mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
Dragan Spiridonov
56206c7be2
Follow-up tod95f0d7b/2f4d119c— the earlier passes updated .claude/skills and assets/skills but missed several other eval surfaces that still pinned retired IDs (claude-3.5-sonnet, claude-3-haiku): - `.github/workflows/test-qe-browser.yml` — the `aqe eval run --model` flag (inert in command-eval mode, but a real dead-ID leftover) -> claude-sonnet-4-6. - `plugins/agentic-qe-fleet/skills/` — the tracked plugin-marketplace skill copy (8 eval suites + a sample-output fixture); chaos skills get the opus-4-8 ceiling. - `docs/schemas/skill-eval.schema.json` — models `enum` was missing claude-opus-4-8 and still allowed retired/deprecated IDs; trimmed to current+active, default flipped to claude-sonnet-4-6. Plus description examples in the sibling schemas and the modelUsed values in docs/examples/*.json fixtures. - `docs/templates/skill-frontmatter.example.yaml` validation_models list. - `src/cli/commands/eval.ts` — the `aqe eval` `--model` help example and the `run-all --models` default (`claude-3.5-sonnet` -> `claude-sonnet-4-6`). Verified: typecheck clean; all edited JSON/YAML parse; zero retired IDs remain in any eval suite, schema, template, workflow, or eval-CLI default. Intentionally left untouched: the consensus-provider subsystem (pricing tables / type-unions / defaults — separate routing layer, bucket-2 data) and historical release notes / QE audit reports (which document the old IDs by design). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
226 lines
6.8 KiB
YAML
226 lines
6.8 KiB
YAML
# =============================================================================
|
|
# AQE Skill Frontmatter Example
|
|
# Schema: docs/schemas/skill-frontmatter.schema.json
|
|
# =============================================================================
|
|
#
|
|
# This example demonstrates ALL available frontmatter fields for SKILL.md files.
|
|
# Only `name` and `description` are required; all other fields are optional.
|
|
#
|
|
# TRUST TIER SYSTEM (Trust But Verify):
|
|
# - Tier 0: Declarative (SKILL.md only) - Default for all skills
|
|
# - Tier 1: Structured (+ JSON output schema)
|
|
# - Tier 2: Validated (+ executable validator script)
|
|
# - Tier 3: Evaluated (+ evaluation test suite with multi-model testing)
|
|
#
|
|
# =============================================================================
|
|
|
|
---
|
|
# =============================================================================
|
|
# REQUIRED FIELDS
|
|
# =============================================================================
|
|
|
|
name: security-testing
|
|
description: "Test for security vulnerabilities using OWASP principles. Use when conducting security audits, testing auth, or implementing security practices."
|
|
|
|
# =============================================================================
|
|
# CATEGORIZATION (Optional but Recommended)
|
|
# =============================================================================
|
|
|
|
category: specialized-testing
|
|
# Options: qcsd-phases, qe-core, testing-methodologies, test-design,
|
|
# specialized-testing, analysis-review, infrastructure,
|
|
# development-practices, bug-management, platform-skills,
|
|
# learning-skills, orchestration, quality-review
|
|
# Default: qe-core
|
|
|
|
priority: critical
|
|
# Options: critical, high, medium, low
|
|
# Default: medium
|
|
|
|
tags:
|
|
- security
|
|
- owasp
|
|
- sast
|
|
- dast
|
|
- vulnerabilities
|
|
- auth
|
|
- injection
|
|
|
|
# =============================================================================
|
|
# VERSIONING & STATUS
|
|
# =============================================================================
|
|
|
|
version: 2.1.0
|
|
# Semantic version of the skill
|
|
|
|
implementation_status: optimized
|
|
# Options: draft, active, optimized, deprecated
|
|
# Default: active
|
|
|
|
optimization_version: "2.1"
|
|
# Version of optimization applied
|
|
|
|
last_optimized: 2026-02-02
|
|
# Date of last optimization (YYYY-MM-DD)
|
|
|
|
last_updated: 2026-02-02
|
|
# Date of last update (YYYY-MM-DD)
|
|
|
|
# =============================================================================
|
|
# TOKEN & RESOURCE ESTIMATES
|
|
# =============================================================================
|
|
|
|
tokenEstimate: 1500
|
|
# Estimated token count for skill content (100-50000)
|
|
|
|
# =============================================================================
|
|
# AGENT CONFIGURATION
|
|
# =============================================================================
|
|
|
|
# Simple format (array of agent names):
|
|
agents:
|
|
- qe-security-scanner
|
|
- qe-api-contract-validator
|
|
- qe-quality-analyzer
|
|
|
|
# Advanced format (structured with core/conditional):
|
|
# agents:
|
|
# core:
|
|
# - qe-security-scanner
|
|
# - qe-api-contract-validator
|
|
# conditional:
|
|
# - qe-penetration-tester
|
|
# total: 3
|
|
# sub_agents: 0
|
|
|
|
# =============================================================================
|
|
# DDD DOMAIN MAPPING (For QCSD Integration)
|
|
# =============================================================================
|
|
|
|
domains:
|
|
primary:
|
|
- domain: security-compliance
|
|
agents:
|
|
- qe-security-scanner
|
|
- qe-security-auditor
|
|
conditional:
|
|
- domain: quality-assessment
|
|
agents:
|
|
- qe-quality-gate
|
|
|
|
# =============================================================================
|
|
# DEPENDENCIES & REQUIREMENTS
|
|
# =============================================================================
|
|
|
|
dependencies:
|
|
- api-testing-patterns
|
|
- compliance-testing
|
|
|
|
requires:
|
|
- npm audit
|
|
- semgrep (optional)
|
|
- trivy (optional)
|
|
|
|
skills:
|
|
- compliance-testing
|
|
- api-testing-patterns
|
|
|
|
# =============================================================================
|
|
# EXECUTION CONFIGURATION
|
|
# =============================================================================
|
|
|
|
execution:
|
|
primary: task-tool
|
|
# Options: task-tool, mcp-tools, cli, bash
|
|
alternatives:
|
|
- mcp-tools
|
|
- cli
|
|
|
|
swarm_pattern: false
|
|
# Whether skill uses swarm execution pattern
|
|
|
|
parallel_batches: 1
|
|
# Number of parallel agent batches (1-10)
|
|
|
|
# =============================================================================
|
|
# OUTPUT & UI CONFIGURATION
|
|
# =============================================================================
|
|
|
|
quick_reference_card: true
|
|
# Whether skill includes quick reference card
|
|
|
|
html_output: false
|
|
# Whether skill generates HTML output
|
|
|
|
enforcement_level: strict
|
|
# Options: strict, moderate, lenient
|
|
# Default: moderate
|
|
|
|
vibium_integration: optional
|
|
# Options: required, optional, none
|
|
# Default: none
|
|
|
|
# =============================================================================
|
|
# CONTRIBUTOR INFORMATION
|
|
# =============================================================================
|
|
|
|
contributor: "@security-team"
|
|
# GitHub handle of primary contributor
|
|
|
|
# =============================================================================
|
|
# TRUST TIER & VALIDATION (Trust But Verify System)
|
|
# =============================================================================
|
|
|
|
trust_tier: 3
|
|
# Trust tier level (0-3):
|
|
# - 0: Declarative (SKILL.md only) - Default
|
|
# - 1: Structured (requires validation.schema_path)
|
|
# - 2: Validated (requires validation.validator_path)
|
|
# - 3: Evaluated (requires validation.eval_path)
|
|
|
|
validation:
|
|
# Required for trust_tier >= 1
|
|
schema_path: schemas/output.json
|
|
# Path to JSON schema defining expected output structure
|
|
|
|
# Required for trust_tier >= 2
|
|
validator_path: scripts/validate-config.json
|
|
# Path to validator config (cross-platform)
|
|
# Used by: node scripts/validate-skill.cjs
|
|
|
|
# Required for trust_tier >= 3
|
|
eval_path: evals/security-testing.yaml
|
|
# Path to evaluation test suite (YAML)
|
|
|
|
# Validation status tracking
|
|
last_validated: 2026-02-02
|
|
# Date of last successful validation run
|
|
|
|
validation_status: passing
|
|
# Options: passing, failing, skipped, pending, unknown
|
|
# Default: unknown
|
|
|
|
# Multi-model testing configuration
|
|
validation_models:
|
|
- claude-sonnet-4-6
|
|
- claude-haiku-4-5
|
|
- gpt-4o
|
|
|
|
# Evaluation metrics
|
|
pass_rate: 0.95
|
|
# Overall pass rate from evaluation suite (0.0-1.0)
|
|
|
|
critical_pass_rate: 1.0
|
|
# Pass rate for critical test cases only
|
|
|
|
avg_reasoning_quality: 0.87
|
|
# Average reasoning quality score from evaluations
|
|
|
|
cross_model_variance: 0.08
|
|
# Variance in results between different models (<0.15 is good)
|
|
---
|
|
|
|
# Security Testing
|
|
|
|
Your skill content goes here...
|