Superpowers — OpenClaw Edition

Adapted from obra/superpowers. Mandatory workflow — not suggestions.

The Pipeline

Idea → Brainstorm → Plan → Subagent-Driven Build (TDD) → Code Review → Finish Branch

Every coding task follows this pipeline. "Too simple to need a design" is always wrong.

Phase 1: Brainstorming

Trigger: User wants to build something. Activate before touching any code.

See: references/brainstorming.md

Summary:

Explore project context (files, docs, recent commits)
Ask clarifying questions — one at a time, prefer multiple choice
Propose 2–3 approaches with trade-offs + recommendation
Present design in sections, get approval after each
Write design doc → docs/plans/YYYY-MM-DD-<topic>-design.md → commit
Hand off to Phase 2: Writing Plans

HARD GATE: Do NOT write any code until user approves design.

Phase 2: Writing Plans

Trigger: Design approved. Activated by brainstorming phase.

See: references/writing-plans.md

Summary:

Write a detailed task-by-task implementation plan
Each task = 2–5 minutes: write test → watch fail → implement → watch pass → commit
Save to docs/plans/YYYY-MM-DD-<feature>.md
Announce: "I'm using the writing-plans skill to create the implementation plan."
After saving, offer two execution modes:
- Subagent-driven (current session): sessions_spawn per task + two-stage review
- Manual execution: User runs tasks themselves

Phase 3: Subagent-Driven Development

Trigger: Plan exists, user chooses subagent-driven execution.

See: references/subagent-development.md

Per-task loop (OpenClaw):

sessions_spawn an implementer subagent with task + full plan context
Wait for completion announcement
sessions_spawn a spec-reviewer subagent → must confirm code matches spec
sessions_spawn a code-quality reviewer subagent → must approve quality
Fix any issues, re-review if needed
Mark task done, move to next
Final: dispatch overall code reviewer → hand off to Phase 5

TDD is mandatory in every task. See references/tdd.md.

Phase 4: Systematic Debugging

Trigger: Bug, test failure, unexpected behaviour — any technical issue.

See: references/systematic-debugging.md

HARD GATE: No fixes without root cause investigation first.

Four phases:

Root Cause Investigation (read errors, reproduce, check recent changes, trace data flow)
Pattern Analysis (find working examples, compare, identify differences)
Hypothesis + Testing (one hypothesis at a time, test to prove/disprove)
Fix + Verification (fix at root, not symptom; verify fix doesn't break anything)

Phase 5: Finishing a Branch

Trigger: All tasks complete, all tests pass.

See: references/finishing-branch.md

Summary:

Verify all tests pass
Determine base branch
Present 4 options: merge locally / push + PR / keep / discard
Execute choice
Clean up

OpenClaw Subagent Dispatch Pattern

When dispatching implementer or reviewer subagents, use sessions_spawn:

Goal: [one sentence]
Context: [why it matters, which plan file]
Files: [exact paths]
Constraints: [what NOT to do — no scope creep, TDD only]
Verify: [how to confirm success — tests pass, specific command]
Task text: [paste full task from plan]

Run sessions_spawn with the task as a detailed prompt. The sub-agent announces results automatically.

Key Principles

One question at a time during brainstorm
TDD always — write failing test first, delete code written before tests
YAGNI — remove unnecessary features from all designs
DRY — no duplication
Systematic over ad-hoc — follow the process especially under time pressure
Evidence over claims — verify before declaring success
Frequent commits — after each green test