agentleFS
samsam007bsamsam007b/claude-code-standards-kit/skills/brainstorm/SKILL.md

brainstorm

Skill2 starsChanged 8 months agoMITView on GitHub

Pre-implementation analysis guard — evaluates scope, reversibility, and approach plurality before Claude starts building. Required for tasks touching > 20 files or with Low/None reversibility.

189 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • CoralGameSkill

    playtest-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

  • CoralGameSkill

    team-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

  • lilangMaxSkill

    soak-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

  • lilangMaxSkill

    team-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

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 156 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
  1. Distinctive:

    If only one approach is visible, the problem is under-understood — clarify before proceeding.

    line 64
  2. Distinctive:

    If any check fails: clarify before implementing.

    line 74

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: Brainstorm Guard

Activate before any non-trivial implementation task. Evaluates the task against 4 criteria before proceeding: scope, reversibility, approach plurality, and motivation clarity.

When to use

SignalCeremony
Bug fix touching 1–3 filesSkip — proceed directly
Feature touching 4–20 filesRecommended
Feature touching > 20 filesRequired (CONTRACT-ANTI-PATTERNS.md §6)
Database migration or schema changeRequired
Architectural refactorRequired
Ambiguous task with no linked issueRequired — clarify first
Any time /brainstorm <task> is invokedRun full analysis

Analysis dimensions

1. Scope assessment

Count files that will be modified or created.

File countLevel
< 5 filesLight — skip or do verbally
5–20 filesRecommended brainstorm
> 20 filesRequired brainstorm

2. Reversibility check

ChangeReversibilityRequired action
New file, no DB changeHighNone
Renamed exportMediumDocument callers
DB schema migrationLowWrite rollback migration first
External API / webhook / emailNoneManual remediation plan required

If reversibility is Low or None: document the rollback plan before the first line of code.

3. Approach plurality

List at least 2 viable approaches before committing to one. Evaluate each on:

  • Implementation complexity (Low / Medium / High)
  • Reversibility
  • Files affected
  • Test strategy

If only one approach is visible, the problem is under-understood — clarify before proceeding.

4. Motivation clarity

The task must pass all four checks:

  • Describable in one sentence
  • Linked to an issue, contract, or spec (or task given by user)
  • Success criteria are measurable
  • No requirements beyond what was stated

If any check fails: clarify before implementing.

Output format

SQWR BRAINSTORM — [Task title]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Scope:         [N files — Light | Recommended | Required]
Reversibility: [High | Medium | Low | None]
               [Rollback plan if Low/None]

Approach A:    [description]
  Complexity:  [Low/Medium/High]
  Trade-off:   [key consideration]

Approach B:    [description]
  Complexity:  [Low/Medium/High]
  Trade-off:   [key consideration]

Contracts:     [which SQWR contracts apply]
Motivation:    [one sentence] — Ref: [issue/contract/task]

Recommendation: Approach [A | B]
→ PROCEED / CLARIFY FIRST / SCOPE REDUCTION RECOMMENDED
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Invoke

/brainstorm <task description>

Examples:

/brainstorm Refactor the authentication module to use JWT refresh tokens
/brainstorm Add multi-tenant support to the billing system
/brainstorm Migrate from Prisma to Drizzle ORM

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.