debug

Helps a human actually learn something — a concept, a codebase, a paper, a topic — using an evidence-based active-learning loop (retrieval practice…

Refactor a codebase using Clean Architecture and Clean Code principles — fix dependency violations, separate concerns, improve code quality, push…

Writes or revises an agent skill — SKILL.md plus reference files — targeting what the model gets wrong rather than restating what it already knows.

Audit GitHub Actions workflows for security issues — dangerous triggers, script injection, unpinned actions, over-permissioned tokens, secret leaks, unsafe…

Strip LLM writing tics from prose so it reads like a person wrote it.

Audit prod dependencies and fix vulnerabilities by tracing to root parents, using recursive updates, parent bumps, or replacements

Workflow for surfacing a task's unknowns before, during, and after implementation — blind spot pass, brainstorm/prototype, interview, references…

Comprehensive code review combining quality, security, and maintainability checks.

Run a comprehensive security audit on a macOS system.

Generates Mermaid.js architecture diagrams for modules and services.

Show a rich feed of the user's active open pull requests across all GitHub repos — links, review status, CI, comments, and latest activity.

Complexity check that forces justification for complex solutions.