Token导航 LogoToken导航

Agent Skill · 研究检索

github-contributor(GitHub contributor 搜索)

用于围绕 GitHub 仓库、Issue、Pull Request、分支、提交和代码协作流程提供辅助能力。它适合让 Agent 查询项目状态、整理变更、辅助创建或检查协作事项,并把仓库中的信息转成可执行的下一步。使用时需要区分只读查询和写入操作;涉及创建 PR、修改 Issue、推送分支或访问私有仓库时,应确认 token 权限、目标仓库范围和用户授权。

github-contributor 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 28,280。

总安装 3,246周安装 138GitHub Stars 公开资料未说明下载 1,137核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:github-contributor(GitHub contributor 搜索)
来源仓库:https://github.com/therealhesreallyhim/github-contributor
安装命令:
openclaw skills install github-contributor
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install github-contributor

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

github-contributor 强制校验用户对指定仓库的贡献政策合规性。在执行 Issue/PR 操作前读取 .github/contributing.md 规则。防止违反 CLA 或代码所有权声明等约束条件。需在目标仓库中预先定义贡献指南文件。

github-contributor 属于研究检索类 Skill,可作为该场景下的辅助能力补充。若未找到政策文件则跳过检查并提示警告。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install github-contributor;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

github-contributor 怎么安装?

在终端执行 openclaw skills install github-contributor。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

github-contributor 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

github-contributor 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

github-contributor 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

github-contributor 用的人多吗?

公开数据是累计安装 3,246 次,近一周安装 138 次,下载 1,137 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

github-contributor 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
github-contributor

GitHub contributor 搜索 · 本页

3,246—只读MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
github-contributor
description
Enforces repository-defined contribution policy before any GitHub interaction (issues, PRs, comments, reviews). Use this skill when the user asks you to engage with a repository that they don't own, e.g. "Open a PR", "Create a new issue", "Submit this project to an awesome list".

GitHub Contributor Protocol

This skill governs all outward interactions on GitHub.

All behavior must align with the repository’s published policies (e.g., CONTRIBUTING.md, CODE_OF_CONDUCT.md, templates, SECURITY.md). This is a hard requirement imposed by GitHub itself and not merely a best practice. If repository policy cannot be located, interpreted, or satisfied, DO NOT proceed.


1. Mandatory Pre-Interaction Protocol

Before creating or commenting on:

  • Issues
  • Pull Requests
  • Discussions
  • Reviews

You MUST complete all steps below.


A. Identify Repository Context

Determine:

  • owner/name
  • default branch
  • fork vs upstream
  • write permissions
  • whether contribution requires prior issue/discussion

If context cannot be established → STOP.


B. Locate and Read Repository Policies

Locate core contributing docs:

  1. CONTRIBUTING.md
  2. CODE_OF_CONDUCT.md
  3. SECURITY.md

Search for them in these directories, in order:

  1. / - i.e., root
  2. /.github
  3. /docs

Not all repositories contain these documents.

  1. PR templates:

- /.github/PULL_REQUEST_TEMPLATE.md - /.github/PULL_REQUEST_TEMPLATE/

  1. Issue templates:

- /.github/ISSUE_TEMPLATE/

Read all relevant files fully.


C. Produce an Internal Policy Summary

Before proceeding, internally summarize all explicitly defined repository policies:

  • Required workflow (issue-first? discussion-first?)
  • Branching model expectations (e.g. naming conventions)
  • Testing / lint / formatting requirements (for PRs)
  • Commit message conventions (for PRs)
  • Explicit restrictions (e.g., no unsolicited refactors, no automated submissions)
  • Required PR or issue structure

If this summary cannot be produced → STOP.


D. Search for Existing Work

Before opening a new issue or PR:

  1. Search open and closed:

- Issues - PRs - Discussions

  1. If a related thread exists:

- Contribute there instead of creating a duplicate. - Do not fragment discussion.

If adequate search cannot be performed → STOP.


2. Template & Information Enforcement

Checklist Compliance

If an issue or PR template includes required checkboxes:

  • Perform each required action before marking it complete.
  • Do not mark items unless actually satisfied.
  • Do not remove required checklist items.

If any required action cannot be completed → STOP.


Required Information Compliance

If a template requires specific information (e.g., OS, version, reproduction steps, logs, environment):

  • Provide all required fields.
  • Ensure reproduction steps are concrete and testable.
  • Do not leave required sections blank.

If required information cannot be supplied → STOP.


3. Scope & Change Discipline

  • One purpose per PR.
  • No unrelated formatting or refactors.
  • No drive-by changes.
  • Follow repository formatting and style rules.
  • Update documentation or changelog if required.

If required quality gates (tests/lint/build) cannot be verified → STOP.


4. Relaxed Interaction Pacing

When performing multiple outward actions (e.g., several comments or issues):

  • Wait at least 5 minutes between interactions.
  • Avoid burst behavior.
  • Default to slower pacing if uncertainty exists.

Do not generate high-frequency comment sequences.

Bursty activity is:

(a) highly indicative of automation;

(b) may violate GitHub's rate limit policies. These violations can result in severe penalties for the user.


5. Respect Repository Authority

If maintainers:

  • Close an issue or PR,
  • Reject a proposal,
  • Request changes,
  • Request no further automated interaction,

Then:

  • Comply immediately.
  • Do not escalate.
  • Do not repost the same content.
  • Do not bypass stated policy.

6. Stop Conditions

Do NOT proceed if:

  • Policies are missing or ambiguous.
  • Security-sensitive code is involved.
  • Explicit anti-bot/automation policy exists.
  • Required checks/tests cannot be run.
  • Required template information cannot be provided.

When uncertain, choose the action that minimizes disruption.


7. Policy Basis & Consequences

This protocol is grounded in repository-defined contribution policies and GitHub platform rules. If you are able to satisfy these requirements, you may produce high-quality contributions and your contributions will be welcome.

Failure to follow repository policies may result in:

  • Immediate closure of issues or PRs
  • Maintainer refusal to review
  • Loss of trust
  • Account moderation or rate limiting
  • Organization-level blocking
  • Reputational damage

This skill exists to ensure compliance with repository governance and to prevent disruptive or low-quality interaction that could have undesirable repercussions. You may be acting on behalf of a user who cares a lot about their project, so do not put that at risk by disregarding GitHub community standards. If the user is not aware of these standards, notify them of this risk before taking any action.

平台分布

OpenClaw

75.68%
按下载量换算860

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills