brainstorming
Skill1 starsChanged 21 days agoMITView on GitHub
Resolve requirements for new or changed behaviour - get the problem from the user, explore the codebase, then interview in short rounds of numbered questions with recommended answers. Use before planning any behavioural change. Runs in the main session; explorers do the reading.
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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- development-workflowSkill
- exploringSkill
- finishing-developmentSkill
- requesting-reviewSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
7
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 9
Run this in the main session - only it can talk to the user.
- Distinctive: line 14
Ask the user to describe the problem: what is wrong or missing, who it affects, and what "done" looks like.
- Distinctive: line 30
Look up facts; ask the user only for decisions.
- Distinctive: line 43
Check each answer for undefined terms, contradictions, missing edge cases, and missing success criteria.
- Distinctive: line 45
If the user is on a protected branch, include the branch name as a question, unless the project instructions already set a convention.
- Distinctive: line 51
Do not answer for the user, and do not treat silence or a topic change as agreement.
- Distinctive: line 54
Round budget: after three rounds, summarise what is decided and what is still open, and ask whether the open points matter.
“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
Turn a request into a resolved specification, so nothing is built on guesses. Run this in the main session - only it can talk to the user. Explorers do the reading. Do not write a plan, create a branch, or change code here.
1. Get the problem first
Ask the user to describe the problem: what is wrong or missing, who it affects, and what "done" looks like. If they already described it, restate it in two or three lines and ask them to confirm. Wait for the answer before exploring.
2. Explore
Dispatch explorers per
exploring, with questions shaped by the problem. Run
independent questions at the same time. Typical questions:
- How does the project already solve something similar? What can be reused?
- Which interfaces, naming, error handling, and data flow constrain the change?
- Which test patterns and spec and lint commands does the project use?
- What does the locked version of a dependency or external API actually support?
Look up facts; ask the user only for decisions. A question the repository can answer goes to an explorer.
3. Interview in rounds
Come back with a short summary of what you found, then a round of 3 to 5 numbered questions. Each question has a recommended answer grounded in the findings, so the user can reply "all yes, except 3".
- Order the questions by dependency: settle a decision before the ones that depend on it.
- Where more than one approach is valid, name the options, state the tradeoff in one line, and recommend one. Prefer the simplest approach that works.
- Check each answer for undefined terms, contradictions, missing edge cases, and missing success criteria. Put follow-ups in the next round.
- If the user is on a protected branch, include the branch name as a question, unless the project instructions already set a convention.
- Cover what applies: scope, non-goals, inputs and outputs, failure behaviour, permissions and security, data and migrations, compatibility, and acceptance criteria.
Do not answer for the user, and do not treat silence or a topic change as agreement.
Round budget: after three rounds, summarise what is decided and what is still open, and ask whether the open points matter. If they do not, record them as discretion for the implementer and move on.
Done when
The problem, requirements, failure behaviour, and acceptance criteria are
decided. Summarise the specification and hand it to
writing-plans.
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.