mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
Dragan Spiridonov
99511738c1
* fix(v3.4.1): bundle missing dependencies and test timeouts - Fixed issue #219: MCP bundle failing due to missing packages - Changed build scripts from --packages=external to selective externalization - Pure JS deps (fast-json-patch, jose, uuid) now bundled inline - Native modules properly externalized (better-sqlite3, hnswlib-node, etc.) - CommonJS modules with dynamic requires externalized (typescript, fast-glob, yaml, commander, cli-progress, ora) - Bundle size reduced from ~15MB to ~5MB - Added timeouts to handleQualityAssess tests to prevent CI failures - Updated version to 3.4.1 Closes #219 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(v3.4.2): add skill validation system with trust tiers (ADR-056) Implement 4-layer skill validation system for deterministic outputs: - Tier 3 (Verified): 46 skills with full eval test suites - Tier 2 (Validated): 7 skills with executable validators - Tier 1 (Structured): 5 skills with JSON output schemas - Tier 0 (Advisory): 5 skills with SKILL.md guidance only Key additions: - JSON Schema validation templates for skill outputs - Executable validator scripts for correctness verification - Evaluation test framework with multi-model support - CLI commands: aqe skill report/summary/compare, aqe eval run/status - ReasoningBank integration for validation pattern learning - GitHub Actions workflow for CI skill validation - Trust tier frontmatter in all 63 skill SKILL.md files - Comprehensive documentation and user guides Infrastructure: - .claude/skills/.validation/ - Templates and frameworks - .claude/skills/*/schemas/ - Output schemas per skill - .claude/skills/*/scripts/ - Validator scripts per skill - .claude/skills/*/evals/ - Test cases per skill Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(ci): trust tier-based skill validation - Tier 3 (Verified): Blocks PR on validation failure - Tier 2 (Validated): Warns only, doesn't block - Tier 1 (Structured): Warns only, doesn't block - Tier 0 (Advisory): Skipped entirely Reads trust_tier from SKILL.md frontmatter to determine validation requirements. Only 46 Tier 3 skills block merge. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(validators): remove local keyword from self-test blocks Shell script fix: 'local' can only be used inside functions, not in if/else blocks. Both accessibility-testing and compatibility-testing validators had 'local' declarations in their self-test sections that caused errors when run outside of a function context. - Remove local test_file from accessibility-testing self-test - Remove local test_file, browser_count, tier1_pass from compatibility-testing self-test - Sync fixes to v3/assets/skills/ Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(validators): add --self-test support to n8n skill validators The 5 n8n skill validators were failing CI because they didn't handle the --self-test flag properly. Added self-test handling that: - Checks for required tools (jq) - Verifies schema file exists and is valid JSON - Returns exit 0 on success Fixed validators: - n8n-expression-testing - n8n-integration-testing-patterns - n8n-security-testing - n8n-trigger-testing-strategies - n8n-workflow-testing-fundamentals Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
146 lines
4.5 KiB
JSON
146 lines
4.5 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
"$id": "https://agentic-qe.dev/schemas/skill-output-template.json",
|
|
"title": "AQE Skill Output Template Schema",
|
|
"description": "Simplified template schema for skill output validation. Use for self-testing validators.",
|
|
"type": "object",
|
|
"required": ["skillName", "version", "timestamp", "status", "output"],
|
|
"properties": {
|
|
"skillName": {
|
|
"type": "string",
|
|
"pattern": "^[a-z][a-z0-9-]*$",
|
|
"minLength": 2,
|
|
"maxLength": 64,
|
|
"description": "Name of the skill that produced this output"
|
|
},
|
|
"version": {
|
|
"type": "string",
|
|
"pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9]+)?$",
|
|
"description": "Semantic version of the skill"
|
|
},
|
|
"timestamp": {
|
|
"type": "string",
|
|
"description": "ISO 8601 timestamp of output generation"
|
|
},
|
|
"status": {
|
|
"type": "string",
|
|
"enum": ["success", "partial", "failed", "skipped"],
|
|
"description": "Overall execution status"
|
|
},
|
|
"trustTier": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"maximum": 3,
|
|
"description": "Trust tier (0-3)"
|
|
},
|
|
"output": {
|
|
"type": "object",
|
|
"description": "Skill-specific output data",
|
|
"properties": {
|
|
"summary": {
|
|
"type": "string",
|
|
"description": "Human-readable summary"
|
|
},
|
|
"findings": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"required": ["id", "title", "severity"],
|
|
"properties": {
|
|
"id": { "type": "string" },
|
|
"title": { "type": "string" },
|
|
"description": { "type": "string" },
|
|
"severity": {
|
|
"type": "string",
|
|
"enum": ["critical", "high", "medium", "low", "info"]
|
|
},
|
|
"category": { "type": "string" },
|
|
"location": {
|
|
"type": "object",
|
|
"properties": {
|
|
"file": { "type": "string" },
|
|
"line": { "type": "integer" }
|
|
}
|
|
},
|
|
"evidence": { "type": "string" }
|
|
}
|
|
},
|
|
"description": "List of findings"
|
|
},
|
|
"recommendations": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"required": ["id", "title", "priority"],
|
|
"properties": {
|
|
"id": { "type": "string" },
|
|
"title": { "type": "string" },
|
|
"description": { "type": "string" },
|
|
"priority": {
|
|
"type": "string",
|
|
"enum": ["critical", "high", "medium", "low"]
|
|
},
|
|
"effort": {
|
|
"type": "string",
|
|
"enum": ["low", "medium", "high"]
|
|
},
|
|
"relatedFindings": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
}
|
|
}
|
|
},
|
|
"description": "Recommendations"
|
|
},
|
|
"metrics": {
|
|
"type": "object",
|
|
"description": "Quantitative metrics"
|
|
},
|
|
"artifacts": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"required": ["type", "path"],
|
|
"properties": {
|
|
"type": {
|
|
"type": "string",
|
|
"enum": ["report", "test", "config", "data", "log"]
|
|
},
|
|
"path": { "type": "string" },
|
|
"format": { "type": "string" },
|
|
"description": { "type": "string" }
|
|
}
|
|
},
|
|
"description": "Generated artifacts"
|
|
}
|
|
}
|
|
},
|
|
"metadata": {
|
|
"type": "object",
|
|
"properties": {
|
|
"executionTimeMs": { "type": "integer", "minimum": 0 },
|
|
"toolsUsed": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
},
|
|
"agentId": { "type": "string" },
|
|
"modelUsed": { "type": "string" },
|
|
"inputHash": { "type": "string" },
|
|
"parentTaskId": { "type": "string" }
|
|
}
|
|
},
|
|
"validation": {
|
|
"type": "object",
|
|
"properties": {
|
|
"schemaValid": { "type": "boolean" },
|
|
"contentValid": { "type": "boolean" },
|
|
"confidence": { "type": "number", "minimum": 0, "maximum": 1 },
|
|
"warnings": {
|
|
"type": "array",
|
|
"items": { "type": "string" }
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|