brainstorm
Skill9 starsChanged 2 months agoApache-2.0View on GitHub
This skill creates and ranks research hypotheses from current findings. You use it after formalization or between investigation batches.
189 other projects use a version of this.
Adopted by
Most recently taken up by
- nielsmadan/skillstheir own version, first seen Nov 8, 2026
- phuthuycoding/kanban-flowtheir own version, first seen Nov 8, 2026
- baethon/skillstheir own version, first seen Nov 8, 2026
- CloudChef/atlasclaw-providerstheir own version, first seen Nov 8, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- LongJohnSilver1504/claude-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use playtest-report, team-polish 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.
CoralGameSkillplaytest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
Also in 9 projects that use this
CoralGameSkillteam-polish
Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.
Also in 11 projects that use this
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 6 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 6 projects that use this
- +8 more from CoralGame
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- codeaholicguy/ai-devkit★ 1.7ksame name
- jtydhr88/ComfyTV★ 1.2ksame name
- event-driven-io/emmett★ 562same name
- zaxbysauce/opencode-swarm★ 519same name
- ZaxbyHub/opencode-swarm★ 518same name
- automagik-dev/genie★ 351same name
- namastexlabs/automagik-genie★ 351same name
- bkywksj/knowledge-base★ 340same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
179 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.
- CLAUDE.mdCLAUDE.md
- analyze-paperSkill
- clarify-goalSkill
- critiqueSkill
- formalize-problemSkill
- investigateSkill
- reaperSkill
- review-literatureSkill
- search-paperSkill
- write-paperSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 156 edited versions we read keep these.
1
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 33
If results.md has 20 or more rows, you read batch summaries instead of all rows.
- Distinctive: line 56
After three or more cycles that suggest refutation, you propose a negative claim.
- Very specific: line 91
If problem-statement.md or ideas.md is missing, you return an error to the orchestrator.
“Common” is measured: kept by at least 6 in 10 of the 156 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
Brainstorm
You must read and apply the language rules before you write any output.
This skill revises ideas without experiments, proof attempts, or literature searches.
Usage
You invoke this skill by name with an optional quoted direction. Slash-command hosts use /brainstorm "<hint>".
brainstorm
brainstorm "explore liveness under partial synchrony"Inputs
You always read these files:
reaper-workspace/notes/problem-statement.mdsupplies the model and properties.reaper-workspace/notes/ideas.mdsupplies ideas and their status.reaper-workspace/notes/current-understanding.mdsupplies current findings.reaper-workspace/notes/results.mdsupplies previous outcomes.
If results.md has 20 or more rows, you read batch summaries instead of all rows. You look for failure patterns across batches. You use the optional direction from the argument. You read these sources only when a specific idea needs them or progress stops:
reaper-workspace/notes/paper-summary.mdreaper-workspace/notes/literature.mdreaper-workspace/notes/clarified-goal.mdreaper-workspace/papers/
Process
1. Assess Current State
You identify resolved hypotheses and open hypotheses. You identify hypotheses with repeated inconclusive cycles. You look for common causes of discarded cycles. You check whether keep results suggest a new direction.
2. Generate Ideas
You select a method from the current evidence:
- Failed attempts: You invert the claim, simplify the case, or change the model or property.
- Confirmed results: You reuse a proof method, remove an assumption, or test a further implication.
- Unexplored combinations: You use
../reaper/references/model.mdto find gaps without a prior investigation result.
You assign each proposed idea to one source category.
After three or more cycles that suggest refutation, you propose a negative claim. You also propose a hypothesis about the weakest assumption that restores the property.
3. Check Impossibility Results
You check each candidate against ../reaper/references/impossibility-results.md. If a known result rules out a candidate, you identify the conflict. You change the candidate to specify additional assumptions or a weaker property. You do not pass a known impossible positive claim to investigate.
4. Set Priorities
You rank ideas by who needs their answers and why. You use the examples in ../reaper/references/model.md.
5. Write Output
You update reaper-workspace/notes/ideas.md. You add new ideas in a new round section. You edit existing ideas in place when their statements or priorities change. You mark ideas that another result already covers.
## Ideas — Brainstorm Round N
### H<next>: [Short title]
- **Statement**: [You state a precise claim that evidence can refute.]
- **Success condition**: [You state the evidence that confirms the claim.]
- **Failure condition**: [You state the evidence that refutes the claim.]
- **Priority**: High / Medium / Low
- **Rationale**: [You explain the effect of resolving this claim.]
- **Source**: [Brainstorm-N] [You identify the finding, failure pattern, gap, or prior hypothesis that suggested this idea.]N is one greater than the highest existing brainstorm round, or 1 for the first round. Hypothesis numbers continue from the highest existing H number.
Quality Criteria
- You add no more than 3-5 ideas per round.
- Each idea tests one claim in one cycle. You split claims that combine properties such as safety and liveness.
- Each idea has explicit success and failure conditions.
- You do not duplicate an unresolved idea.
- You give the user's direction high priority without excluding other useful ideas.
- If
problem-statement.mdorideas.mdis missing, you return an error to the orchestrator.
Report
You report the number of new ideas and the most important new idea. You explain any lower priorities or ideas that other results now cover.
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.

