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.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/verify/SKILL.md

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, actionable verification workflow with explicit validation, error-recovery feedback loops, and clean one-level-deep references to real bundle files. It is efficient rather than padded, with only minor verbosity in the inline check inventory and the output examples.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient: it uses compact tables for principles, severity, and error handling and assumes Claude's competence without explaining basic concepts. Minor trimming opportunities remain, notably the dense inline 'Checks performed' paragraph and the two full output-example blocks that partly restate the Phase 4 format.	4 / 5
Actionability	Provides a concrete executable command (`node ${SKILL_DIR}/scripts/static-checks.js ${PROJECT_ROOT}`), a JSON output schema, an explicit gate-interaction format with numbered options, and decision/error tables. The only minor gap is that the parallel Task subagent invocation is described in prose rather than shown as a copy-paste-ready call.	4 / 5
Workflow Clarity	Five phases are clearly sequenced (Static Checks -> Expert Review -> Synthesize -> Surface via Gate -> Handle Decision) with an explicit validation checkpoint (pass/fail/warn) before synthesis and feedback loops for error recovery (subagent timeout -> partial results; decision branches). This matches the anchor 5 example of a clear sequence with validation and recovery loops.	5 / 5
Progressive Disclosure	The body is an overview that points one level deep to real, well-signaled references (`references/verification.md`, `references/criteria.md`, `references/review-checklists.md`) and the `scripts/static-checks.js` check inventory, with content appropriately split (severity criteria, templates, and rationale each in their own file).	5 / 5
	Total	18 / 20 Passed

Description

70%Weight 40%Scale 1-5

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 is third-person, triggers are explicit and well-supplied with synonyms, and the 'when' guidance is concrete with a named slash command. Its main weakness is that the 'what' is expressed as a cluster of near-synonymous verify/check/validate verbs rather than distinct named capabilities, so it never reveals what the skill actually does.

Suggestions

Lead with one concrete capability statement (e.g. 'Runs static checks and parallel expert review of epistemic protocol definitions') so the 'what' is explicit rather than inferred from trigger verbs.

Collapse the redundant verify/check/validate trigger variants and add one or two truly distinct actions to broaden specificity.

Tighten 'ensure epistemic protocol quality' toward a phrase a user would naturally say, since it currently reads as jargon.

Dimension	Reasoning	Score
Specificity	Names the domain (epistemic protocol verification) and several action verbs ('verify protocols', 'check consistency before commit', 'validate definitions'), but these are variations of one verify/check/validate theme rather than multiple distinct concrete capabilities; it never states the actual mechanism (static checks + expert review).	3 / 5
Completeness	Has both a 'what' (verify/validate epistemic protocols) and an explicit, specific 'when' (multiple concrete trigger phrases plus 'Invoke explicitly with /verify for pre-commit validation'), but the 'what' is conveyed only through action verbs rather than a crisp capability statement, keeping it just below the anchor 5 example.	4 / 5
Trigger Term Quality	Good coverage of natural synonyms a user might say ('verify protocols', 'check consistency before commit', 'run pre-commit checks') plus an explicit '/verify' invocation, though some phrases like 'verify soundness' and 'ensure epistemic protocol quality' lean technical.	4 / 5
Distinctiveness Conflict Risk	The epistemic-protocol framing is a fairly distinct niche with specific triggers, but generic terms like 'verify' and 'run pre-commit checks' create minor overlap risk with general commit/verification helpers.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: jongwony/epistemic-protocols
Path: .claude/skills/verify/SKILL.md
Commit: 3ffe94c

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.