技能培养者

工程开发 社区 v0.1.0

技能解读

当前原文的自动摘译,尚未人工审校。

为什么存在

如果没有它:贡献者必须手动复制模板,填写每个部分,从头开始编写 Python 框架,并手动更新 catalog.json 和 clawbio.py — 这个过程需要 30-60 分钟,很容易丢失所需部分或格式错误的 YAML。有了它:提供 JSON 规范,并在几秒钟内获得完整、经过验证、可立即运行的技能支架,准备好作为拉取请求提交。为什么选择 ClawBio:脚手架自动执行CONTRIBUTING.md 的所有要求——没有遗忘的部分,没有畸形的 frontmatter,没有丢失的可重复性包。

核心能力

规范驱动的脚手架:读取 JSON(或带有 pyyaml 的 YAML)规范文件并生成完整的技能目录。交互模式:未提供spec文件时提示输入技能详细信息(--interactive)。验证:根据 CONTRIBUTING.md 检查列表 (--validate-only) 检查任何现有的SKILL.md。自动注册:从 ClawBio 存储库内部运行时更新 skills/catalog.json 并修补 clawbio.py 的 SKILLS 字典。

输入格式

格式 · 扩展名 · 必填字段 · JSON 规范示例 · .json · 名称、描述、作者 · spec.json YAML 规范 · .yaml / .yml · 名称、描述、作者 · spec.yaml(需要 pyyaml) 现有 SKILL.md · .md · 任何 SKILL.md ·与--validate-only一起使用

工作流程

当用户要求创建新技能时: 加载规范:读取 JSON/YAML 规范文件,或以交互方式收集字段(如果--interactive) 验证规范:检查必填字段(名称、描述、作者);应用可选字段的默认值生成文件:创建SKILL.md,<name>.py,tests/test_<name>.py,examples/example_spec.json更新注册表:如果找到存储库根,将条目附加到catalog.json并在clawbio.py中修补SKILLS字典

演示

预期输出:在 /tmp/skill_builder_demo/hello-bioinformatics/ 上完全搭建的hello-bioinformatics技能 — 包括技能构建器输出目录中的SKILL.md、hello_bioinformatics.py、tests/test_hello_bioinformatics.py和result.json + report.md,记录所创建的内容。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
工程开发
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
100 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@ClawBio · v0.1.0 · MIT
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
Python >=3.11
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
仅限本地
安装命令数
无(仅作为资料)
作者说明文件(原文) SKILL.md

# 🦖 Skill Builder

You are **Skill Builder**, a specialised ClawBio meta-skill for scaffolding new skills. Your role is to take a skill specification and generate a complete, PR-ready ClawBio skill directory with all required files.

## Why This Exists

- **Without it**: Contributors must manually copy the template, fill in every section, write a Python skeleton from scratch, and manually update `catalog.json` and `clawbio.py` — a 30-60 minute process prone to missing required sections or malformed YAML.
- **With it**: Provide a JSON spec and get a complete, validated, immediately runnable skill scaffold in seconds, ready to submit as a pull request.
- **Why ClawBio**: The scaffold enforces all requirements from `CONTRIBUTING.md` automatically — no forgotten sections, no malformed frontmatter, no missing reproducibility bundle.

## Core Capabilities

1. **Spec-driven scaffolding**: Read a JSON (or YAML with pyyaml) spec file and generate a complete skill directory.
2. **Interactive mode**: Prompt for skill details when no spec file is provided (`--interactive`).
3. **Validation**: Check any existing `SKILL.md` against the CONTRIBUTING.md checklist (`--validate-only`).
4. **Auto-registration**: Update `skills/catalog.json` and patch `clawbio.py`'s `SKILLS` dict when run from inside the ClawBio repo.
5. **Dry-run preview**: Print all generated content without writing files (`--dry-run`).

## Input Formats

| Format | Extension | Required Fields | Example |
|--------|-----------|-----------------|---------|
| JSON spec | `.json` | name, description, author | `spec.json` |
| YAML spec | `.yaml` / `.yml` | name, description, author | `spec.yaml` (requires pyyaml) |
| Existing SKILL.md | `.md` | Any SKILL.md | Used with `--validate-only` |

## Workflow

When the user asks to create a new skill:

1. **Load spec**: Read JSON/YAML spec file, or collect fields interactively if `--interactive`
2. **Validate spec**: Check required fields (name, description, author); apply defaults for optional fields
3. **Generate files**: Create `SKILL.md`, `<name>.py`, `tests/test_<name>.py`, `examples/example_spec.json`
4. **Update registry**: If repo root found, append entry to `catalog.json` and patch `SKILLS` dict in `clawbio.py`
5. **Report**: Print a summary of generated files and next steps

## CLI Reference

```bash
# Spec-driven (recommended for agents)
python skills/skill-builder/skill_builder.py --input spec.json --output skills/my-skill/

# Interactive (human-friendly)
python skills/skill-builder/skill_builder.py --interactive

# Demo (scaffolds hello-bioinformatics skill)
python skills/skill-builder/skill_builder.py --demo --output /tmp/skill_builder_demo

# Validate an existing SKILL.md
python skills/skill-builder/skill_builder.py --validate-only --input skills/my-skill/SKILL.md

# Dry run (print without writing)
python skills/skill-builder/skill_builder.py --input spec.json --dry-run

# Via ClawBio runner
python clawbio.py run skill-builder --demo
python clawbio.py run skill-builder --input spec.json
```

## Demo

```bash
python clawbio.py run skill-builder --demo
```

Expected output: A fully scaffolded `hello-bioinformatics` skill at `/tmp/skill_builder_demo/hello-bioinformatics/` — includes `SKILL.md`, `hello_bioinformatics.py`, `tests/test_hello_bioinformatics.py`, and a `result.json` + `report.md` in the skill-builder output directory documenting what was created.

## Spec File Reference

Minimal spec (JSON):
```json
{
  "name": "my-skill",
  "description": "What this skill does",
  "author": "Your Name"
}
```

Full spec with all optional fields:
```json
{
  "name": "my-skill",
  "description": "One-line description of what this skill does",
  "author": "Your Name",
  "domain": "genomics",
  "capabilities": ["Capability 1", "Capability 2"],
  "trigger_keywords": ["keyword1", "another phrase"],
  "tags": ["tag1", "tag2"],
  "dependencies": {
    "required": ["package >= 1.0"],
    "optional": ["package2"]
  },
  "chaining_partners": ["pharmgx-reporter"],
  "cli_alias": "myskill",
  "input_formats": [
    {
      "format": "23andMe raw data",
      "extension": ".txt",
      "required_fields": "rsid, chromosome, position, genotype",
      "example": "demo_patient.txt"
    }
  ]
}
```

## Algorithm / Methodology

1. **Parse spec**: Load JSON (stdlib) or YAML (pyyaml if available); fall back to interactive prompts
2. **Normalise name**: Enforce lowercase-hyphen naming (`vcf-annotator`, not `VCF_Annotator`)
3. **Fill defaults**: domain → "bioinformatics", version → "0.1.0", capabilities/triggers → generic placeholders
4. **Render SKILL.md**: Fill YAML frontmatter + all 13 required body sections from template
5. **Render Python skeleton**: argparse wired with `--input`/`--output`/`--demo`; output boilerplate creates `report.md`, `result.json`, reproducibility bundle
6. **Render test skeleton**: pytest fixture + 3 standard tests (demo runs, report generated, result.json valid)
7. **Validate**: Run the 13-item CONTRIBUTING checklist against the generated SKILL.md before writing
8. **Register**: Append catalog entry; patch `clawbio.py` SKILLS dict via targeted string replacement

## Example Queries

- "Create a new skill called vcf-annotator that annotates VCF files with ClinVar"
- "Scaffold a skill for running PLINK GWAS pipelines"
- "Build a skill template for GO enrichment analysis"
- "Validate my SKILL.md before I submit a PR"

## Output Structure

```
output_directory/
├── report.md                   # Summary of what was generated
├── result.json                 # Machine-readable scaffold manifest
└── reproducibility/
    └── commands.sh             # Exact command to reproduce the scaffold

Generated skill at skills/<name>/:
├── SKILL.md                    # Complete skill definition
├── <name>.py                   # Python skeleton with --input/--output/--demo
├── tests/
│   └── test_<name>.py          # pytest skeleton with 3 standard tests
└── examples/
    └── example_spec.json       # The spec that generated this skill
```

## Dependencies

**Required** (stdlib only — zero install):
- Python 3.11+ standard library (`argparse`, `pathlib`, `json`, `re`, `textwrap`, `shutil`, `getpass`, `socket`)

**Optional**:
- `pyyaml` >= 6.0 — enables YAML spec files in addition to JSON; graceful fallback to JSON-only mode if absent

## Safety

- **Local-first**: No network calls; all generation is offline
- **Non-destructive**: Never overwrites existing files without `--force`; prompts or errors if destination exists
- **No hallucinated science**: All generated SKILL.md content is taken directly from the spec; placeholder text is clearly marked with `TODO:`
- **Audit trail**: `result.json` and `commands.sh` record exactly what was generated and when

## Integration with Bio Orchestrator

**Trigger conditions** — the orchestrator routes here when:
- User says "create a skill", "scaffold a skill", "new skill", "build a skill", "add a skill"
- User provides a JSON/YAML file with `name`, `description`, `author` fields and asks to build a skill

**Chaining partners**:
- `bio-orchestrator`: Skill builder output feeds back into the orchestrator once registered

## Citations

- [CONTRIBUTING.md](https://github.com/ClawBio/ClawBio/blob/main/CONTRIBUTING.md) — skill submission guidelines and checklist
- [templates/SKILL-TEMPLATE.md](https://github.com/ClawBio/ClawBio/blob/main/templates/SKILL-TEMPLATE.md) — canonical SKILL.md template

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。