Skill
Skill protocol schemas
Skill Trigger Condition Schema
Defines programmatic conditions under which a skill becomes active.
Allows context-aware activation based on object type, user role, etc.
Source: packages/spec/src/ai/skill.zod.ts
TypeScript Usage
import { Skill, SkillTriggerCondition } from '@objectstack/spec/ai';
import type { Skill, SkillTriggerCondition } from '@objectstack/spec/ai';
// Validate data
const result = Skill.parse(data);Skill
Properties
| Property | Type | Required | Description |
|---|---|---|---|
| name | string | ✅ | Skill unique identifier (snake_case) |
| label | string | ✅ | Skill display name |
| description | string | optional | Skill description |
| instructions | string | optional | LLM instructions when skill is active |
| tools | string[] | ✅ | Tool names belonging to this skill (supports trailing wildcard, e.g. action_*) |
| triggerPhrases | string[] | optional | Phrases that activate this skill |
| triggerConditions | Object[] | optional | Programmatic activation conditions |
| permissions | string[] | optional | Required permissions or roles |
| active | boolean | ✅ | Whether the skill is enabled |
| protection | Object | optional | Package author protection block — lock policy for this skill. |
| _lock | Enum<'none' | 'no-overlay' | 'no-delete' | 'full'> | optional | Item-level lock — controls overlay & delete (ADR-0010). |
| _lockReason | string | optional | Human-readable reason shown when a write is refused by _lock. |
| _lockSource | Enum<'artifact' | 'package' | 'env-forced'> | optional | Layer that set _lock (artifact |
| _provenance | Enum<'package' | 'org' | 'env-forced'> | optional | Origin of the item (package |
| _packageId | string | optional | Owning package machine id. |
| _packageVersion | string | optional | Owning package version. |
| _lockDocsUrl | string | optional | Optional documentation link surfaced next to _lockReason. |
SkillTriggerCondition
Properties
| Property | Type | Required | Description |
|---|---|---|---|
| field | string | ✅ | Context field to evaluate |
| operator | Enum<'eq' | 'neq' | 'in' | 'not_in' | 'contains'> | ✅ | Comparison operator |
| value | string | string[] | ✅ | Expected value or values |