brainstorming
Skill439 starsChanged 8 months agoMITView on GitHub
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
We split this skill into the rules it gives an agent
19 rules. 1 is common, 16 are distinctive, and 2 are very specific to this project.
1
Common
Most of the 173 edited versions we read keep these.
16
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
- Distinctive: line 12
Start by understanding the current project context, then ask questions one at a time to refine the idea.
- Distinctive: line 15
Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a …
- Very specific: line 28
If the project has no existing files: skip the "Explore project context" step, start directly with clarifying questions, and create the …
- Distinctive: line 67
The terminal state is loading writing-plans: Do NOT load frontend-design, mcp-builder, or any other implementation skill.
- Common: line 72
Check out the current project state first (files, docs, recent commits)
- Distinctive: line 73
Ask questions one at a time to refine the idea
- Distinctive: line 74
Prefer multiple choice questions when possible, but open-ended is fine too
- Distinctive: line 75
Only one question per message - if a topic needs more exploration, break it into multiple questions
- Distinctive: line 78
Termination criterion for clarifying questions: Ask clarifying questions until: (a) you can restate the goal in one sentence, (b) you know …
- Distinctive: line 88
Ask after each section whether it looks right so far
- Distinctive: line 93
If the user approves with modifications: incorporate the modifications, re-present the changed section only, then proceed
- Distinctive: line 94
Do not re-present unchanged sections
- Very specific: line 99
Write the validated design to docs/plans/YYYY-MM-DD-<topic>-design.md
- Distinctive: line 100
Use elements-of-style:writing-clearly-and-concisely skill if available
- Distinctive: line 101
Commit the design document to git
- Distinctive: line 105
Do NOT load any other skill.
- Distinctive: line 109
One question at a time: - Don't overwhelm with multiple questions
- Distinctive: line 111
YAGNI ruthlessly: - Remove unnecessary features from all designs
- Distinctive: line 112
Explore alternatives: - Always propose 2-3 approaches before settling
“Common” is measured: kept by at least 6 in 10 of the 173 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 Ideas Into Designs
Overview
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
<HARD-GATE>
Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.Announce: "Design HARD-GATE: I will not write code or scaffold files until you approve this design."
An implementation action is: writing any file that will be part of the product (src/, lib/, app/), running npm init/create-*, generating scaffolding.
</HARD-GATE>
Anti-Pattern: "This Is Too Simple To Need A Design"
Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
Greenfield Projects
If the project has no existing files: skip the "Explore project context" step, start directly with clarifying questions, and create the docs/ directory as the first implementation action after approval.
Checklist
You MUST create a task for each of these items and complete them in order:
- Explore project context — check files, docs, recent commits
- Ensure Planning Mode — prompt user to switch to Planning Mode if not already active
- Ask clarifying questions — one at a time, understand purpose/constraints/success criteria
- Propose 2-3 approaches — with trade-offs and your recommendation
- Present design — in sections scaled to their complexity, get user approval after each section
- Write design doc — save to
docs/plans/YYYY-MM-DD-<topic>-design.mdand commit - Transition to implementation — load writing-plans skill to create implementation plan
Process Flow
digraph brainstorming {
"Explore project context" [shape=box];
"Ask clarifying questions" [shape=box];
"Propose 2-3 approaches" [shape=box];
"Present design sections" [shape=box];
"User approves design?" [shape=diamond];
"Incorporate modifications, re-present changed section" [shape=box];
"Write design doc" [shape=box];
"Load writing-plans skill" [shape=doublecircle];
"Explore project context" -> "Ask clarifying questions";
"Ask clarifying questions" -> "Propose 2-3 approaches";
"Propose 2-3 approaches" -> "Present design sections";
"Present design sections" -> "User approves design?";
"User approves design?" -> "Present design sections" [label="no, revise"];
"User approves design?" -> "Incorporate modifications, re-present changed section" [label="approved with modifications"];
"Incorporate modifications, re-present changed section" -> "Write design doc";
"User approves design?" -> "Write design doc" [label="yes"];
"Write design doc" -> "Load writing-plans skill";
}The terminal state is loading writing-plans. Do NOT load frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you load after brainstorming is writing-plans.
The Process
Understanding the idea:
- Check out the current project state first (files, docs, recent commits)
- Ask questions one at a time to refine the idea
- Prefer multiple choice questions when possible, but open-ended is fine too
- Only one question per message - if a topic needs more exploration, break it into multiple questions
- Focus on understanding: purpose, constraints, success criteria
Termination criterion for clarifying questions: Ask clarifying questions until: (a) you can restate the goal in one sentence, (b) you know the top constraint, (c) you understand the success criteria. Stop at 3-5 questions unless complexity demands more.
Exploring approaches:
- Propose 2-3 different approaches with trade-offs
- Present options conversationally with your recommendation and reasoning
- Lead with your recommended option and explain why
Presenting the design:
- Once you believe you understand what you're building, present the design
- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
- Ask after each section whether it looks right so far
- Cover: architecture, components, data flow, error handling, testing
- Be ready to go back and clarify if something doesn't make sense
Handling partial approval:
- If the user approves with modifications: incorporate the modifications, re-present the changed section only, then proceed
- Do not re-present unchanged sections
After the Design
Documentation:
- Write the validated design to
docs/plans/YYYY-MM-DD-<topic>-design.md - Use elements-of-style:writing-clearly-and-concisely skill if available
- Commit the design document to git
Implementation:
- Load the writing-plans skill to create a detailed implementation plan
- Do NOT load any other skill. writing-plans is the next step.
Key Principles
- One question at a time - Don't overwhelm with multiple questions
- Multiple choice preferred - Easier to answer than open-ended when possible
- YAGNI ruthlessly - Remove unnecessary features from all designs
- Explore alternatives - Always propose 2-3 approaches before settling
- Incremental validation - Present design, get approval before moving on
- Be flexible - Go back and clarify when something doesn't make sense
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 107
- openai/plugins★ 7.4k16% same
- farm-fe/farm★ 5.6k34% same
- BetterTyped/react-zoom-pan-pinch★ 1.9k34% same
- revokslab/ShipFree★ 1.7k78% same
- pcvelz/superpowers★ 1.3k12% same
- coco-research/coco★ 79733% same
- AgentTeam-TaichuAI/ScienceClaw★ 67139% same
- shobcoder/shob★ 57534% same
- lnikell/loopndroll★ 56734% same
- involvex/youtube-music-cli★ 46878% same
97 more not listed
Wrote their own version · 84
- obra/superpowers★ 305ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- JetBrains/thinkrail★ 6.8ksame name
- microsoft/FluidFramework★ 5ksame name
- feiskyer/claude-code-settings★ 1.7ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- sentient-agi/EvoSkill★ 1.2ksame name
- feiskyer/codex-settings★ 243same name
74 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.
Used alongsideProjects 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.
GEd520Skillchinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。
Also in 7 projects that use this
GEd520Skillchinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。
Also in 7 projects that use this
ryanportfolioSkilladdskill
Create, import, update, or install repository or personal skills; includes runtime ownership, resources, and discovery validation.
Also in 5 projects that use this
ryanportfolioSkillastra-fullreview
Full multi-agent Codex review on gpt-6-astra at medium reasoning. Same verified lifecycle as codex-fullreview. Use for /astra-fullreview or 'full Astra review with sub-reviewers'.
Also in 5 projects that use this
- +2 more from GEd520
- +6 more from ryanportfolio
In this repository19 other files it gives its agents.
- architecture-designSkill
- browser-agentSkill
- confidence-checkSkill
- deep-researchSkill
- dependency-managementSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- performance-optimizationSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- security-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-superantigravitySkill
- verification-before-completionSkill
- writing-plansSkill
- writing-skillsSkill
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.

