Menu
Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Accessibility audit against WCAG 2.1 AA. Checks semantic HTML, ARIA, keyboard navigation, color contrast, screen reader compatibility.
Design the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework.
Use before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.
Use to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.
Synchronize canvas state across team sessions via git. Ensures all team members see the same product knowledge.
Update canvas sections with new evidence. Ensures canvas stays current as the single source of truth.
Based on SOC occupation classification
| name | eval-runner |
| description | Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics. |
Benchmark the agent's performance against defined scenarios. Adapted from n-trax eval system.
run <category/name>.claude/evals/scenarios/<category>/<name>.yml.claude/evals/results/<timestamp>-<name>.jsonrun-all [category].claude/evals/scenarios/**/*.ymlreport.claude/evals/results/| Category | Pass Rate | Avg Iterations | Avg Time | Notes |
|-------------|-----------|----------------|----------|-------|
| discovery | ... | ... | ... | |
| delivery | ... | ... | ... | |
| integration | ... | ... | ... | |
| **Overall** | ... | ... | ... | |
See .claude/evals/schema.md for YAML scenario and JSON result formats.
Place YAML files in .claude/evals/scenarios/<category>/. Define task_prompt, success_criteria, and budget.