subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
finding-dead-code
>
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans
using-lsp-tools
Use when mcp-language-server tools are available and you need semantic code intelligence for navigation, refactoring, or type analysis
using-skills
Use when starting any conversation to establish skill discovery patterns
worktree-merge
Use when merging parallel worktrees back together after parallel implementation with interface contracts
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
instruction-optimizer
Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability
implementation-plan-reviewer
Use when reviewing implementation plans before execution, especially plans derived from design documents
debugging
Use when debugging bugs, test failures, or unexpected behavior. Supports --scientific and --systematic flags for direct methodology selection.
fact-checking
>
subagent-prompting
>
instruction-engineering
Use when: (1) constructing prompts for subagents, (2) invoking the Task tool, or (3) writing/improving skill instructions or any LLM prompts for maximum effectiveness
implementing-features
|
fixing-tests
Use when tests are failing, test quality issues were identified, or user wants to fix/improve specific tests
brainstorming
Use before any creative work - creating features, building components, adding functionality, or modifying behavior
nim-pr-guide
>
merge-conflict-resolution
Use when git merge or rebase fails with conflicts, you see 'unmerged paths' or conflict markers (<<<<<<< =======), or need help resolving conflicted files
fun-mode
Use when starting a session and wanting creative engagement, or when user says '/fun' or asks for a persona
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work (merge, PR, or cleanup)
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
devils-advocate
Use before design phase to challenge assumptions, scope, architecture, and design decisions in understanding documents or design docs
emotional-stakes
Use when writing subagent prompts, skill instructions, or any high-stakes task requiring accuracy and truthfulness
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable
async-await-patterns
Use when writing JavaScript or TypeScript code with asynchronous operations
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
design-doc-reviewer
Use when reviewing design documents, technical specifications, or architecture docs before implementation planning
green-mirage-audit
Use when reviewing test suites, after test runs pass, or when user asks about test quality