Workflow

Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.

Superpowers is a complete software development workflow library for AI coding assistants. It provides structured skills for test-driven development, systematic debugging, brainstorming, implementation planning, code review, and subagent-driven development. The skills enforce disciplined practices through mandatory workflows and integrate with Claude Code, OpenCode, and Codex platforms.

This skill provides a PreToolUse hook that tracks how many Edit/Write operations you've made and suggests running /compact at strategic points (default: every 50 calls, then every 25 after). It helps preserve important context by suggesting compaction at logical workflow boundaries rather than relying on arbitrary auto-compaction.

Continuous Learning v2 is an advanced learning system that observes your Claude Code sessions through hooks, capturing tool usage patterns. It creates atomic 'instincts' with confidence scoring that can evolve into reusable skills, commands, and agents. The system learns your preferences and workflows to make Claude more personalized over time.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

A comprehensive guide for implementing saga patterns in distributed systems. Provides Python templates for orchestration-based and choreography-based sagas, including order fulfillment workflows, compensation handling, and timeout management.

A comprehensive testing guide for Temporal Python workflows. Covers unit testing with time-skipping, integration testing with mocked activities, replay testing for determinism validation, and local development setup with Docker Compose and pytest configuration.

A comprehensive reference guide for designing durable workflows with Temporal. Covers workflow vs activity separation, saga patterns for distributed transactions, state management, determinism constraints, and best practices for building reliable long-running processes and microservice orchestration.

A comprehensive guide to mastering advanced Git techniques including interactive rebasing, cherry-picking commits across branches, using git bisect to find bugs, managing multiple worktrees for parallel development, and recovering from mistakes with reflog. Helps developers maintain clean commit history and collaborate effectively.

Conductor is a Context-Driven Development plugin that organizes software projects through structured documentation and workflows. It creates and maintains product vision, tech stack, and workflow artifacts while guiding implementation through specification-first, TDD-based development with git-aware progress tracking and semantic reversion capabilities.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when executing implementation plans with independent tasks in the current session

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Planning with Files implements the Manus-style context engineering pattern, creating task_plan.md, findings.md, and progress.md files to serve as persistent 'working memory on disk'. It helps manage complex multi-step tasks by tracking phases, storing research findings, logging progress, and recovering context across sessions. The skill supports 10+ AI coding assistants including Claude Code, Cursor, Gemini CLI, and Kiro.

This skill provides a unified interface for managing Git worktrees, enabling isolated parallel development. It handles creating worktrees from branches, listing active worktrees, switching between them, and cleaning up completed work, with automatic .env file copying to ensure environment consistency across worktrees.

This skill provides a structured file-based todo tracking system for managing code review feedback, technical debt, and feature requests. Each todo is a markdown file with YAML frontmatter stored in a todos/ directory, supporting workflows for creation, triage, dependency tracking, and completion.

A brainstorming workflow skill that helps users clarify what to build before planning implementation. It guides exploration of requirements, proposes approaches with trade-offs, and captures key decisions in structured markdown documents.

Hookify lets you create custom hooks that warn or block specific behaviors in Claude Code. Define rules in markdown files with regex patterns to catch dangerous commands, debug code, or enforce workflows - no complex configuration needed.

Ralph Loop implements continuous self-referential AI loops for interactive iterative development. It uses a stop hook to repeatedly feed the same prompt, allowing Claude to see and improve upon its previous work until completion criteria are met.

Feature Development provides a structured 7-phase workflow for building new features: discover requirements, explore the codebase with specialized agents, clarify ambiguities, design architecture, implement with approval, review quality, and summarize results. Uses code-explorer, code-architect, and code-reviewer agents in parallel for thorough analysis.

Automates common git operations with three commands: /commit for smart commits, /commit-push-pr for complete PR workflows, and /clean_gone for branch cleanup. Integrates with GitHub CLI for PR creation.

This skill helps ensure requirements are properly understood before implementation begins. It provides a structured workflow for identifying when requests are underspecified, asking targeted clarifying questions (1-5 at a time), and confirming interpretation before proceeding with work. Useful for avoiding wasted effort on misunderstood requirements.