superpowers-mcp 6.0.3 → 6.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (37) hide show
  1. package/README.ja.md +15 -2
  2. package/README.ko.md +15 -2
  3. package/README.md +21 -2
  4. package/README.zh-TW.md +22 -3
  5. package/out/server.js +1 -1
  6. package/package.json +1 -1
  7. package/skills/brainstorming/SKILL.md +1 -9
  8. package/skills/brainstorming/scripts/stop-server.ps1 +11 -3
  9. package/skills/brainstorming/visual-companion.md +7 -0
  10. package/skills/dispatching-parallel-agents/SKILL.md +0 -18
  11. package/skills/executing-plans/SKILL.md +6 -12
  12. package/skills/finishing-a-development-branch/SKILL.md +64 -105
  13. package/skills/receiving-code-review/SKILL.md +0 -8
  14. package/skills/requesting-code-review/SKILL.md +6 -14
  15. package/skills/subagent-driven-development/SKILL.md +314 -228
  16. package/skills/subagent-driven-development/implementer-prompt.md +6 -3
  17. package/skills/subagent-driven-development/re-review-prompt.md +106 -0
  18. package/skills/subagent-driven-development/scripts/review-package +11 -9
  19. package/skills/subagent-driven-development/scripts/review-package.ps1 +17 -10
  20. package/skills/subagent-driven-development/scripts/sdd-workspace +26 -8
  21. package/skills/subagent-driven-development/scripts/sdd-workspace.ps1 +29 -4
  22. package/skills/subagent-driven-development/scripts/task-brief +4 -3
  23. package/skills/subagent-driven-development/scripts/task-brief.ps1 +5 -4
  24. package/skills/subagent-driven-development/task-reviewer-prompt.md +3 -5
  25. package/skills/systematic-debugging/SKILL.md +1 -14
  26. package/skills/systematic-debugging/find-polluter.ps1 +20 -4
  27. package/skills/test-driven-development/SKILL.md +10 -61
  28. package/skills/test-driven-development/writing-good-tests.md +198 -0
  29. package/skills/using-git-worktrees/SKILL.md +9 -44
  30. package/skills/using-superpowers/references/antigravity-tools.md +1 -1
  31. package/skills/using-superpowers/references/codex-tools.md +1 -1
  32. package/skills/using-superpowers/references/gemini-tools.md +44 -32
  33. package/skills/verification-before-completion/SKILL.md +0 -19
  34. package/skills/writing-plans/SKILL.md +0 -6
  35. package/skills/writing-skills/SKILL.md +1 -11
  36. package/skills/test-driven-development/testing-anti-patterns.md +0 -299
  37. package/skills/using-superpowers/references/copilot-tools.md +0 -42
@@ -5,7 +5,7 @@ description: Use when completing tasks, implementing major features, or before m
5
5
 
6
6
  # Requesting Code Review
7
7
 
8
- Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.
8
+ Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history.
9
9
 
10
10
  **Core principle:** Review early, review often.
11
11
 
@@ -72,20 +72,12 @@ You: [Fix progress indicators]
72
72
  [Continue to Task 3]
73
73
  ```
74
74
 
75
- ## Integration with Workflows
75
+ ## Common Rationalizations
76
76
 
77
- **Subagent-Driven Development:**
78
- - Review after EACH task
79
- - Catch issues before they compound
80
- - Fix before moving to next task
81
-
82
- **Executing Plans:**
83
- - Review after each task or at natural checkpoints
84
- - Get feedback, apply, continue
85
-
86
- **Ad-Hoc Development:**
87
- - Review before merge
88
- - Review when stuck
77
+ | Excuse | Reality |
78
+ |--------|---------|
79
+ | "I'll just review the diff myself instead of dispatching a reviewer" | You're the coordinator — reviewing the diff inline burns the context window you need to keep driving the work. Dispatch a reviewer subagent: the diff and the evaluation live in its context, and only the findings come back to you. |
80
+ | "The reviewer needs my whole session history to understand the change" | Hand it precisely crafted context, never your session's history. That keeps the reviewer on the work product, not your thought process. |
89
81
 
90
82
  ## Red Flags
91
83