connect_kit

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

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

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Use after implementation complete to verify all tasks done, update roadmap, run full test suite, and create final report - ensures implementation completeness before finishing development branch

Use when specs/product/ is empty or incomplete to create mission.md, roadmap.md and tech-stack.md through incremental brainstorming and validation.

Use during Phase 2 of spec creation to gather detailed requirements through one-question-at-a-time dialogue - analyzes product context, asks targeted questions, requests visual assets, identifies reusability opportunities, and documents all findings

Use when the user is starting a project or wants to catch up on project progress - scans the specs/ folder, surfaces current status, proposes the next SDD phase, and routes to the appropriate workflow after confirmation.

Use when creating new spec or resuming incomplete spec - detects current phase, routes to appropriate phase skill (initialization, requirements, spec-writing, tasks-planning, verification), and manages phase transitions with validation checkpoints

Use when spec verified and ready for implementation to orchestrate development using isolated workspace and quality gates - sets up worktree, executes tasks via subagent-driven or sequential approach, verifies completion, and finishes development branch

Use at start of spec creation to initialize folder structure with dated naming and save raw feature idea - creates planning, implementation, and verification folders ready for subsequent phases

Use during Phase 5 of spec creation to verify completeness and accuracy before implementation - checks requirements accuracy, visual integration, reusability leverage, task specificity, and identifies over-engineering concerns

Use during Phase 3 of spec creation to create specification document - searches codebase for reusable patterns, presents spec in validated 150-200 word sections, and saves complete specification following template structure

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Use during Phase 4 of spec creation to break specification into organized task groups with dependencies - analyzes requirements to determine natural groupings, presents structure for validation, and creates detailed actionable tasks

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 starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge