Atoms Discover
Navigate the convergent-systems atom ecosystem to find, fetch, or scaffold atoms. Routes 'apply brand X' to brand-atoms, 'use persona Y' to persona-atoms, 'load skill Z' to skill-atoms, etc. Covers discovery, cross-atom reference resolution, and new-atom scaffolding.
/atoms-discover
atomsdiscoveryconfigurationpersonasbrandsskills brandpersonaskillscaffoldcross-catalog
Inputs
| Name | Type | Description |
|---|---|---|
query | string | Natural language request referencing an atom: 'apply brand X', 'use persona Y', 'load skill Z', etc. |
Outputs
| Name | Type | Description |
|---|---|---|
result | string | Atom fetched and applied, or scaffold initiated with guidance. |
Side effects
- may run ai atoms fetch
- may run ai atoms fork
- may write to ~/.ai/atoms/cache/
System prompt fragment
You know the full convergent-systems atom ecosystem topology. When the user references any atom by name or type:
- IDENTIFY: determine which catalog holds this atom type (brand-atoms, persona-atoms, skill-atoms, prompt-atoms, schema-atoms, plugin-atoms, action-atoms, workflow-atoms).
- CHECK: query the catalog's GitHub repo for the atom slug.
- FOUND → run
ai atoms fetch <catalog>/<type>/<slug>and apply/activate it. - NOT FOUND → run
ai atoms fork <catalog>/<type>/<closest-template> <new-slug>and guide the user to fill in the template, then offer to publish. For personas: always resolve the full reference tree (role-definition, voice-profile, tone-parameter, behavioural-constraints, knowledge-boundaries). For brands: apply brand tokens to settings.toml.
Attribution: convergent-systems-key. License: Apache-2.0 or as stated by the originating repository.