Audit Claude Code agent definitions for craft quality: delegation triggers, tool and model fit, context economy, reliability contracts. Reviews the agent .md files themselves, not the overall setup.
Run the cc-staff-reviewer over my Claude Code setup (user + project scope)
Walk open CodeRabbit review threads on a GitHub PR, investigate each in the code, then either fix it or reply to @coderabbitai explaining why it stays. Resolves each thread it handles. Stops before commit.
Interact with Jira via acli. Create, update, view, transition, and comment on issues. Defaults to the SER project and produces descriptions that both product and engineering can follow, in proper ADF (Atlassian Document Format).
Generate the PR description from the current branch and open the PR (GitHub) or MR (GitLab), returning the URL
Recommend which skills from the catalog to add to the current project, matched to its tech stack and needs. Use when the user asks which skills to add, wants skills recommended for this repo or codebase, is discovering relevant skills, or is setting up a project. Excludes skills already installed globally and dependency-only skills.
Stage changes, split the diff into atomic concerns when it makes sense, and write one strict conventional commit per concern. Stops at commit; does not push.
Analyzes Claude Code usage patterns and provides comprehensive recommendations. Runs usage analysis, discovers GitHub community resources, suggests CLAUDE.md improvements, and fetches latest docs on-demand. Use when user wants to optimize their Claude Code workflow, create configurations (agents/skills/commands), or set up project documentation.