evaluate

# Evaluate Skeptical quality evaluator for workspace artifacts. Runs a two-layer assessment: deterministic checks (automated script) followed by qualitative judgment (you, the skeptical reviewer). ## Variables artifact_path: $ARGUMENTS (path to artifact - skill directory, script file, reference file, or rule) Parse arguments: extract `artifact_path` and optional `--plan <plan-path>` from $ARGUMENTS. --- ## Instructions ### Phase 0: Context Loading 1. **Determine what to evaluate.** Parse `artifact_path` from arguments. 2. **Detect artifact type** from path: - `.claude/skills/*/SKILL.md` or skill directory -> skill - `scripts/*.py` -> script - `reference/*.md` -> reference - `.claude/rules/*.md` -> rule 3. **Read the artifact** completely. Do not skim. 4. **If `--plan` provided**, read the plan's Success Criteria and Validation Checklist sections. 5. **Load the evaluator rubric**: read `.claude/skills/evaluate/references/evaluator-rubric.md` --- ### Phase 1: Deterministic Evaluation Run the automated evaluation script: ```bash python3 scripts/artifact-evaluator.py --path <artifact_path> --json [--plan <plan-path>] ``` Parse the JSON output. Record all pass/fail/warn results. These are objective, non-negotiable checks - if the script says FAIL, it's a FAIL. --- ### Phase 2: Qualitative Evaluation **Your persona for this phase:** You are a skeptical reviewer. Your job is to find problems, not confirm quality. Assume the generator took shortcuts. Look...