brainstorming
Skill0 starsChanged 4 months agoMITView on GitHub
Turns a vague idea into a validated design through dialogue — clarifies intent one question at a time, explores 2-3 approaches with trade-offs, and validates the design in sections before implementation. Use before building a feature, component, or system when the requirements or approach aren't nailed down yet.
190 other projects use a version of this.
Adopted by
Most recently taken up by
- DemonDamon/AgenticXtheir own version, first seen Nov 9, 2026
- roundpilot/superpowers-antigravitytheir own version, first seen Nov 8, 2026
- ainurdev/mystical-assistanttheir own version, first seen Nov 8, 2026
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- lingyired/status-triotheir own version, first seen Nov 8, 2026
- alunadev/ald-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时，用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
- Leodorareluctant259Skill
chinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 projects that use this
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
- ryanportfolioSkill
apply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +2 more from Leodorareluctant259
- +6 more from ryanportfolio
Other versions190 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 190
- obra/superpowers★ 314ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- JetBrains/thinkrail★ 7.9ksame name
- openai/plugins★ 7.8ksame name
- farm-fe/farm★ 5.6ksame name
- microsoft/FluidFramework★ 4.9ksame name
- BetterTyped/react-zoom-pan-pinch★ 1.9ksame name
- lingyired/status-trio★ 1.8ksame name
180 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-phaseSkill
- code-reviewSkill
- debuggingSkill
- online-researchSkill
- security-reviewSkill
- skill-creatorSkill
- skill-reviewerSkill
- software-developmentSkill
- writing-plansSkill
- writing-testsSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Write implementation code or a task breakdown → hand off to writing-plans (to phase it) and software-development (to build it).
- Distinctive: line 21
Add features nobody asked for → keep the design minimal (YAGNI).
- Distinctive: line 29
Read the current project state (files, docs, recent commits) before asking anything.
- Distinctive: line 33
Ask ONE question per turn (multiple-choice when you can — it's easier to answer).
- Very specific: line 49
Write the validated design to docs/plans/YYYY-MM-DD-<topic>-design.md.
“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brainstorming
Design before building. Draw the requirements out of the user through dialogue, explore alternatives, and validate the design incrementally — don't jump to a solution or start coding.
Scope
This skill DOES:
- Understand the idea, clarify intent one question at a time, explore approaches with trade-offs, and validate the design in small sections.
This skill does NOT:
- Write implementation code or a task breakdown → hand off to
writing-plans(to phase it) andsoftware-development(to build it). - Barrel ahead once it knows "enough" without validating with the user.
- Add features nobody asked for → keep the design minimal (YAGNI).
Steps
Surface these as TodoWrite items. Checkpoint the work-in-progress design to
./.claude-skills-work/brainstorming/<topic>/design.md so a long session
resumes; the final validated design is written to docs/plans/ in step 5.
1. Understand the context
Read the current project state (files, docs, recent commits) before asking anything. Restate the idea in your own words so the user can correct you.
2. Clarify intent — one question at a time ⛔
Ask ONE question per turn (multiple-choice when you can — it's easier to answer).
Cover purpose, constraints, success criteria, and scope. Keep going until you can
state plainly what's being built and what "done/good" means. Prefer stop-and-ask
over assuming. See references/questioning.md.
3. Explore approaches
Propose 2–3 distinct approaches with concrete trade-offs. Lead with your recommendation and why; let the user choose. Don't present a single option as if it's the only one.
4. Present the design in sections
Present the design in small sections (~200–300 words each): architecture, components, data flow, error handling, testing. After each, ask "does this look right?" and adjust before continuing. Go back if something doesn't fit.
5. Write it down and hand off
Write the validated design to docs/plans/YYYY-MM-DD-<topic>-design.md. Point
the user to writing-plans to turn it into a phased implementation plan.
Red flags (stop and correct)
| If you notice… | Do this |
| Asking several questions at once | One question per turn |
| Jumping to a design/solution before intent is clear | Clarify intent first (step 2) |
| Dumping a whole design wall | Present in sections; validate each |
| Offering only one option | Propose 2–3 approaches with trade-offs |
| Starting to write implementation code | Stop — design here; software-development builds |
| Designing for hypothetical futures | Keep it minimal (YAGNI); design the real need |
| Accepting a vague "make it good" | Pin down concrete success criteria |
Done when
- You can state what's being built, its constraints, and its success criteria.
- The user chose among explored alternatives, and the design was validated section by section.
- The design is written to
docs/plans/and handed off towriting-plans.
References (load only when needed)
references/questioning.md— asking good one-at-a-time questions (multiple-choice vs open, when to stop) and framing approach trade-offs.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.