SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
crucible
Orchestrates an end-to-end development pipeline: interactive design, planning, autonomous execution, and quality gates with TDD and iterative reviews.
my-cc-harness
Guides an agent through the TDD cycle: write a failing test, implement minimal code to pass, then refactor. Useful for disciplined feature development and maint
tdg
Guides agents through a TDD (Red-Green-Refactor) workflow: detect project test setup, generate tests, and iterate to implement and refactor code.
agent-skills
Automates migration guidance from Jest/Vitest to Rstest: translate configs, update APIs, and provide minimal-change patches to make tests run under Rstest.
alfred-dev
Read and map a repository before making changes: discover structure, config, tests, patterns, and dependencies to avoid breaking conventions when modifying code
claude-skill-registry
Run multi-language quality gates (lint, format, type check, tests) across a codebase to validate changes before PRs or release.
ryanb/dotfiles
Guided interactive rebase skill: rebases the current branch onto a base branch, helps resolve conflicts, runs related tests, and compares the result to the remo
reviw
Toolkit for backend API testing with proper test frameworks (vitest/jest, go test, pytest, cargo test). Supports verifying API endpoints, database state changes
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
dotclaude
Runs Prisma generate, lint (with auto-fix), typecheck and tests in sequence and applies minimal safe fixes until the repo is clean.
ryanb/dotfiles
Run the project's review tool (`bin/claude-review --print`), report the findings, and iteratively apply fixes, committing each change individually.
