
Clarify intent, requirements, and solution direction before any creative implementation work.
Create, revise, and validate AI skills before deployment.
Implement features and fixes by writing tests before production code.
Turn requirements into a clear step-by-step execution plan before implementation.
Execute implementation plans by splitting and advancing independent tasks in-session.
Helps decide merge, PR, or cleanup steps after branch work is complete.
Systematically investigate bugs, test failures, and unexpected behavior before fixing.
Create isolated workspaces for feature development without disturbing current code.
Set conversation rules to discover and invoke skills before replying.
Verify results before claiming work is complete, fixed, or passing.
Privately journal thoughts and quickly retrieve insights with semantic search.
Learn core Skills workflows, search patterns, and brainstorming use cases quickly.
Replace fixed delays with condition polling for more reliable async tests.
Design layered validation across data flows to prevent bugs and security issues.
Iteratively test process documentation to find gaps and refine instructions.
Name code by domain meaning to improve clarity and team alignment.
Write evergreen comments focused on what and why, not historical context.
Trace bugs backward through call stacks to find the original trigger.
Helps developers write code comments explaining intent, rationale, and key tradeoffs.
Dispatch multiple agents in parallel to investigate and fix independent issues.
Helps developers finish a branch with merge, PR, or cleanup workflows.
Execute implementation plans with task-specific subagents and code review checkpoints.
Trigger a code review against plans or requirements before moving forward.
Create isolated Git worktrees safely with smart directory selection.
Debug issues with a four-phase method that finds root causes before fixes.
Create process documentation with test-driven validation before finalizing the draft.
Use test-first development to improve code quality and maintainability.
Helps users reduce software complexity for better maintainability and delivery speed.
Helps you spot multi-purpose routines and refactor them into single-responsibility units.
Help developers limit variable scope to improve code clarity and maintainability.
Validate external inputs to prevent errors, failures, and security issues.
Helps developers handle code review feedback with rigor, judgment, and effective responses.
Run verification checks before completion to ensure results are truly correct.
Check a skills wiki for links, naming, cross-references, and coverage gaps.
Helps developers avoid common testing anti-patterns and write more reliable tests.
Improve code clarity and maintainability by assigning each variable one purpose.
Execute detailed plans in batches with review checkpoints and course correction.
Help developers simplify nested conditionals for clearer, more maintainable code.
Choose clear, accurate variable names that improve code readability and maintenance.
Compare 2-3 approaches before execution to choose a stronger solution.
Plan with pseudocode first, refine approaches, then translate into working code.
Search past Claude Code chats to recover facts, decisions, and context.
Design systems by hiding implementation details behind domain-level interfaces.
Helps developers keep class abstractions cohesive and free of unrelated responsibilities.
Create step-by-step implementation plans for engineers new to a codebase.
Build, update, test, and release Claude Code plugins efficiently end to end.
Audit codebases to find semantically duplicate functions with different names or implementations.
Rewrite reader-facing text to be clearer, tighter, and more professional.
Search past conversations before answering to recover context and avoid wrong assumptions.
Get official guidance for Claude Code CLI, MCP, plugins, and configuration.
Run interactive CLI sessions safely via tmux for editors, REPLs, and Git flows.
Use MCP services on demand via CLI without preloading extra context.
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
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Refactor with tests first, one change at a time, never mix refactoring with bug fixes or new features
Interactive idea refinement using Socratic method to develop fully-formed designs
Fork, clone to ~/.clank, run installer, edit CLAUDE.md