Validate JSON artifacts against Pydantic schemas, ensuring data integrity throughout the E2E pipeline.
/plugin marketplace add KreativReason/merged-end-to-end-ai-dpp---e2e-cli/plugin install kreativreason-e2e-pipeline@kreativreason-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Validate JSON artifacts against Pydantic schemas, ensuring data integrity throughout the E2E pipeline.
This skill provides utilities for validating pipeline artifacts (PRD, Flow, ERD, Journey, Tasks, ADR, Scaffold) against their defined schemas.
| Artifact | Schema | File |
|---|---|---|
| PRD | PRDModel | app/models.py |
| Flow | FlowModel | app/models.py |
| ERD | ERDModel | app/models.py |
| Journey | JourneyModel | app/models.py |
| Tasks | TasksModel | app/models.py |
| ADR | ADRModel | app/models.py |
| Scaffold | ScaffoldModel | app/models.py |
validate_artifact(artifact_type, data)Validates artifact data against its schema.
Input:
{
"artifact_type": "prd",
"data": { ... artifact JSON ... }
}
Output (Success):
{
"valid": true,
"artifact_type": "prd",
"validation_time": "0.023s",
"warnings": []
}
Output (Failure):
{
"valid": false,
"artifact_type": "prd",
"errors": [
{
"field": "features[0].id",
"error": "Invalid format: expected FR-XXX",
"value": "feature-1"
},
{
"field": "owner_email",
"error": "Field required",
"value": null
}
],
"error_count": 2
}
validate_file(file_path)Validates a JSON file against its inferred schema.
Input:
{
"file_path": "docs/prd.json"
}
Output:
{
"valid": true,
"file_path": "docs/prd.json",
"artifact_type": "prd",
"file_size": "12.5KB",
"validation_time": "0.045s"
}
validate_cross_references()Validates cross-references between artifacts.
Output:
{
"valid": true,
"checks": [
{
"check": "Flow references PRD features",
"status": "pass",
"details": "All 15 flow feature_ids exist in PRD"
},
{
"check": "ERD entities support flows",
"status": "pass",
"details": "All data requirements covered"
},
{
"check": "Tasks reference valid artifacts",
"status": "warning",
"details": "TASK-015 references non-existent FLOW-099"
}
],
"warnings": 1,
"errors": 0
}
get_schema(artifact_type)Returns the schema definition for an artifact type.
Input:
{
"artifact_type": "prd"
}
Output:
{
"artifact_type": "prd",
"schema": {
"type": "object",
"required": ["project_name", "features"],
"properties": {
"project_name": {"type": "string"},
"features": {
"type": "array",
"items": {
"type": "object",
"required": ["id", "title"],
"properties": {
"id": {"type": "string", "pattern": "^FR-\\d{3}$"},
"title": {"type": "string", "minLength": 3}
}
}
}
}
}
}
FR-XXX (e.g., FR-001, FR-002)ST-XXX (e.g., ST-001, ST-002)FLOW-XXX (e.g., FLOW-001)ENT-XXX (e.g., ENT-001)TASK-XXX (e.g., TASK-001)ADR-XXXX (e.g., ADR-0001)All required fields must be present, all references must be valid.
Warnings instead of errors for missing optional fields.
{
"artifact_type": "prd",
"data": { ... },
"mode": "lenient"
}
Minimal validation for work-in-progress artifacts.
{
"artifact_type": "prd",
"data": { ... },
"mode": "draft"
}
Each genesis agent validates output before emitting:
result = agent.generate()
validation = validate_artifact(artifact_type, result)
if not validation.valid:
return error_response(validation.errors)
Run validation across all artifacts:
/kreativreason:validate --all
> Validating pipeline artifacts...
> ✓ docs/prd.json (valid)
> ✓ docs/flows/final_flow.json (valid)
> ✓ docs/erd.json (valid)
> ✓ docs/journey.json (valid)
> ✓ docs/tasks.json (valid)
> ✓ docs/adr/project.json (valid)
>
> Cross-reference check...
> ✓ All references valid
>
> Result: All artifacts valid
| Error Code | Description | Resolution |
|---|---|---|
MISSING_REQUIRED | Required field missing | Add the field |
INVALID_ID_FORMAT | ID doesn't match pattern | Fix ID format |
DUPLICATE_ID | ID already exists | Use unique ID |
INVALID_REFERENCE | Referenced ID not found | Fix reference |
TYPE_MISMATCH | Wrong data type | Fix value type |
CONSTRAINT_VIOLATION | Value doesn't meet constraint | Fix value |
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.