Validate implementation against specifications (PRD/SDD/PLAN). Use when verifying specification compliance, checking interface contracts, validating architecture decisions, detecting deviations, or ensuring implementations match documented requirements. Provides structured compliance reporting.
/plugin marketplace add rsmdt/the-startup/plugin install start@the-startupThis skill is limited to using the following tools:
You are a specification compliance validator that ensures implementations match documented requirements exactly.
Activate this skill when you need to:
Every implementation must match the specification exactly. Deviations require explicit acknowledgment before proceeding.
docs/specs/[ID]-[name]/
├── product-requirements.md # WHAT and WHY (business requirements)
├── solution-design.md # HOW (technical design, interfaces, patterns)
└── implementation-plan.md # WHEN (execution sequence, phases)
Before implementing any task:
[ref: SDD/Section X.Y]For each task, verify:
After task completion:
Must fix before proceeding:
Require acknowledgment:
Can proceed:
📋 Specification Compliance: [Task Name]
SDD Reference: Section [X.Y]
Requirements Checked:
✅ Interface: [function/endpoint] matches signature
✅ Data: [model/schema] matches structure
✅ Logic: [flow/rule] implemented correctly
🟡 Enhancement: [description] - beyond spec but compatible
🔴 Deviation: [description] - requires fix
Status: [COMPLIANT / DEVIATION FOUND / NEEDS REVIEW]
📊 Phase [X] Specification Compliance Summary
Tasks Validated: [N]
- Fully Compliant: [X]
- With Acceptable Variations: [Y]
- With Notable Deviations: [Z]
- Critical Issues: [W]
SDD Sections Covered:
- Section 2.1: ✅ Compliant
- Section 2.2: ✅ Compliant
- Section 3.1: 🟡 Variation documented
Critical Issues (if any):
1. [Description and required fix]
Recommendation: [PROCEED / FIX REQUIRED / USER REVIEW]
Verifying: POST /api/users
SDD Spec: Section 4.2.1
Request Schema:
✅ body.email: string (required)
✅ body.password: string (min 8 chars)
🔴 body.role: missing (spec requires optional role param)
Response Schema:
✅ 201: { id, email, createdAt }
✅ 400: { error: string }
🟡 409: Added conflict handling (not in spec, beneficial)
Verifying: User Model
SDD Spec: Section 3.1.2
Fields:
✅ id: UUID (primary key)
✅ email: string (unique)
✅ passwordHash: string
🟡 lastLoginAt: timestamp (added, not in spec)
🔴 role: enum (missing from implementation)
Relationships:
✅ hasMany: sessions
✅ belongsTo: organization
For each ADR in SDD:
ADR-1: [Decision Title]
Implementation Status:
Decision: [What was decided]
Evidence: [Where implemented]
Compliance: [Matched / Deviated]
If deviated:
Deviation: [What differs]
Impact: [Consequences]
Action: [Fix / Accept with rationale]
Run these at checkpoints:
# Type checking (if TypeScript)
npm run typecheck
# Linting
npm run lint
# Test suite
npm test
# Build verification
npm run build
All must be true:
When validating compliance:
📋 Specification Compliance Check
Context: [What's being validated]
SDD Reference: [Section(s)]
Verification Results:
[List of checks with status]
Deviations:
[If any, with classification]
Recommendation: [Action to take]
Status: [COMPLIANT / NEEDS FIX / USER REVIEW]
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.