$npx -y skills add heymegabyte/claude-skills --skill 20-superpowersUse when starting creative work, planning a multi-step task, isolating a workspace, wrapping a branch, or giving/getting code review. Not when the task is a one-line fix with no design surface.
| 1 | # Superpowers — Process Discipline |
| 2 | |
| 3 | Vendored from [obra/Superpowers](https://github.com/obra/Superpowers) (MIT, Jesse Vincent), compressed to house style — see `NOTICE.md`. These are **process skills**: they decide HOW to approach a task and run BEFORE implementation skills. On conflict, this repo's `01-operating-system` + `rules/*` + Brian's preferences win. |
| 4 | |
| 5 | ## The flow (route by where you are) |
| 6 | |
| 7 | 1. **Starting anything creative?** → `brainstorming/SKILL.md` — explore intent + design before code. Non-negotiable first step. |
| 8 | 2. **Have requirements, multi-step?** → `writing-plans/SKILL.md` — write the plan before touching code. |
| 9 | 3. **Work needs isolation?** → `using-git-worktrees/SKILL.md` — spin an isolated workspace (`[[main-only-branch]]`). |
| 10 | 4. **Executing the plan?** → `subagent-driven-development/SKILL.md` — one subagent per task + two-stage review (`[[monitor-orchestration]]`, `[[parallel-subagent-economy]]`). |
| 11 | 5. **Before merge?** → `requesting-code-review/SKILL.md` — dispatch the `code-reviewer` agent + Agent Diversity Review (`[[agent-selection]]`). |
| 12 | 6. **Got feedback?** → `receiving-code-review/SKILL.md` — verify it technically, then act; no blind agreement. |
| 13 | 7. **Tests green, done?** → `finishing-a-development-branch/SKILL.md` — merge / PR / cleanup (`[[no-staging-doctrine]]`, auto-push). |
| 14 | |
| 15 | **Authoring a skill itself?** → `writing-skills/SKILL.md` + `[[skill-authoring-contract]]` (the house authoring rule, where the SDO / match-the-form / ordered-by-weight insights now live). |
| 16 | |
| 17 | ## Agent map |
| 18 | |
| 19 | - `requesting-code-review` → the `code-reviewer` agent + diversity gate. |
| 20 | - `subagent-driven-development` → `meta-orchestrator` / parallel `Agent` spawns. |
| 21 | - `brainstorming` → pairs with `14-independent-idea-engine`. |
| 22 | |
| 23 | ## Folded — these live in rules/, not duplicated here |
| 24 | |
| 25 | - `test-driven-development` → `[[e2e-tdd-organization]]` |
| 26 | - `systematic-debugging` → `[[error-recovery]]` |
| 27 | - `verification-before-completion` → `[[verification-loop]]` |
| 28 | - `dispatching-parallel-agents` → `[[parallel-subagent-economy]]` |
| 29 | - `executing-plans` → `[[monitor-orchestration]]` |
| 30 | - `using-superpowers` → `01-operating-system` (skill-check before action) |
| 31 | - writing-skills best insights (SDO, match-the-form, ordered-by-weight, human-voice) → `[[skill-authoring-contract]]` |
| 32 | |
| 33 | <!-- budget: ~63 --> |