← 返回 Skills 市场
105
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install project-init
功能描述
Project initialization toolkit. contributing - auto-generate CONTRIBUTING.md from project structure [contributing.md]. "init", "project init", "initialize pr...
安全使用建议
This skill is coherent for generating a CONTRIBUTING.md: it will read project files (package.json, .editorconfig, eslint, husky, pnpm-workspace.yaml, src/, packages/ etc.) and propose/write ./CONTRIBUTING.md. Before running or committing output: (1) ensure you run it inside the intended repository (it will read files in the current working tree), (2) review the generated CONTRIBUTING.md before accepting/committing (the skill notes it will ask before overwriting), (3) be aware some config files or scripts may contain sensitive info — verify nothing secret is unintentionally revealed in the generated doc, (4) the instructions assume helper tools like jq and typical Node tooling (pnpm/corepack) — install those if needed or the analysis commands may fail, and (5) because this is instruction-only and asks no secrets, risk is low but always review generated content before pushing.
能力评估
Purpose & Capability
The name/description claim to analyze project structure and generate CONTRIBUTING.md, and the SKILL.md describes reading package.json, .editorconfig, lint and husky configs, monorepo files, and producing a CONTRIBUTING.md — all coherent and proportionate to the stated purpose.
Instruction Scope
Runtime instructions explicitly call local filesystem inspection (ls, cat, reading config files) and then writing ./CONTRIBUTING.md. This is expected for a project-init tool. The skill includes a non-destructive confirmation step before overwriting. Note: examples use tools like jq and assume standard repo layout; those binaries are not declared but are normal helper assumptions rather than suspicious behavior.
Install Mechanism
No install spec and no code files (instruction-only), so nothing is downloaded or written to disk by an installer. This is the lowest-risk pattern for this kind of skill.
Credentials
The skill requests no environment variables, credentials, or config paths. It only reads local repo files consistent with its purpose; there are no unexplained secrets requested.
Persistence & Privilege
always is false and the skill does not request persistent presence or modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) but not combined with other red flags.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install project-init - 安装完成后，直接呼叫该 Skill 的名称或使用
/project-init触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
Initial release: contributing topic for auto-generating CONTRIBUTING.md
元数据
常见问题
Project Init 是什么？
Project initialization toolkit. contributing - auto-generate CONTRIBUTING.md from project structure [contributing.md]. "init", "project init", "initialize pr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 105 次。
如何安装 Project Init？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install project-init」即可一键安装，无需额外配置。
Project Init 是免费的吗？
是的，Project Init 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Project Init 支持哪些平台？
Project Init 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Project Init？
由 es6kr（@drumrobot）开发并维护，当前版本 v0.1.0。
推荐 Skills