agentleFS
sakurablushsakurablush/zeroagent-studio/.cursor/skills/add-brain-provider/SKILL.md

add-brain-provider

Skill4 starsChanged 4 months agoMITView on GitHub

Add a BYOK or local brain to ZeroAgent Studio. Use when integrating a new AI API or local inference engine.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Prefer smallest default model

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Add Brain Provider

Files (in order)

  1. src/engines/<provider>.ts — BrainEngine: name, isAvailable, chat
  2. src/engines/index.ts — getEngine() switch
  3. src/types/index.ts — BrainType, ApiKeys if BYOK
  4. src/lib/brainResolver.ts — isBrainConfigured(), getBrainCostLabel(); fallback copy if BYOK
  5. src/lib/brainLabels.ts — getBrainDisplayName()
  6. src/components/settings/SettingsPanel.tsx — key + models (free options first)
  7. src/components/inspector/NodeInspector.tsx — brain + model dropdown
  8. tests/engines/<provider>.test.ts — positive, negative, edge (see test-engineer rule)

BYOK pattern

export function createProviderEngine(apiKey: string): BrainEngine {
  return {
    name: 'Provider',
    isAvailable: () => !!apiKey,
    async chat(messages, options) { /* fetch provider */ },
  }
}

Local engine pattern

  • Dynamic import() for heavy deps
  • createModelLoadCallback() for download UI
  • isAvailable() checks WebGPU / browser support
  • Prefer smallest default model

Prometheus

  • Register in free-brain selection if usable without key
  • Missing key → brainResolver fallback, not crash
  • Settings: label cost clearly (Free (local), Free tier, etc.)

Validate

npm run ci

Manual: Demo workflow + agent node on new brain; verify activity log on fallback.

Rules: .cursor/rules/zeroagent-engineer.mdc · .cursor/rules/zeroagent-test-engineer.mdc

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.