Validate that implementation matches specs, design, and tasks. Trigger: "verify", "verificar", "validate", "check implementation", "quality gate", "sdd verify", "revisar cambio", "/sdd:verify".
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description has strong trigger term coverage with explicit multilingual keywords and a clear 'Trigger:' clause that answers when to use it. However, the 'what' portion is somewhat vague—it would benefit from listing specific validation actions. The generic nature of 'verify' and 'validate' creates some conflict risk with other validation-related skills.
Suggestions
Add specific concrete actions to the 'what' portion, e.g., 'Compares code implementation against SDD specifications, verifies API contracts match design, checks task completion criteria'
Consider adding more distinctive domain terms like 'SDD compliance', 'spec conformance', or 'design-to-code verification' to reduce overlap with generic validation skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (implementation validation against specs/design/tasks) and describes the general action, but lacks specific concrete actions like 'compare code to requirements', 'check test coverage', or 'verify API contracts'. | 2 / 3 |
Completeness | Clearly answers both what ('Validate that implementation matches specs, design, and tasks') and when (explicit 'Trigger:' clause with multiple specific trigger terms). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'verify', 'validate', 'check implementation', 'quality gate', plus Spanish variants ('verificar', 'revisar cambio') and a command-style trigger ('/sdd:verify'). | 3 / 3 |
Distinctiveness Conflict Risk | The terms 'verify' and 'validate' are fairly generic and could overlap with other validation skills (e.g., data validation, test validation). The 'sdd verify' and '/sdd:verify' triggers help distinguish it, but the core terms remain broad. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill with excellent actionability and workflow clarity. The verification process is thoroughly documented with clear steps, validation checkpoints, and comprehensive error recovery guidance. Minor verbosity in the purpose section and output templates could be tightened, but overall the skill effectively guides Claude through a complex verification workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., the detailed output template could be more condensed, and some explanatory text like 'You are a sub-agent responsible for VERIFICATION' is unnecessary context Claude doesn't need). | 2 / 3 |
Actionability | Provides highly concrete, executable guidance with specific file paths to check, exact command detection logic, clear classification criteria (COMPLIANT/PARTIAL/NOT COMPLIANT), and detailed output templates that are copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with 7 clearly numbered steps, explicit validation checkpoints (Step 2b automated checks), clear decision trees for each step, and comprehensive error recovery table with specific actions for each situation. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to external files (persistence-contract.md, engram-convention.md, openspec-convention.md) that are one level deep and clearly signaled. Content is appropriately organized into logical sections. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
d9bf9a4
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.