Agent Skills

Mutant (mutation testing)

mutant

Run Mutant mutation testing, analyze alive mutations, and produce clear fix actions (add tests or simplify code).

Code Spec Backfill

liza

Identify missing function-level contracts and backfill docstrings and type annotations; report ambiguous gaps with misuse scenarios. Incremental, state-driven w

zigts Expert (Zigttp)

zigttp

Author, verify, and fix zigts (restricted TypeScript) handlers for the zigttp runtime using a compiler-in-the-loop workflow and JSON diagnostics.

Language‑Agnostic Coding Principles

claude-code-workflows

Opinionated, language-agnostic principles for writing maintainable, readable, and secure code — use when implementing features, refactoring, or reviewing code q

TDD (Test-Driven Development) Skill

dotfiles

Guides an agent through a strict red–green–refactor TDD cycle: write a failing test, implement the minimal change, and refactor with verification.

spec-gen: Execute Refactor

spec-gen

Apply a confirmed refactoring plan safely: reads a refactor plan, applies changes as small, test-gated mini-developments, and stops on failures to avoid lost co

Project Setup & Workflows

dotnet-claude-kit

Interactive .NET project initialization, health checks, and migration workflows that generate tailored CLAUDE.md and run MCP-driven codebase analysis.

SOLID Generic — TypeScript / Bun / Node.js

agents

Opinionated SOLID-guidelines for TypeScript/Bun/Node projects: small files, separated interfaces, mandatory JSDoc, reuse-first workflow and templates to keep co

SwiftButler

swiftbutler

CLI to analyze, syntax-check, reindent, and split large Swift source files for easier inspection and tooling.

Issue Triage & PR Review

gsd-skill-creator

Autonomously triage GitHub issues, submit fixes as PRs, and perform adversarial PR reviews to find security and quality problems.

Fix-All Review Automation

ryanb/dotfiles

Run the project's review tool (`bin/claude-review --print`), report the findings, and iteratively apply fixes, committing each change individually.

Language-Agnostic Coding Principles

claude-code-workflows

Opinionated, language-agnostic principles and patterns to improve maintainability, readability, and robustness when implementing features, refactoring, or revie

Project Audit Rules

superclaude-plusplus

Run project-specific verification rules that check business logic, architecture patterns, and naming conventions beyond linters.

Code Quality Metrics Guide

dotfiles-claude

Practical guide to quantitative code-quality metrics (cyclomatic, cognitive, Halstead, maintainability index) with thresholds, formulas and measurement commands

Plan Tree Validator

aura-frog

Validates hierarchical plan trees against 8 invariants (parent/child integrity, no orphans, valid status, monotonic revisions, DAG acyclicity, etc.) and refuses

Kurtosis: Lint

Kurtosis

Lint and auto-format Kurtosis Starlark (.star) files; check syntax and validate docstrings to keep Starlark packages consistent and CI-friendly.

ESLint — JavaScript & TypeScript Linting

skills

Guides configuration and usage of ESLint 9+ (flat config) for JS/TS projects, including React and TypeScript plugin patterns and CI integration.

Code Review

openagentscontrol

Automated code review guidance focusing on security, correctness, and maintainability; used to validate changes before committing.

Metrics Report (codebase test & coverage analyzer)

ai-playground

Scans a repository, discovers and runs tests, computes coverage, evaluates test quality, and generates a metrics report website and JSON output.

Evolve — Goal-Driven Improvement Loop

boshu2

Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr

Project Hardening Audit

marvin-template

Autonomous project hardening audit: security, AI-specific risks, test coverage, code quality, and decoupling recommendations for repositories.

Code Quality Assurance

cc-best

Strategies and checklists for code quality: security reviews, systematic debugging, and code-health assessments to reduce technical debt and improve reliability

Reduce Max Lines

awesome-omni-skill

Generates a plan to reduce the maximum allowed lines per class or module, identifies violations, and produces refactoring tasks and config changes.

crap4clj — CRAP Metric for Clojure

crap4clj

Compute CRAP scores (cyclomatic complexity combined with coverage) for Clojure functions to flag high-risk, under-tested code.

Test-Driven Development (TDD)

grove

Defines a test-first workflow (red–green–refactor) for coding agents: write failing tests, implement minimal code to pass, then refactor with repeatable rules a

Code Evaluation Harness

my-cc-harness

Spawns an independent evaluator agent to score code outputs on functionality, code quality, originality, and usability/security, producing a structured EVAL_REP

Matrix Warnings

claude-matrix

Manage file and package warnings (add, remove, list, check) for a Matrix workflow; parse user arguments and call the matrix_warn tool to enforce repository-leve

Go Code Hygiene

agentclash

Run lightweight Go-specific checks (detect go.mod, run tests) after commits when Go code is present to catch regressions early.

Complexity Trend Tracker

skills

Analyzes codebase complexity (cyclomatic & cognitive) with lizard/radon and generates weekly reports attributing complexity changes per module.

LSP Extract Function

agent-lsp

Extract a selected block of code into a named function using LSP code actions when available, with a manual fallback that analyzes captured variables, return va