Agent skills for Claude Desktop

PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs.

Address PR review comments by implementing reviewer feedback and suggestions.

PR review coordinator who gathers comment context, acknowledges every

Context-efficient PR comment triage. Evaluate, decide, act. Fix important issues, resolve the rest silently.

Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes.

Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review…

Executes emergency hotfix workflows to safely push verified critical fixes directly to protected target branches.

Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through…

Research an upstream repo.

Deep code review agent that analyzes all diffs on the current branch for performance bottlenecks, security vulnerabilities, code quality…

Poll a PR for CodeRabbit review, apply fixes (up to 3 rounds), then merge.

Review GitHub pull requests for code quality, security, and best practices.

Use when reviewing a pull request for security issues — automatically analyzes the diff for vulnerabilities, hardcoded secrets, injection…

Generate a scaffolded sequence of practice problems with graduated difficulty and strategic variability.

Transforms rough feature ideas and brainstorms into structured, production-ready product requirement documents with integrated UI mockups…

Transforms vague requests into structured Product Requirement Documents with measurable acceptance criteria and clear scope boundaries.

Reviews PRDs and product requirement specs across PM, engineering, and QA perspectives to identify gaps, validate diagrams, and assess…

Take a PRD from docs/prd/ and draft an openspec change — proposal and specs artifacts — from it.

Executes automated dual-axis pre-commit code reviews, static security scans, baseline regression tests, and autonomous fix loops before…

Performs read-only impact analysis and symbol dependency mapping across your codebase before initiating code changes.

Run an evidence-backed, stack-agnostic security and abuse-resistance review before an application launch.