agents/skills/brainstorm/SKILL.md
Open-ended exploration before committing to an approach. Use when the user says "let's brainstorm", "help me think through this", "what should we build", "explore options", or any ambiguous request with multiple valid framings.
npx skillsauth add erikrogne/monorepo-starter brainstormInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Pre-commit exploration. Used before planning, drafting, or coding — when the user is still figuring out what they want.
write or research if the topic is half-formed.Restate the user's question in your own words. Confirm you've got the right thing before diverging into options. If the question is too vague to mirror, ask one clarifying question.
Ask: what are the axes of variation here? List them. Examples:
The user picks where they want to be on each axis. Sometimes they don't know — that's fine, list a default and ask.
Produce 3–5 distinct framings or approaches. Distinct is the bar — don't list three variations of the same idea.
For each:
Ask: "Which of these is closest to what you want, and what would you change?"
If the user picks one, hand off to the appropriate skill (write, research, compile, or just normal execution).
If none fit, ask what's missing and generate again.
If the brainstorm produced something worth keeping, suggest writing it to wiki/concepts/<slug>.md or appending to a project's notes.md. Don't save automatically.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.