Auto-generated from skills/verify/SKILL.md

Source: https://github.com/yonatangross/orchestkit

Verify Feature

Comprehensive verification using parallel specialized agents with nuanced grading (0-10 scale) and improvement suggestions.

Quick Start

/verify authentication flow
/verify user profile feature
/verify --scope=backend database migrations

STEP 0: Verify User Intent with AskUserQuestion

BEFORE creating tasks, clarify verification scope:

AskUserQuestion(
  questions=[{
    "question": "What scope for this verification?",
    "header": "Scope",
    "options": [
      {"label": "Full verification (Recommended)", "description": "All tests + security + code quality + grades"},
      {"label": "Tests only", "description": "Run unit + integration + e2e tests"},
      {"label": "Security audit", "description": "Focus on security vulnerabilities"},
      {"label": "Code quality", "description": "Lint, types, complexity analysis"},
      {"label": "Quick check", "description": "Just run tests, skip detailed analysis"}
    ],
    "multiSelect": false
  }]
)

Based on answer, adjust workflow:

• Full verification: All 8 phases, all 5 parallel agents
• Tests only: Skip phases 2 (security), 5 (UI/UX analysis)
• Security audit: Focus on security-auditor agent
• Code quality: Focus on code-quality-reviewer agent
• Quick check: Run tests only, skip grading and suggestions

Task Management (CC 2.1.16)

# Create main verification task
TaskCreate(
  subject="Verify [feature-name] implementation",
  description="Comprehensive verification with nuanced grading",
  activeForm="Verifying [feature-name] implementation"
)

# Create subtasks for 8-phase process
phases = ["Run code quality checks", "Execute security audit",
          "Verify test coverage", "Validate API", "Check UI/UX",
          "Calculate grades", "Generate suggestions", "Compile report"]
for phase in phases:
    TaskCreate(subject=phase, activeForm=f"{phase}ing")

Workflow Overview

Phase	Activities	Output
1. Context Gathering	Git diff, commit history	Changes summary
2. Parallel Agent Dispatch	5 agents evaluate	0-10 scores
3. Test Execution	Backend + frontend tests	Coverage data
4. Nuanced Grading	Composite score calculation	Grade (A-F)
5. Improvement Suggestions	Effort vs impact analysis	Prioritized list
6. Alternative Comparison	Compare approaches (optional)	Recommendation
7. Metrics Tracking	Trend analysis	Historical data
8. Report Compilation	Evidence artifacts	Final report

Phase 1: Context Gathering

# PARALLEL - Run in ONE message
git diff main --stat
git log main..HEAD --oneline
git diff main --name-only | sort -u

Phase 2: Parallel Agent Dispatch (5 Agents)

Launch ALL agents in ONE message with run_in_background=True.

Agent	Focus	Output
code-quality-reviewer	Lint, types, patterns	Quality 0-10
security-auditor	OWASP, secrets, CVEs	Security 0-10
test-generator	Coverage, test quality	Coverage 0-10
backend-system-architect	API design, async	API 0-10
frontend-ui-developer	React 19, Zod, a11y	UI 0-10

See Grading Rubric for detailed scoring criteria.

Phase 3: Parallel Test Execution

# PARALLEL - Backend and frontend
cd backend && poetry run pytest tests/ -v --cov=app --cov-report=json
cd frontend && npm run test -- --coverage

Phase 4: Nuanced Grading

See Grading Rubric for full scoring details.

Weights:

Dimension	Weight
Code Quality	20%
Security	25%
Test Coverage	20%
API Compliance	20%
UI Compliance	15%

Grade Interpretation:

Score	Grade	Action
9.0-10.0	A+	Ship it!
8.0-8.9	A	Ready for merge
7.0-7.9	B	Minor improvements optional
6.0-6.9	C	Consider improvements
5.0-5.9	D	Improvements recommended
0.0-4.9	F	Do not merge

Phase 5: Improvement Suggestions

Each suggestion includes effort (1-5) and impact (1-5) with priority = impact/effort.

Points	Effort	Impact
1	< 15 min	Minimal
2	15-60 min	Low
3	1-4 hrs	Medium
4	4-8 hrs	High
5	1+ days	Critical

Quick Wins: Effort <= 2 AND Impact >= 4

Phase 6: Alternative Comparison (Optional)

See Alternative Comparison for template.

Use when:

• Multiple valid approaches exist
• User asked "is this the best way?"
• Major architectural decisions made

Phase 7: Metrics Tracking

mcp__memory__create_entities(entities=[{
  "name": "verification-{date}-{feature}",
  "entityType": "VerificationMetrics",
  "observations": [f"composite_score: {score}", ...]
}])

Query trends: mcp__memory__search_nodes(query="VerificationMetrics")

Phase 8: Report Compilation

See Report Template for full format.

# Feature Verification Report

**Composite Score: [N.N]/10** (Grade: [LETTER])

## Top Improvement Suggestions
| # | Suggestion | Effort | Impact | Priority |
|---|------------|--------|--------|----------|
| 1 | [highest] | [N] | [N] | [N.N] |

## Verdict
**[READY FOR MERGE | IMPROVEMENTS RECOMMENDED | BLOCKED]**

Policy-as-Code

See Policy-as-Code for configuration.

Define verification rules in .claude/policies/verification-policy.json:

{
  "thresholds": {
    "composite_minimum": 6.0,
    "security_minimum": 7.0,
    "coverage_minimum": 70
  },
  "blocking_rules": [
    {"dimension": "security", "below": 5.0, "action": "block"}
  ]
}

Key Decisions

Decision	Choice	Rationale
Scoring scale	0-10 with decimals	Nuanced, not binary
Improvement priority	Impact / Effort ratio	Do high-value first
Alternative comparison	Optional phase	Only when multiple valid approaches
Metrics persistence	Memory MCP	Track trends over time

Related Skills

• implement - Full implementation with verification
• review-pr - PR-specific verification
• run-tests - Detailed test execution
• quality-gates - Quality gate patterns

Version: 3.0.0 (January 2026)