verify
This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality. Invoke explicitly with /verify for pre-commit validation.
69
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/verify/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description focuses almost entirely on when to trigger the skill but fails to explain what it actually does in concrete terms. The domain ('epistemic protocol quality') is unclear and jargon-heavy, making it difficult for Claude to confidently select this skill. The lack of specific actions or outputs is the primary weakness.
Suggestions
Add concrete descriptions of what the skill does, e.g., 'Validates epistemic protocol definitions for structural consistency, checks cross-references between protocols, and reports missing or conflicting entries.'
Clarify the domain by explaining what 'epistemic protocols' are in this context, so Claude can distinguish this from general code validation or linting skills.
Describe the outputs or results of the verification process, e.g., 'Produces a validation report listing errors, warnings, and inconsistencies found in protocol files.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions. Terms like 'verify protocols', 'check consistency', 'validate definitions', and 'verify soundness' are vague and do not describe specific, tangible operations. There is no explanation of what the skill actually does beyond abstract validation language. | 1 / 3 |
Completeness | The 'when' is well-covered with explicit trigger phrases and a 'Use when' equivalent. However, the 'what' is essentially missing — the description never explains what the skill concretely does, what it checks, or what outputs it produces. It only describes when to invoke it, not what it accomplishes. | 2 / 3 |
Trigger Term Quality | It includes several trigger phrases like 'verify protocols', 'check consistency before commit', 'validate definitions', 'run pre-commit checks', and '/verify'. However, these are somewhat niche and jargon-heavy ('epistemic protocol quality'), and the domain is unclear enough that users may not naturally use these terms. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'epistemic protocol quality' and '/verify' command gives it some distinctiveness, but terms like 'check consistency', 'validate definitions', and 'pre-commit checks' could easily overlap with linting, code validation, or general pre-commit hook skills. | 2 / 3 |
Total | 7 / 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 well-crafted skill with excellent workflow clarity, strong actionability through concrete commands and output schemas, and good progressive disclosure via external references. The main weakness is moderate verbosity—the full subagent prompt templates inline add significant length and could potentially be referenced externally, and some sections (Integration Notes) add limited value. Overall, it's a high-quality skill that clearly guides Claude through a complex multi-phase verification process.
Suggestions
Consider moving the full subagent prompt templates to a referenced file (e.g., references/review-checklists.md already mentioned) and keeping only a summary of each perspective's focus inline to reduce token consumption.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-structured, but includes some content that could be tightened—particularly the full subagent prompt templates which are quite verbose and could be referenced externally. The integration notes section adds marginal value. However, most content is domain-specific and not explaining things Claude already knows. | 2 / 3 |
Actionability | Provides fully executable commands (the static checks bash command), specific JSON output schemas, concrete subagent prompt templates, exact output formatting examples, and clear decision-action mappings. The skill is copy-paste ready at every step. | 3 / 3 |
Workflow Clarity | Excellent 5-phase workflow with clear sequencing, explicit validation checkpoints (Phase 3 synthesis, Phase 4 gate interaction), error handling table, feedback loops (fix → re-validate pattern in Phase 5), and graduated severity categorization. The user decision handling provides clear branching logic. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview workflow inline while deferring detailed severity definitions to 'references/criteria.md' and review checklists to 'references/review-checklists.md'—one level deep, clearly signaled. The main document stays navigable with tables and headers while pointing to supporting files. | 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- jongwony/epistemic-protocols
- Commit
9342160
- Reviewed
Table of Contents
Is this your skill?
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.