brainstorming
Skill1 starsChanged 4 months agoMITView on GitHub
The generative half of the idea workflow — expand a rough idea, feature request, or vague problem into a coherent design and a short menu of approaches. Use when you start something new (a feature, a UX change, a refactor with real design choices) and the shape isn't obvious yet, or when the user says "I want to add…", "what if we…", or "how should we…". Optional, not a required gate. Pairs with idea-review, which prunes what this grows.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- dvy1987/agent-loomtheir own version, first seen Nov 15, 2026
- FimawLLC/fimaw-skillstheir own version, first seen Nov 15, 2026
- mdiri-ai/SoduWorktheir own version, first seen Nov 15, 2026
- Wenaixi/dsh-superpowertheir own version, first seen Nov 15, 2026
- iliaal/ai-skillstheir own version, first seen Nov 14, 2026
- bartstc/vite-ts-react-templatetheir own version, first seen Nov 13, 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
Leodorareluctant259Skillchinese-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
ryanportfolioSkillapply-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 versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- obra/superpowers★ 314ksame name
- jnMetaCode/superpowers-zh★ 8.5ksame name
- JetBrains/thinkrail★ 8.3ksame name
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame 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
181 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/00-harness.mdcCursor rule
- checkpointing-progressSkill
- executing-plansSkill
- idea-reviewSkill
- initiating-a-projectSkill
- onboardingSkill
- <kebab-case-folder-name>Skill
- test-driven-developmentSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 172 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Ask when a choice changes what gets built and you can't infer it (scope, which surface first, a hard constraint).
- Distinctive: line 27
Keep the brief short and disposable — it's the input to the spec, not the spec itself.
“Common” is measured: kept by at least 6 in 10 of the 172 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
Skill: Brainstorming (generative pre-spec exploration)
This is the generative half of the idea workflow; idea-review is the adversarial half. Grow ideas here, prune them there. This step is optional — reach for it when a one-line request would otherwise jump straight to a spec that solves the wrong problem, not as mandatory ceremony for every change.
Goal
Turn a vague ask into: a crisp problem statement, 2–4 genuinely different approaches, and a recommended direction with its open questions — enough to write a spec (or to hand to idea-review if the idea is risky).
How to run it
- Pin the real problem, not the proposed solution. What does the user actually need, who hits it, and how often? State it in one sentence. If the ask is already a solution ("add a tree view"), work backward to the need it serves.
- Check it against the core. Does this serve the product's reason to exist (the differentiator in
AGENTS.md/ the PRD), or at least not fight it? Does it respect theAGENTS.mdinvariants? An idea that breaks an invariant needs a very good reason — surface it now, not after a spec exists. - Generate 2–4 distinct approaches, not variations of one. For each: the mechanism, where it lands in the codebase's layers/modules, and the smallest version that delivers value. Always include a "do nothing / smallest possible" option.
- Weigh them on effort, risk, reversibility, and fit with existing seams (prefer extending an existing abstraction over a parallel code path). Name the tradeoffs plainly.
- Recommend one, and list the open questions it still carries.
When to ask the user vs. decide
Ask when a choice changes what gets built and you can't infer it (scope, which surface first, a hard constraint). Decide yourself — and say so — when there's a conventional default. Don't stall on questions the differentiator or an invariant already answers.
Output → spec (optionally via idea-review)
A short brief: problem, approaches considered (with tradeoffs), recommended direction, open questions. If the idea is risky or expensive, hand that to idea-review before writing the spec; otherwise write the DRAFT spec in docs/specs/ directly.
Conventions
- Breadth before depth: get the option space out before committing. One well-argued option is not a brainstorm.
- Keep the brief short and disposable — it's the input to the spec, not the spec itself.
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.

