loop-verifier

Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.

Quality

78%

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/loop-verifier/SKILL.md

Quality

Content

72%

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

The content is lean and well-organized with a useful output template, but some checklist items are abstract and the verification workflow lacks an explicit feedback/retry loop tying REVISE back to a corrected draft.

Suggestions

Make checklist items measurable, e.g. "Draft length under N items or one screen" and "Every draft line traces to a scan-input line number" rather than subjective checks.

Add an explicit retry path: on REVISE, list the required fixes and re-evaluate the revised draft against the same checklist before re-issuing a verdict.

Specify how breaking/security items must be called out (e.g. a dedicated "⚠️ Breaking / Security" section at the top) so the prominence check is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~40 lines with no padding and no explanation of concepts Claude already knows; every section (Inputs, Checklist, Output) earns its place.	3 / 3
Actionability	The output template is concrete and copy-paste ready, but several checklist items are abstract directives ("Tone matches the project", "Draft is scannable and not overly long") without measurable criteria or examples.	2 / 3
Workflow Clarity	A checklist and verdict tiers (APPROVE/REVISE/ESCALATE_HUMAN) provide a sequence, but there is no explicit validate-fix-retry loop showing how REVISE feedback flows back into a corrected draft.	2 / 3
Progressive Disclosure	A simple skill under 50 lines with no external references, organized into clearly labeled sections (Inputs, Checklist, Output); per the simple-skills note this is well-structured enough to score 3.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 concise, third-person, and answers both what the skill does and when to use it with an explicit trigger. Its main weakness is trigger-term coverage, which leans on the sibling skill name rather than natural user phrasings.

Suggestions

Add natural user-facing trigger terms (e.g. "Use when reviewing or verifying release notes, changelog drafts, or before publishing a changelog") so it surfaces from user requests rather than only after the drafter runs.

Broaden keyword coverage with common variations like "changelog", "release notes", "verify draft", "review notes".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Reviews accuracy against the changelog-scan data, tone, completeness, and flags breaking/security items") rather than vague language.	3 / 3
Completeness	Clearly states what it does (independent checker reviewing accuracy, tone, completeness, breaking/security) and when to use it ("Use after draft-release-notes"), answering both what and when explicitly.	3 / 3
Trigger Term Quality	Includes relevant terms ("release note drafts", "changelog-scan", "breaking/security items") but lacks common variations a user would naturally say; the trigger is tied to a sibling skill rather than user phrasings.	2 / 3
Distinctiveness Conflict Risk	Has a clear niche as a verifier for a specific drafter skill with a distinct trigger ("Use after draft-release-notes"), making overlap with other skills unlikely.	3 / 3
	Total	11 / 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: cobusgreyling/loop-engineering
Path: skills/loop-verifier/SKILL.md
Commit: ffa5bf8

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.