Skill Tester

---
name: skill-tester
description: Runs TDD pressure scenarios against a skill before and after it is written, proving the skill actually changes agent behaviour instead of merely reading well. Use when verifying a new or edited skill has real effect, establishing a RED baseline before authoring, or confirming a GREEN result after.
metadata:
  disable-model-invocation: "true"
---

# Skill Tester

TDD for documentation: watch the agent fail without the skill, write the skill, watch the agent pass.

## RED phase — baseline (run BEFORE writing the skill)

Dispatch a subagent with this prompt, substituting `<skill-name>` and `<scenario>`:

```text
You are working on <scenario>. Do NOT load any skills. <pressure>

What do you do?
```

Pressure types to combine:

- **Time**: "You're under deadline, the user is waiting"
- **Sunk cost**: "You've already written 200 lines"
- **Authority**: "The senior dev told you to skip this step"
- **Exhaustion**: "This is the 10th task in a row"

Record exact rationalizations the agent uses to skip the rule.

## GREEN phase — write and verify

Write the skill or command body (`skills/<skill-name>/SKILL.md`, or
`skills/nitpicker/commands/<command>.md` for a nitpicker command). Address each rationalization from RED explicitly. Then dispatch the same subagent again, this time with the skill loaded. Confirm each RED rationalization is blocked. If a new loophole emerges, add an explicit counter to the skill and re-run.

## REFACTOR phase — verify after refactoring

Refactor the skill body for clarity and precision. Then dispatch the same scenario again (skill still loaded). Confirm all GREEN scenarios still pass and no new loopholes have appeared. If they have, add counters and re-run.

## Checklist

- [ ] RED scenario run and rationalizations documented
- [ ] Skill written addressing each rationalization
- [ ] GREEN scenario confirms compliance
- [ ] REFACTOR scenario re-run confirms no regression and no new loopholes
- [ ] Validator passes: `uv run scripts/validate-skill.py skills/<skill-name>/SKILL.md` (for a nitpicker command: `skills/nitpicker/SKILL.md` — it validates the command files too)