Loop Execution Evaluator — Development skill for Claude Code
Verify implementation quality.
How to install Loop Execution Evaluator
Installs to ~/.claude/skills/markyy101-conductor-orchestrator-superpowers-loop-execution-evaluator/SKILL.md
mkdir -p ~/.claude/skills/markyy101-conductor-orchestrator-superpowers-loop-execution-evaluator && curl -fsSL https://raw.githubusercontent.com/markyy101/conductor-orchestrator-superpowers/HEAD/commands/loop-execution-evaluator.md -o ~/.claude/skills/markyy101-conductor-orchestrator-superpowers-loop-execution-evaluator/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Loop Execution Evaluator does
name: loop-execution-evaluator description: "Verify implementation quality. Evaluate-Loop Step 4." arguments:
- name: track_id description: "The track ID to evaluate" required: true user_invocable: true
/loop-execution-evaluator — Evaluate Implementation
Evaluate-Loop Step 4: Verify the implementation meets quality standards.
Usage
/loop-execution-evaluator
Your Task
You ARE the loop-execution-evaluator agent. Run quality checks based on tra
Alternatives in Development
- Implementation Plan — You are tasked with creating detailed implementation plans through an interactive, iterative process 10k ★
- Evaluate Quality — Evaluate Quality of New Examples 570 ★
- Verify Theme — Run the full Graphite quality gate (drift, tokens, contrast, YAML) and report pass/fail 452 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Loop Planner
Create execution plan from specification. Evaluate-Loop Step 1.
Adversarial Dev
GAN-inspired three-agent harness that pits a generator against an adversarial evaluator to build applications
Gan Build
Run a generator/evaluator build loop for implementation tasks with bounded iterations and scoring.
Judge
Evaluate the execution quality of a skill or agent
Loop Executor
Implement tasks from the plan. Evaluate-Loop Step 3.
Vibememo Eval
Periodic VibeMemo evaluation and capture. Runs on a loop (default 30m) to assess whether significant decisions
Related Agents
Loop Evaluator
Evaluate artifact strictly against active loop criteria and return structured pass/fail output. Use proactivel
Plan Judge
Independent reviewer that scores an implementation plan against the fixed plan-quality rubric and returns spec
Evolve Cache Strategy Scan
Cache-coherence audit agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Bui