ibrahim-3d/conductor-orchestrator-superpowers/loop-execution-evaluator
Claude Code and agent skill by ibrahim-3d/conductor-orchestrator-superpowers
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install ibrahim-3d/conductor-orchestrator-superpowers/loop-execution-evaluatorSKILL.md
Loop Execution Evaluator — Step 4: Dispatcher
This agent does NOT evaluate directly. It determines the track type and dispatches the correct specialized evaluator.
Why Specialized Evaluators?
Different track types need fundamentally different checks:
- A UI track needs design system adherence, visual consistency, responsive checks
- A feature track needs build integrity, type safety, code patterns
- An integration track needs API contracts, auth flows, error recovery
- A business logic track needs product rules, edge cases, state transitions
A generic checklist misses critical issues specific to each type.
Dispatch Logic
read_file the track's metadata.json and spec.md to determine the track type, then dispatch:
| Track Type | Keywords in spec/metadata | Evaluator | |
|---|---|---|---|
| UI / Design | "screen", "component", "design system", "layout", "visual", "UI shell" | eval-ui-ux | |
| Feature / Code | "implement", "feature", "refactor", "infrastructure", "hook", "store" | eval-code-quality | |
| Integration | "Supabase", "Stripe", "Gemini", "API", "auth", "database", "webhook" | eval-integration | |
| Business Logic | "generation", "lock", "dependency", "pricing", "tier", "pipeline", "download" | eval-business-logic |
Multi-Type Tracks
Some tracks need multiple evaluators. For example:
- A generator logic track →
eval-business-logic+eval-code-quality - An auth/DB integration track →
eval-integration+eval-code-quality - A UI shell track →
eval-ui-uxonly
When multiple evaluators apply, run them all. The track passes only if ALL evaluators pass.
Dispatch Workflow
Structural Checks (Always Run)
Regardless of track type, always verify these baseline checks:
| Check | Method | |
|---|---|---|
| plan.md updated | All completed tasks marked [x] with commit SHA and summary | |
| Scope alignment | No unplanned work added without documentation | |
| No skipped tasks | All [ ] tasks either completed or documented as intentionally deferred | |
| Build passes | npm run build exits 0 | |
| Business docs in sync | If track made pricing/model/business decisions, verify docs are flagged for Step 5.5 sync |
Business Doc Sync Check
If the track made any business-impacting changes, verify:
- The executor's summary includes
Business Doc Sync Required: Yes - Affected documents are listed
- This flags the Conductor to run Step 5.5 (Business Doc Sync) before marking complete
What counts as business-impacting:
- Pricing tier, price point, or feature list changes
- AI model, SDK, or cost structure changes
- New package or product tier additions
- Asset pipeline changes (add/remove/modify assets)
- Persona, GTM, or revenue assumption changes
See ${CLAUDE_PLUGIN_ROOT}/skills/business-docs-sync/SKILL.md for the full registry.
Aggregated Verdict
Metadata Checkpoint Updates
The execution evaluator MUST update the track's metadata.json at key points:
On Start
On PASS
On FAIL
Update Protocol
- read_file current
metadata.json - Update
loop_state.checkpoints.EVALUATE_EXECUTIONwith results - If PASS + business sync needed: Set
current_steptoBUSINESS_SYNC - If PASS + no sync needed: Set
current_steptoCOMPLETE - If FAIL: Set
current_steptoFIX, incrementfix_cycle_countin loop_state - write_file back to
metadata.json
Handoff
- ALL PASS + No Business Doc Sync → Conductor marks track complete (Step 5)
- ALL PASS + Business Doc Sync Needed → Conductor runs Step 5.5 (Business Doc Sync) before marking complete
- ANY FAIL → Conductor dispatches
loop-fixerwith combined fix list
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/loop-execution-evaluator/SKILL.md
Popularity
- Repository stars
- 300
- Repository forks
- 31
- 7-day trend score
- 29
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 30 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ibrahim-3d/conductor-orchestrator-superpowers/loop-execution-evaluator)