GitHub MCP

Monitor CI/CD workflows after every `git push` using GitHub MCP.

11 stars

Best use case

GitHub MCP is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Monitor CI/CD workflows after every `git push` using GitHub MCP.

Teams using GitHub MCP should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/github-mcp/SKILL.md --create-dirs "https://raw.githubusercontent.com/hivellm/rulebook/main/templates/skills/modules/github-mcp/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/github-mcp/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How GitHub MCP Compares

Feature / AgentGitHub MCPStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Monitor CI/CD workflows after every `git push` using GitHub MCP.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

<!-- GITHUB_MCP:START -->
# GitHub MCP Server Integration

**CRITICAL**: Monitor CI/CD workflows after every `git push` using GitHub MCP.

## Workflow After Push

```
1. Push changes
2. Wait 10 seconds  
3. Check workflow status via GitHub MCP
4. If workflows running → check again in next interaction
5. If workflows failed → fetch logs, analyze, fix
6. If workflows passed → confirm to user
```

## Error Recovery

**When CI/CD fails:**

```
1. Fetch error information (workflow, job, step, logs)
2. Analyze against AGENTS.md standards
3. Propose fix
4. Implement fix with full quality checks
5. Commit and provide push command
6. Monitor workflows again
```

## Best Practices

✅ **DO:**
- Always check workflows after push
- Fetch complete error logs on failures
- Fix issues before next feature
- Verify fixes locally before re-pushing
- Report status to user

❌ **DON'T:**
- Ignore workflow failures
- Push again without fixing
- Skip error analysis
- Proceed if workflows failing
- Create tags if CI/CD failed

## Configuration

```json
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}
```

**Token permissions:** Repository (read), Actions (read), Workflows (read/write)

<!-- GITHUB_MCP:END -->