.build/codex/skills/json-schema-design/SKILL.md
Design and validate JSON Schemas for API contracts, configuration files, and data exchange formats. Covers schema composition, conditional validation, and code generation from schemas. Triggers on JSON Schema creation, data validation, or API contract design requests.
npx skillsauth add organvm-iv-taxis/a-i--skills json-schema-designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Define precise data contracts with JSON Schema for validation, documentation, and code generation.
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://organvm.dev/schemas/repo.json",
"title": "Repository",
"description": "An ORGANVM repository entry",
"type": "object",
"required": ["name", "organ", "tier", "status"],
"properties": {
"name": {
"type": "string",
"pattern": "^[a-z][a-z0-9-]*$",
"minLength": 2,
"maxLength": 64
},
"organ": {
"type": "string",
"enum": ["I", "II", "III", "IV", "V", "VI", "VII", "META"]
},
"tier": {
"type": "string",
"enum": ["flagship", "standard", "infrastructure"]
},
"status": {
"type": "string",
"enum": ["LOCAL", "CANDIDATE", "PUBLIC_PROCESS", "GRADUATED", "ARCHIVED"]
},
"tags": {
"type": "array",
"items": { "type": "string" },
"uniqueItems": true
}
},
"additionalProperties": false
}
{
"priority": {
"type": "integer",
"minimum": 1,
"maximum": 10
},
"score": {
"type": "number",
"exclusiveMinimum": 0,
"maximum": 1.0
}
}
{
"$defs": {
"organ": {
"type": "string",
"enum": ["I", "II", "III", "IV", "V", "VI", "VII", "META"]
},
"timestamp": {
"type": "string",
"format": "date-time"
}
},
"properties": {
"source_organ": { "$ref": "#/$defs/organ" },
"target_organ": { "$ref": "#/$defs/organ" },
"created_at": { "$ref": "#/$defs/timestamp" }
}
}
{
"allOf": [
{ "$ref": "#/$defs/base-entity" },
{
"properties": {
"extra_field": { "type": "string" }
}
}
]
}
{
"oneOf": [
{
"properties": {
"type": { "const": "skill" },
"category": { "type": "string" }
},
"required": ["type", "category"]
},
{
"properties": {
"type": { "const": "bundle" },
"includes": { "type": "array", "items": { "type": "string" } }
},
"required": ["type", "includes"]
}
],
"discriminator": { "propertyName": "type" }
}
{
"if": {
"properties": { "tier": { "const": "flagship" } }
},
"then": {
"required": ["ci_url", "docs_url"]
}
}
{
"status": {
"anyOf": [
{ "enum": ["active", "archived", "draft"] },
{ "type": "string", "pattern": "^x-" }
]
}
}
{
"metadata": {
"type": "object",
"additionalProperties": { "type": "string" },
"propertyNames": { "pattern": "^[a-z_]+$" }
}
}
{
"description": {
"oneOf": [
{ "type": "string" },
{ "type": "null" }
]
}
}
import jsonschema
import json
from pathlib import Path
def validate_entry(data: dict, schema_path: str) -> list[str]:
schema = json.loads(Path(schema_path).read_text())
validator = jsonschema.Draft202012Validator(schema)
errors = sorted(validator.iter_errors(data), key=lambda e: list(e.path))
return [f"{'.'.join(str(p) for p in e.path)}: {e.message}" for e in errors]
| Change | Safe? | Strategy | |--------|-------|----------| | Add optional field | Yes | No version bump needed | | Add required field | No | Major version, provide default | | Remove field | No | Deprecate first, then remove | | Widen type (string → string|number) | Yes | Backward compatible | | Narrow type | No | Major version | | Add enum value | Yes | Consumers should handle unknown | | Remove enum value | No | Deprecate first |
additionalProperties: false — Typos in field names pass silently$defs for reuse$id or $schema — Always specify schema version and identitytesting
Four-phase protocol for clearing accumulated drift between memory claims, CLAUDE.md citations, and on-disk reality. Detects stale citations, missing files, and orphan plans; classifies findings; emits proposed diffs; codifies prevention. Companion to closeout (closeout discovers orphans; this skill polishes them). Discovery ≠ remediation — Phase 3 emits proposed diffs only; constitutional doc edits require explicit conductor authorization.
development
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
testing
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
tools
Craft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.