Agent Skills Hub

format

Verify code style and formatting using Prettier and Stylelint without applying changes. Ensures consistent codebases by identifying issues in JS/TS/CSS/SCSS files.

dod

Definition of Done (DoD) verification workflow that triggers automatically upon implementation completion to ensure quality, document evidence, and standardize reporting.

python-plan-optimization

6-phase read-only Python analysis workflow that identifies design principle violations, code smells, and modernization opportunities based on specific project types (POC to Open Source).

implement-type-annotations

Automates the integration of Python and TypeScript type hints to enhance IDE intellisense, error detection, and AI code comprehension.

mutation-testing-js

Mutation testing patterns for JS/TS using Stryker. Analyze branch code to find weak or missing tests, verify test effectiveness, and strengthen Node.js test suites.

using-superpowers

The foundational skill for the Superpowers methodology. Ensures agents correctly identify and invoke required development skills before starting any task or conversation.

awb

Interactive UI components for Claude Code and AI agents. Create confirmations, checklists, inputs, tables, and views to handle non-blocking interactions and monitoring.

skill-from-github

Create high-performance AI skills by reverse-engineering successful GitHub projects and proven open-source methodologies.

quality-fixer

Automatically apply safe quality fixes including formatting (Black, isort), linting (Ruff auto-fixes), and resolving formatter conflicts to maintain Python code quality.

commit-safe

A secure Git commit workflow agent that prevents accidental mass commits and promotes surgical, file-specific staging and semantic commits.

tldr

Token-efficient codebase analysis skill for call graphs, semantic search, impact analysis, and data flow. Saves ~95% tokens vs. raw reads.

swift-review

Expert Swift code review for macOS/iOS. Detects memory leaks, threading bugs, concurrency issues, and accessibility gaps using parallel analysis agents.