Stats
Actions
Tags
From ralph-starter
Fetches GitHub issues or PRs, previews specs, and implements them autonomously with ralph-starter. Automates building, committing, PRs, and batch processing multiple issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ralph-starter:ralph-githubThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Fetch specs from GitHub issues or PRs and run an autonomous coding loop to implement them.
Fetch specs from GitHub issues or PRs and run an autonomous coding loop to implement them.
Use ralph_fetch_spec with source: "github" to preview the issue/PR:
identifier: repo URL, "owner/repo#123", or issue URLproject to filter by repo, label to filter by labelUse ralph_run to build from the spec:
from: "github" and provide project (owner/repo)label (e.g., "good first issue", "bug")auto: true, commit: true, validate: true for full automationFor batch processing multiple issues, use ralph_run with auto: true — each issue gets its own branch and PR.
npx claudepluginhub multivmlabs/ralph-starter --plugin ralph-starterRuns autonomous AI coding loop with ralph-starter: checks project state, implements tasks from specs/GitHub/Linear/Notion/Figma issues, iterates code writing/validation/commits.
Resolves GitHub issues via 8-phase workflow: fetch details, analyze requirements, implement solutions, verify correctness, code review, commit changes, create PRs. Activates on resolve, implement, fix requests or issue references.
Investigates GitHub issues and PRs: pulls, classifies, searches codebase for root cause, reviews contributed code, proposes fixes with file:line references, and optionally implements fixes.