SureForge
SkillAn instruction-only skill that makes agents research before they ask, plan before they build, and verify before they call anything done.
- workflow
- verification
- quality
- skill
Anthropic's official GitHub Action that runs Claude Code in CI.
Adds a `@claude` mention to your GitHub workflow so Claude Code can review diffs, fix CI failures, and answer questions in issues and pull requests.
Best for maintainers who want a codebase-aware review bot on every PR, and for teams automating triage (label an issue and let Claude take a first pass). The shared, auditable surface for collaborators who don't have Claude Code locally.
Create .github/workflows/claude.yml:
name: Claude Code
on:
issue_comment:
types: [created]
jobs:
claude:
uses: anthropics/claude-code-action@v1
with:
anthropic_token: ${{ secrets.ANTHROPIC_API_KEY }}
Then mention @claude in any issue or PR.Every @claude run consumes API tokens — cap it with the action's turn/budget inputs for cost control. The workflow's GITHUB_TOKEN scope is what Claude can do; grant contents:write only when pushes are needed. Issue and PR text is untrusted input routed to a model with repo access — keep that in mind on public repos.
Repository
anthropics/claude-code-actionCharted
An instruction-only skill that makes agents research before they ask, plan before they build, and verify before they call anything done.
Guizang's agent skill turns your repo's recent updates into a finished promo video — real components, code-rendered animation, an original code-written soundtrack — no video editor involved.
An agent skill that geolocates a photo with nothing readable in it — OSM geometry, elevation skylines and satellite tiles turn “where was this taken?” into a measured answer with an error radius.