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

75%

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

77%

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

A well-sequenced, actionable verification workflow that leans on real bundle files, held back by a broken reference (docs/verification.md) and inline prose that duplicates its own script.

Suggestions

Create the missing docs/verification.md (or remove the reference) so every cited path resolves to a real bundle file.

Trim the 'Checks performed' paragraph to a one-line pointer to scripts/static-checks.js since the script is already declared authoritative.

Consolidate the repeated references to criteria.md and review-checklists.md into a single 'References' section to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tables and phases, but the long 'Checks performed' paragraph explicitly duplicates the script it defers to, and criteria.md/review-checklists.md are cross-referenced more than once.	2 / 3
Actionability	It gives a concrete executable command (node ${SKILL_DIR}/scripts/static-checks.js ${PROJECT_ROOT}) backed by a real script, an explicit JSON output schema, and concrete result/annotation templates.	3 / 3
Workflow Clarity	Five phases are clearly sequenced with severity categorization, an error-handling table, and a fix-then-await-approval feedback loop in Phase 5.	3 / 3
Progressive Disclosure	Structure is a clean overview with one-level-deep references, but the referenced docs/verification.md does not exist in the bundle and the inline 'Checks performed' prose admits it should live in the script/reference.	2 / 3
	Total	10 / 12 Passed

Description

72%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A trigger-rich description with strong "when" guidance and a clear niche, weakened by abstract jargon ("epistemic protocol quality") and a thin, trigger-framed statement of what the skill actually does.

Suggestions

Lead with a concrete capability statement (e.g., 'Runs static protocol checks and parallel expert review, then surfaces findings by severity before commit') before the trigger list, so 'what' is as clear as 'when'.

Replace the abstract phrase 'ensure epistemic protocol quality' with concrete actions the skill performs.

Keep the quoted user utterances but tighten the list to the most natural variations to reduce trigger-framing repetition.

Dimension	Reasoning	Score
Specificity	The description names several actions ("verify protocols", "validate definitions", "run pre-commit checks") but presents them as quoted trigger phrases rather than a clean capability list, and "ensure epistemic protocol quality" is abstract jargon rather than a concrete action.	2 / 3
Completeness	The "when" is answered strongly and explicitly via the trigger clauses, but the "what" is only weakly present (buried "pre-commit validation" and jargon "epistemic protocol quality") rather than a clearly stated concrete capability.	2 / 3
Trigger Term Quality	It explicitly frames natural user utterances ("when the user asks to 'check consistency before commit'", "'run pre-commit checks'") with good coverage of phrasings a developer would actually say.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (epistemic protocol verification before commit) with protocol-specific triggers and an explicit /verify invocation, making conflicts with other skills unlikely.	3 / 3
	Total	10 / 12 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: ab9aa56

Reviewed: 3 days 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.