
Generate granular conventional commits from staged changes
Find all commits made by the current git user that touched a given path, formatted for a brag/perf-review doc
Generate a post-implementation QA handoff comment for a completed backend feature. Use this skill whenever a developer has finished implementing backend work and needs to write a comment to post on the ClickUp card to inform QA of what was built and what to verify. Trigger when the user says things like "write a QA comment", "write the comment for this card", "post-implementation comment", "handoff to QA", "write a ClickUp comment", "help me document what I did for QA", or "write a ticket description for this backend change". Also trigger when the user says "write the description for this subtask" or "write a card comment" after finishing implementation. Reads the relevant source files to understand what was built and produces a concise developer-to-QA handoff note.
Implement UI components from Figma designs using semantic HTML, Tailwind 4, and tailwind-variants (tv()) following project conventions
Perform a HIPAA Security Rule compliance audit on a healthcare codebase. Use this skill whenever the user asks for a HIPAA audit, PHI compliance review, security review of a healthcare app, production readiness check of a patient-facing system, or wants to find where protected health information is exposed or mishandled. Also trigger when the user asks about ePHI risks, BAA coverage, audit trail gaps, or access control issues in medical software. Do not wait for the user to say "HIPAA" explicitly — trigger whenever the codebase clearly handles patient data and a security or compliance concern is raised.
Use this skill whenever the user wants to write, refine, or break down a subtask for a software ticket — especially backend endpoints, frontend components, or API integrations. Trigger when the user shares a user story, acceptance criteria, or ticket scope and asks for a subtask, refinement card, or implementation breakdown. Also trigger when the user says things like "help me refine this", "write a subtask for X", "break this down", or "create a card for the endpoint / component / feature". This skill produces structured, audience-appropriate subtask write-ups for developers, PMs, and QAs alike.
Show a Claude Code usage report — model token breakdown, estimated costs, top projects, and session patterns. Delegates to the stats-analyzer subagent (Haiku) to avoid polluting the main context with raw data.
Writes React components without unnecessary useEffect. Use when creating/reviewing React components, refactoring effects, or when code uses useEffect to transform data or handle events.
Cleans up .claude/settings.local.json or settings.json by generalizing overly-specific Bash permission rules, removing hardcoded paths, ensuring Read(./**) is present, and flagging write-capable commands. Use this skill whenever the user asks to clean up, tidy, fix, or simplify their Claude Code permissions or settings file, or when settings.local.json has accumulated specific paths or one-off commands that should be generalized.
Run the full quality pipeline (type-check, linting, tests) via the quality-checker subagent. Returns a concise summary of issues without flooding the main context with raw output.