agentleFS
omdenkar2-uiomdenkar2-ui/all-in-one/skills/aio-brainstorm/SKILL.md

aio-brainstorm

Skill0 starsChanged 31 days agoMITView on GitHub

Explore ambiguous backend, API, agent or workflow ideas into a bounded requirements brief with alternatives and observable success. Use before architecture or planning when the outcome or scope is unsettled.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Read the named source, relevant repository contracts and current interfaces.

    line 14
  2. Distinctive:

    Read backend discovery for an ambiguous workflow.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

AIO Brainstorm

Determine what must become true for callers or operators before selecting how to build it. Preserve the user's backend scope, existing stack, constraints and already granted autonomy. A brief can be a short answer; substantial work needs stable requirements that travel into the implementation plan.

Inherit the caller's stage contract, resource budget and original journal; use thorough for a standalone run. Default to HOLD SCOPE. For a named scope mode or proposed addition/deferral, read scope modes. Explicit user instructions govern; a mode does not approve a requirement change or production implementation.

Establish the brief

  1. Read the named source, relevant repository contracts and current interfaces. Separate observed facts, user decisions and hypotheses. Resolve repository facts through inspection rather than asking the user to look them up.
  2. State the outcome, affected actors and exclusions. Distinguish an implementation suggestion from the outcome it serves. An agent framework, queue or vector database is a means, not success.
  3. Read backend discovery for an ambiguous workflow. Ask only questions that materially change the outcome, safety or irreversible scope. Carry settled choices forward; new evidence of infeasibility earns an explicit blocker, not a silent replacement.
  4. Compare plausible alternatives against the same acceptance criteria, including the least complex option. Explain carrying cost, failure behavior and reversibility. If a decisive claim needs an experiment, route a bounded question to AIO Prototype; do not disguise a guess as a decision.
  5. Record accepted requirements as stable R1, R2 IDs with observable acceptance, provenance and real uncertainties. Use brief template when a durable artifact helps later workers. Omit irrelevant sections; do not inflate a narrow change into a platform project.

Ready for planning

A planner must be able to identify the goal, scope, inputs/outputs, constraints, success conditions and unresolved decisions without inventing product behavior. Do not call an incomplete brief executable. For architecture-intensive work, hand it to AIO Architecture; an established brief goes to AIO Plan.

A standalone brainstorm writes only its requested brief and reports the next useful step. In an already authorized build or Complete Destruction run, return the brief, stable source path, readiness and blockers to the controller, which continues without another routine approval. Do not implement production code inside this skill.

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.