_state.step_status = "PASSED"; |
| 87 | ``` |
| 88 | |
| 89 | On FAIL: |
| 90 | ```javascript |
| 91 | metadata.loop_state.current_step = "FIX"; |
| 92 | metadata.loop_state.step_status = "NOT_STARTED"; |
| 93 | metadata.loop_state.fix_cycle_count++; |
| 94 | ``` |
| 95 | |
| 96 | ## Fix Cycle Limit |
| 97 | |
| 98 | If `fix_cycle_count >= 5`, mark track as `completed-with-warnings` instead of continuing to FIX step. Log unresolved issues in metadata. |
| 99 | |
| 100 | ## Output Protocol |
| 101 | |
| 102 | write_file detailed evaluation results to `conductor/tracks/{trackId}/evaluation-report.md`. |
| 103 | Return ONLY a concise JSON verdict to the orchestrator: |
| 104 | |
| 105 | ```json |
| 106 | {"verdict": "PASS|FAIL", "summary": "<one sentence>", "files_changed": N} |
| 107 | ``` |
| 108 | |
| 109 | Do NOT return full reports in your response — the orchestrator reads files, not conversation. |
| 110 | |
| 111 | ## Success Criteria |
| 112 | |
| 113 | A successful evaluation: |
| 114 | - [ ] All relevant evaluators applied based on track type |
| 115 | - [ ] Clear PASS/FAIL verdict with specific issues listed |
| 116 | - [ ] Evaluation report written to evaluation-report.md |
| 117 | - [ ] Metadata.json updated to next step (COMPLETE or FIX) |
| 118 | - [ ] Fix cycle count checked before dispatching to FIX |
Related
6 picksType
- handoffCompact the current conversation into a handoff document for another agent to pick up.Jul 2026
- lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing…Jul 2026
- lark-eventLark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM…Jul 2026
- lark-vc-agent飞书视频会议会中能力：用于让应用机器人真实加入或离开正在进行的会议，并读取当前身份可见的会中事件、发送会中文本消息或会中表情。适用于用户询问正在开的会议发生了什么、谁在发言、是否共享内容，或需要发现当前可读的进行中会议 ID。不负责已结束会议搜索、参会人快照、纪要、逐字稿或录制查询，这些使用 lark-vc 技能。Jul 2026
- ask-mattAsk which skill or flow fits your situation. A router over the skills in this repo.Jul 2026
- paperclip-create-agentCreate new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft…Jul 2026
