Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
claude-code-action
No description provided.
8kstars
1.9kforks
TypeScript
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
GitHub Action that lets Claude Code run directly in CI pipelines to review, debug, or generate code automatically.
Use this when
- Your CI pipeline needs AI-powered code review before merging
- You want to auto-generate tests or docs from code changes
- You need AI to debug failing builds or tests
- You're running nightly code quality scans
- You want to enforce coding standards with AI feedback
Don't use when
- You need human-only code review
- Your workflows run in air-gapped environments without internet
- You require deterministic outputs for compliance reasons
Capabilities
- Runs Claude Code in GitHub Actions workflows
- Reviews pull requests for bugs, style issues, or security flaws
- Generates unit tests or documentation from code changes
- Debugs failing CI jobs by analyzing logs and code
- Supports custom prompts for tailored AI feedback
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest anthropics/claude-code-actionAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/claude-code-action curl -fsSL https://raw.githubusercontent.com/anthropics/claude-code-action/main/SKILL.md -o ~/.claude/skills/claude-code-action/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
claude-code-action — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt