Pulser — Skill Diagnostics & Testing

Run pulser to diagnose and test Claude Code skills, then present results conversationally.

How to Run

pulser --format json ~/.claude/skills/

If pulser is not installed globally, use:

npx pulser-cli --format json ~/.claude/skills/

For a single skill:

pulser --format json --skill <name> ~/.claude/skills/

How to Present Results

1. Run the command above and capture JSON output
2. Parse the JSON result
3. Present a conversational summary:
   • Total skills, score, healthy/warning/error counts
   • Top issues (max 5) with skill name + issue
   • "Fix these issues?" prompt
4. If user says yes, apply prescriptions one by one:
   • Show the before/after diff
   • Ask for confirmation
   • Apply via Edit tool (NOT via --fix flag — you have more context than the CLI)

Summary Format

스킬 진단 완료:

📊 30개 스킬 스캔 | Score: 76/100
✓ 22 healthy  ⚠ 6 warnings  ✗ 2 errors

주요 이슈:
1. cardnews — Gotchas 없음, allowed-tools 미설정
2. geo-audit — 338줄 단일파일, Gotchas 없음
3. detailpage — Gotchas 없음, allowed-tools 미설정

고칠까요?

When Fixing

Use the prescription data from JSON. For each fix:

• Read the actual SKILL.md file
• Apply the suggested change using Edit tool
• Verify the change makes sense in context
• You can improve on the template prescriptions — you understand the skill's purpose

Eval — Skill Testing

Run pulser eval to test skills that have eval.yaml files:

pulser eval --format json

For a single skill:

pulser eval --format json --skill <name>

Present eval results conversationally:

• Total tests, passed, failed, regressions
• Failed test details with assertion info
• Regression warnings (previously passing tests that now fail)

Gotchas

1. Do not dump raw JSON to the user — always summarize conversationally
2. If pulser is not installed, suggest npm install -g pulser-cli first
3. For --fix operations, use Edit tool directly rather than CLI --fix (you have better context)
4. Score below 50 is critical — highlight urgently
5. Don't fix all skills at once — group by priority, confirm with user
6. Eval only works for text-output skills (analysis, research, generation, reference) — execution-type skills cannot be tested this way
7. Eval requires Claude Code CLI installed (claude -p must be available)