agentleFS
Sign inStart free
steepy-itsteepy-it/steepy-apex/skills/brainstorm/SKILL.md

brainstorm

Skill14 starsChanged 36 days agoApache-2.0View on GitHub

Turn an idea into a local working spec under .apex/work/specs/. Classifies the idea against the routing table, dialogues one question at a time, proposes approaches, and on approval writes the spec as a gitignored work artifact.

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, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 0

    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
  1. Very specific:

    Only this SKILL.md is meant to stay in context for the whole run.

    line 39
  2. Very specific:

    Always set model: explicitly when dispatching a subagent.

    line 46

“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

brainstorm

Turn an idea into a local working spec informed by the hub. Do not write code or scaffold anything in this skill — the only artifact produced is the spec.

Engine root: this skill's base directory is <engine-root>/skills/brainstorm/; engine scripts live two levels up, at <engine-root>/scripts/. Resolve them relative to the base directory your harness reports for this skill.

Checklist

  1. Derive coverage and gear from the human request and stable routed evidence; obtain ratification (Step 0).
  2. Orient against the hub (routing table + owning surface standard). 1.5. Resolve a CONFLICT (doc-wins, or override that rewrites the doc) or GAP (explore-first, then write-back or brainstorm) verdict.
  3. Understand the idea — grill it against the hub, one question at a time (gear 2–3).
  4. Propose 2–3 approaches.
  5. Present the design as a draft in .apex/work/specs/ and get approval, section by section (gate).
  6. Finalize the approved draft — fold in the review changes; the header stays status: DRAFT until the approval gate passes. 5.5. Self-review the spec inline — free gate, gear 2 and 3 (Step 5.5).
  7. Validate the stable hub with validate-hub.mjs (deterministic gate).
  8. Human review gate — ask the user to review the written spec, then choose drive mode: manual or autopilot (gear 3).
  9. Hand Gear 2 directly to implement; hand Gear 3 to plan (Step 8).

Procedure

The steps live in co-located files, each read in full at the point named here:

StepsFileRead it
Handoff envelope, resume pairs, publication ordermanual-handoff.mdbefore the spec is published (Step 7 in Gear 3, Step 8 in Gear 2); brainstorm accepts no handoff input, so not at entry
0–1.5: read the gear, orient against the hub, resolve a CONFLICT or GAP verdictentry.mdat the start of every run, fresh or resumed
2–5.5: understand the idea, propose approaches, present and finalize the design, self-review, write-back routingdesign.mdbefore the first design question
6–8: validate, human review gate and drive mode, hand offfinish.mdafter the self-review passes

Only this SKILL.md is meant to stay in context for the whole run; a context compaction can drop the step files you read earlier. Before you act on a step, its file must be fully in view. If it is not — after a compaction, on resume, or when only a summary of it remains — re-read it from this skill's base directory first. Never act on a summary of a step file.

Model Selection

Always set model: explicitly when dispatching a subagent. An omitted model inherits the session model (usually the most capable and most expensive) and silently defeats this policy.

Pick the tier by task complexity and risk:

SignalTier
Mechanical / transcription (1-2 files, complete spec)cheap
Integration / multi-file / judgmentstandard
Design / architecture / high-risk or subtle changemost-capable

Reviewers floor at standard and rise to most-capable when the artifact is high-risk or subtle.

Turn count beats token price. The cheapest model often takes 2-3× the turns on multi-step work — more wall-clock and context overall. Make a mid-tier model the floor for reviewers and for implementers working from prose; reserve the cheapest tier for transcription tasks whose exact code the plan already contains.

Translate the tier to a concrete model by judgment at dispatch time using your harness's available models. The three tiers are the whole ladder — most-capable is its top rung, not an open-ended "best available". A model that sits above that rung is outside the ladder: never reach it from a tier, and record a one-line reason in the ledger when you override to it. On a harness without per-dispatch model choice, everything runs on the session model — record that in the ledger.

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.

Check your setup, free