verification-agent

Provides a structured verification workflow for code and prompt outputs. Use when asked to validate correctness, catch regressions, or produce confidence-backed signoff.

Quality

66%

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 ./skills/verification-agent/SKILL.md

Quality

Content

65%

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

The body is concise, well-structured, and free of redundant explanations. Its main weaknesses are a missing referenced file (strategies.md) and implicit rather than explicit validation checkpoints, which limit standalone actionability.

Suggestions

Provide the missing strategies.md in a references/ bundle, or inline the quick/targeted/deep strategy definitions, so the "Strategy Guide" link is no longer a dangling reference.

Add an explicit validation/feedback checkpoint in the Core Workflow (e.g. "If checks fail or evidence is inconclusive, return to step 2 and revise the strategy") instead of relying on the output contract's implicit "Next step".

Include at least one ready-to-run verification pattern inline so the skill remains actionable when the external file is unavailable.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned with no padding and no explanations of concepts Claude already knows; every line (Purpose, Core Workflow, Minimal Output Contract, Strategy Guide) earns its place, matching the score-3 "lean and efficient; assumes Claude's competence" anchor.	3 / 3
Actionability	The workflow steps and output contract (Status/Evidence/Risk/Next step) give concrete structural guidance, but "Select a strategy (quick, targeted, or deep)" leaves the strategies undefined and the "ready-to-run verification patterns" are deferred to strategies.md, so guidance is actionable but incomplete — score 2.	2 / 3
Workflow Clarity	The Core Workflow is a clearly sequenced 5-step list, but validation/feedback checkpoints are only implicit via the output contract's "Next step: exact follow-up action if needed"; there is no explicit "if checks fail, retry/adjust" loop, fitting score 2 ("steps listed but checkpoints missing or implicit").	2 / 3
Progressive Disclosure	Sections are well-organized and the body signals a one-level-deep reference to strategies.md, but no bundle file exists in references/, scripts/, or assets/, so the referenced file is a dangling pointer and navigation is undermined — score 2 rather than 3.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly answers both what the skill does and when to use it via an explicit third-person trigger clause. Its weaknesses are abstract capability verbs and trigger terms that miss common natural variations, leaving it distinguishable but not maximally concrete.

Suggestions

Replace abstract action verbs with concrete deliverables, e.g. "run tests, diff outputs, and generate a confidence-backed verification report" to lift specificity toward a score of 3.

Broaden trigger coverage with natural terms users actually say — "verify", "check", "confirm", "sign off on" — alongside "validate correctness" and "catch regressions".

Sharpen the niche to reduce overlap with testing/code-review skills by emphasizing the confidence-backed signoff artifact that distinguishes this skill.

Dimension	Reasoning	Score
Specificity	The description "Provides a structured verification workflow for code and prompt outputs" names the domain and some actions ("validate correctness, catch regressions, or produce confidence-backed signoff"), but the actions are abstract verbs rather than multiple concrete operations, matching the score-2 anchor rather than the score-3 "lists multiple specific concrete actions."	2 / 3
Completeness	It explicitly states what the skill does ("Provides a structured verification workflow for code and prompt outputs") and when to use it via an explicit "Use when..." trigger clause, exactly matching the score-3 anchor that answers both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	The "Use when asked to validate correctness, catch regressions, or produce confidence-backed signoff" clause includes natural, relevant phrases, but it misses common variations a user would say ("verify", "check", "confirm", "sign off on"), fitting score 2 ("some relevant keywords but missing common variations").	2 / 3
Distinctiveness Conflict Risk	The verification/signoff niche is somewhat specific, but "validate correctness" and "catch regressions" are generic enough to overlap with general testing or code-review skills, fitting score 2 ("somewhat specific but could still overlap") rather than the clearly-distinct score-3 niche.	2 / 3
	Total	9 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: repowise-dev/claude-code-prompts
Path: skills/verification-agent/SKILL.md
Commit: 989fc0e

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.