Skip to main content
ClaudeWave

Claude Code Skills · page 136

Individual Claude Code skills mined from every repository in the directory: each SKILL.md, installable with one command, with its full definition and the repository's trust signals.

13,545 skills1-command install
  1. Start a new milestone cycle — update PROJECT.md and route to requirements

  2. Initialize a new project with deep context gathering and PROJECT.md

  3. Create an isolated workspace with repo copies and independent .planning/

  4. Automatically advance to the next logical step in the MindForge workflow

  5. Zero-friction idea capture. Append, list, or promote notes to todos.

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

  7. Create context handoff when pausing work mid-phase

  8. Create phases to close all gaps identified by milestone audit

  9. Create detailed phase plan (PLAN.md) with verification loop

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

  11. Capture a forward-looking idea with trigger conditions — surfaces automatically at the right milestone

  12. Create a clean PR branch by filtering out .planning/ commits — ready for code review

  13. Generate developer behavioral profile and create Claude-discoverable artifacts

  14. Check project progress, show context, and route to next action (execute or plan)

  15. Execute a quick task with MindForge guarantees (atomic commits, state tracking) but skip optional agents

  16. Reapply local modifications after a MindForge update

  17. Remove a future phase from roadmap and renumber subsequent phases

  18. Remove a MindForge workspace and clean up worktrees

  19. Research how to implement a phase (standalone - usually use /mindforge-plan-phase instead)

  20. Resume work from previous session with full context restoration

  21. Review and promote backlog items to active milestone

  22. 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

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

  24. Request cross-AI peer review of phase plans from external AI CLIs

  25. Generate a session report with token usage estimates, work summary, and outcomes

  26. Switch model profile for MindForge agents (quality/balanced/budget/inherit)

  27. Configure MindForge workflow toggles and model profile

  28. Create PR, run review, and prepare for merge after verification passes

  29. 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

  30. Use when creating new skills, editing existing skills, or verifying skills work before deployment

  31. Display project statistics — phases, plans, requirements, git metrics, and timeline

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

  33. Design systems with appropriate complexity - no more, no less. Use when the user asks to architect applications, design system boundaries, plan service decomposition, evaluate monolith vs microservices, make scaling decisions, or review structural trade-offs. Applies to new system design, refactoring, and migration planning.

  34. Strict TDD workflow (Red-Green-Refactor).

  35. Use when implementing any feature or bugfix, before writing implementation code

  36. Manage persistent context threads for cross-session work

  37. Generate UI design contract (UI-SPEC.md) for frontend phases

  38. Retroactive 6-pillar visual audit of implemented frontend code

  39. Update MindForge to latest version with changelog display

  40. Retroactively audit and fill Nyquist validation gaps for a completed phase

  41. Validate built features through conversational UAT

  42. 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

  43. 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

  44. Manage parallel workstreams — list, create, switch, status, progress, complete, and resume

  45. Publish a skill to the npm registry (or private registry).