brainstorming
This skill structures ideation by requiring explicit goal restatement, generation of at least three distinct approaches with their trade-offs, evaluation against four criteria, and commitment to a chosen direction before implementation begins. Use it when tackling any substantial problem to avoid premature solution-narrowing and ensure thorough consideration of alternatives.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/brainstorming && cp -r /tmp/brainstorming/skills/core/brainstorming ~/.claude/skills/brainstormingSKILL.md
# Brainstorming Before implementing anything non-trivial, brainstorm first. ## The Process ### Step 1: Restate the Goal Write what you are actually trying to achieve in 1-2 sentences. ### Step 2: Generate Options (minimum 3) List at least 3 different approaches. Include approaches that seem impractical. For each option: - What makes it appealing - What risks or downsides it carries - What unknowns would need to be resolved ### Step 3: Evaluate Score each option against: Simplicity, Reversibility, Risk, Speed. ### Step 4: Pick and Commit Choose one approach. State why. Then move to writing-plans.
Syncs agent daily memory and MEMORY.md to an Obsidian vault so notes are human-browsable. Use nightly or on demand.
Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.
Executes plans task-by-task with verification. Use when implementing a plan.
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
Crawls a new codebase to infer stack, conventions, and key invariants, then generates a PROJECT.md context file for the agent
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Detects skill name shadowing and description-overlap conflicts that cause OpenClaw to trigger the wrong skill or silently ignore one when two skills compete for the same intent.
Reviews whether a skill will trigger reliably, guide useful behavior, avoid overlap, and produce testable outcomes.