skills

Generate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks. Use when a repository needs clear agent onboarding covering structure, tooling, testing, task flow, README expectations, and conventional commit summaries.

Generate Bash 3.2-compatible scripts with a standardized check_requirements guardrail, friendly validation errors, and optional shfmt formatting. Use when writing or updating bash scripts that need consistent argument validation, dependency checks, and portability.

Update Homebrew formula files with latest GitHub release URLs and SHA256 checksums. This skill should be used when the user wants to update a Homebrew tap formula (.rb file) with a new version from a GitHub release. Triggers on phrases like "update formula", "update homebrew", "new release", "bump version", or when pointing to a .rb formula file that needs version updates.

Interactive release readiness checklist with semantic versioning guidance. Use when preparing a software release, cutting a version, deploying to production, or when user asks about release preparation. Triggers on phrases like "prepare release", "release checklist", "ready to release", "cut a version", "version bump", or "/release-readiness-checklist".

Use when executing implementation plans phase-by-phase with strict enforcement of quality gates, tests, and Definition of Done. Triggers on "build this plan", "execute plan", "implement phases", or when user provides a plan document to execute.

Weekly codebase hygiene skill that identifies and fixes AI-generated code problems ("slop") using Martin Fowler's refactoring techniques. Scans for 15 common issues, prioritizes by severity, and generates superplan-compatible plans for systematic improvement.

Generates a docs/ directory of markdown files giving AI and humans deep context on WHAT a codebase is, HOW it works, and WHY decisions were made. Scans any codebase, produces structured documentation. Re-runnable — detects existing docs, monorepos, and git-based staleness. Runs automatically without user interaction.

Use when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with parallelizable phases, poker estimates, TDD-first acceptance criteria, and quality gates. Detects tech stack from CLAUDE.md/AGENTS.md (bypassing internet research if complete) or via codebase scan.

Transforms technical documents into rigorous learning journeys with collegiate-level mastery requirements. Uses Bloom's taxonomy progression, 80%+ mastery thresholds, and multi-level verification before advancing. Treats learning as a high school to college graduation progression. Use when user wants deep understanding, not surface familiarity.