pulser

分类: 工具与效率 | 上传者: TheStack-ai | 下载: 0 | 版本: v1.0（最新）

根据 Anthropic 的 7 项原则诊断和测试 Claude Code 技能。扫描 SKILL.md 文件，检查 8 条规则（陷阱、描述、允许的工具、文件大小、结构、frontmatter、冲突、用法挂钩）、对技能类型进行分类、生成处方并运行评估测试。在检查技能质量、审核技能、测试技能或发布技能之前使用。在“스킬 점검”、“스킬 진단”、“스킬 테스트”、“检查技能”、“审核技能”、“测试技能”、“技能健康状况”、“脉冲器”、“脉冲器评估”上触发。

更新日志: Source: GitHub https://github.com/TheStack-ai/pulser

目录结构

当前层级: tree/main/skill/

📄 SKILL.md 3.0 KB

SKILL.md

---
name: pulser
description: Diagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (gotchas, description, allowed-tools, file-size, structure, frontmatter, conflicts, usage-hooks), classifies skill types, generates prescriptions, and runs eval tests. Use when checking skill quality, auditing skills, testing skills, or before publishing skills. Triggers on "스킬 점검", "스킬 진단", "스킬 테스트", "check skills", "audit skills", "test skills", "skill health", "pulser", "pulser eval".
disable-model-invocation: false
allowed-tools: Bash(pulser *), Bash(npx pulser-cli *), Read, Edit
---

# Pulser — Skill Diagnostics & Testing

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

## How to Run

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

If `pulser` is not installed globally, use:
```bash
npx pulser-cli --format json ~/.claude/skills/
```

For a single skill:
```bash
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:

```bash
pulser eval --format json
```

For a single skill:
```bash
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)

登录后下载/点赞/收藏 ❤ 8 | ★ 0

pulser

目录结构

SKILL.md

举报内容

提示