modules/programs/agents/shared/skills/fix-pr/SKILL.md
Autonomously fix a pull request by resolving relevant failing PR checks, then addressing PR comments and posting replies. Use when user says "fix pr", "prfix", "fix PR checks", "address PR feedback", or asks to clean up a PR end to end.
npx skillsauth add MichaelVessia/nixos-config fix-prInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Arguments: $ARGUMENTS (optional PR number or URL).
Execute this flow fully, stop only if blocked.
$ARGUMENTS has PR URL/number, use it.gh pr view.gh pr diff --name-only.gh pr view <PR> --json mergeable,mergeStateStatus.resolve-merge-conflicts with the PR number.gh pr view <PR> --json statusCheckRollup.gh run list and
details via gh run view --log-failed.Invoke address-pr-feedback to review and address all open PR comments. The
skill handles gathering comments, creating a todo list, implementing fixes,
running tests, and committing changes.
After address-pr-feedback completes, invoke gh-comment to post replies for
each processed comment. Include:
addressed or not addressed)Keep replies factual and brief.
Complete only when all are true:
gh-comment.If blocked (missing permissions, failing external service, ambiguous feedback), stop and report exact blocker plus next required user action.
development
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to nicobailon/visual-explainer.
development
Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.
development
Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.
testing
Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.