verification-loop

This skill should be used when the user asks to "verify code", "run verification", "check quality", "validate changes", or before creating a PR. Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

92%

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

The body is well-structured and highly actionable with a clear phased workflow and explicit stop-and-fix checkpoints. Its main weakness is progressive disclosure: a referenced example file is missing and the report template is duplicated inline.

Suggestions

Create the missing examples/example-verification-report.md file referenced in the Reference Files section, or remove the dangling reference so navigation is not broken.

Avoid duplicating references/REPORT-TEMPLATE.md inline in the Output Format section; either reference it or keep the content in only one place.

Consider moving the full per-language command matrices (Python/Node variants) into references/ and keeping SKILL.md to a single representative command per phase to tighten token use.

Dimension	Reasoning	Score
Conciseness	The body is lean: terse per-phase command blocks with output-piping (e.g. "uv build 2>&1 \| tail -20") and minimal prose, assuming Claude's competence without explaining build/test concepts. Not a 2 because there is no padded concept explanation; the brief Continuous Mode and Hooks sections are short and earn their place.	3 / 3
Actionability	Provides copy-paste-ready executable commands per phase (uv/npm/pnpm build, npx tsc, ruff check, pytest --cov, pip-audit, git diff). Not a 2 because the examples are complete and executable rather than pseudocode or abstract descriptions.	3 / 3
Workflow Clarity	Sequences six numbered phases with explicit feedback checkpoints: "If build fails, STOP and fix before continuing" and "Fix critical ones before continuing". Not a 2 because validation/stop-gates are explicit, and the operations are read-only scans rather than destructive batch ops that would cap the score.	3 / 3
Progressive Disclosure	References are one level deep and clearly signaled via a "Reference Files" section, but "examples/example-verification-report.md" is referenced yet does not exist (no examples/ directory), and the inline Output Format block duplicates references/REPORT-TEMPLATE.md. Not a 3 because navigation is broken by the dangling path and some separately-filed content is duplicated inline; not a 1 because references are not deeply nested and the structure is otherwise organized.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 excellent: it states concrete capabilities, gives natural trigger terms, and explicitly covers both what and when in third-person voice. It matches the strongest rubric anchors across all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "build, type check, lint, tests, security scan, and diff review" rather than vague language. Not below 3 since it enumerates a comprehensive set of specific verification actions; not a 2 because it is far more than naming a domain and some actions.	3 / 3
Completeness	Explicitly answers both what ("Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review") and when ("should be used when the user asks to ... or before creating a PR"). Not a 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes natural phrasing users would actually say: "verify code", "run verification", "check quality", "validate changes", and "before creating a PR". Not a 2 because these cover common natural variations rather than only technical jargon or a single keyword.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (pre-PR verification) with distinct triggers unlikely to fire for unrelated skills. Not a 2 because the combination of verification phases plus PR-creation trigger is specific and not a generic overlap with other skills.	3 / 3
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/verification-loop/SKILL.md
Commit: 2f7766f

Reviewed: about 13 hours 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.