Skill3.8k estrellas del repoactualizado 4mo ago

github-search

This Claude Code skill searches GitHub for code snippets, repositories, issues, and pull requests using customizable search parameters. Use it when you need to locate specific code implementations, find repositories matching criteria, identify open issues or PRs, or gather repository information across GitHub's public and accessible private repositories.

Ver fuente Repositorio: Continuous-Claude-v3

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3 /tmp/github-search && cp -r /tmp/github-search/.claude/skills/github-search ~/.claude/skills/github-search

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# GitHub Search Skill

## When to Use

- Search code across repositories
- Find issues or PRs
- Look up repository information

## Instructions

```bash
uv run python -m runtime.harness scripts/mcp/github_search.py \
    --type "code" \
    --query "your search query"
```

### Parameters

- `--type`: Search type - `code`, `repos`, `issues`, `prs`
- `--query`: Search query (supports GitHub search syntax)
- `--owner`: (optional) Filter by repo owner
- `--repo`: (optional) Filter by repo name

### Examples

```bash
# Search code
uv run python -m runtime.harness scripts/mcp/github_search.py \
    --type "code" \
    --query "authentication language:python"

# Search issues
uv run python -m runtime.harness scripts/mcp/github_search.py \
    --type "issues" \
    --query "bug label:critical" \
    --owner "anthropics"
```

## MCP Server Required

Requires `github` server in mcp_config.json with GITHUB_PERSONAL_ACCESS_TOKEN.

Del mismo repositorio

aegisSubagent

Security vulnerability analysis and testing

agentica-agentSubagent

Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration

arbiterSubagent

Unit and integration test execution and validation

architectSubagent

Feature planning, design documentation, AND integration planning

atlasSubagent

End-to-end and acceptance test execution

braintrust-analystSubagent