AgentStack
SKILL verified MIT Self-run

Github Researcher

skill-allenli178-yuyan-skills-github-researcher · by allenli178

GitHub项目搜索和分析Skill,根据评估维度搜索GitHub上的候选项目,并获取每个项目的关键指标。

No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-allenli178-yuyan-skills-github-researcher

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Github Researcher? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

GitHub项目搜索和分析Skill

1. Goal (目标)

根据评估维度搜索GitHub上的候选项目,并获取每个项目的关键指标,为技术选型评估提供数据支持。

2. Input Format (输入格式)

{
  "must_haves": ["[必选功能1]", "[必选功能2]"],
  "weights": {"[评估维度1]": [权重值], "[评估维度2]": [权重值]},
  "search_terms": ["[搜索关键词1]", "[搜索关键词2]"]
}

3. Output Format (输出格式)

  • 候选项目列表:每个项目包含以下信息
  • 项目名称
  • 项目URL
  • 关键指标(stars、forks、openissues、lastpush、license、recentcommits6m、language、archived)
  • 初步评估结果

4. Workflow (工作流)

  1. 根据搜索关键词和评估维度搜索GitHub项目
  2. 对每个项目运行 fetchrepostats.py 获取量化指标
  3. 过滤掉 archived=True 或 recentcommits6m < 10 的项目
  4. 对每个项目进行初步评估
  5. 生成候选项目列表

5. Output Template (输出模板)

[
  {
    "name": "[项目名称]",
    "url": "[项目URL]",
    "stats": {
      "stars": [stars数量],
      "forks": [forks数量],
      "open_issues": [open_issues数量],
      "last_push": "[最后推送时间]",
      "license": "[许可证]",
      "recent_commits_6m": [最近6个月commit数],
      "language": "[主要语言]",
      "archived": [是否归档]
    },
    "evaluation": {
      "meets_requirements": [是否满足需求],
      "initial_score": [初步评分]
    }
  }
]

6. Self-Correction (自我纠错)

  • 验证GitHub API调用是否成功
  • 检查返回的项目数据是否完整
  • 确保过滤条件正确应用
  • 验证初步评估结果的合理性

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.