skill-reviewer

Identify improvement opportunities in Claude Code skills through targeted review operations. Complements review-multi by focusing on actionable improvements rather than scoring. Use when seeking specific improvements, conducting improvement-focused reviews, or identifying enhancement opportunities for existing skills.

Quality

62%

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/skill-reviewer/SKILL.md

Quality

Content

46%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 body is well organized and appropriately brief, but the four operations are framed as vague prompts rather than executable review procedures — no criteria, heuristics, output format, or worked example is given. It reads as a table of contents for a review process that was never written.

Suggestions

Replace the abstract per-step questions with concrete review heuristics: what to check in examples (specificity, edge cases, runnable code), what friction signals to look for in usage, and how to judge an integration opportunity.

Specify the output format for each operation, e.g., a structured improvement item with priority, evidence quote, and suggested change, so results are comparable across reviews.

Cut the redundant Quick Reference table (it duplicates the Operations section) or cut the Operations detail and keep only the table plus concrete procedures.

Dimension	Reasoning	Score
Conciseness	The body is structured and free of concept over-explanation, but the Quick Reference table restates the four operations almost verbatim, and the review-multi integration is explained twice (Overview and "Use with"). Noticeable redundancy keeps it below 4.	3 / 5
Actionability	Process steps are abstract questions ("Test actual usage - where's friction?", "Review examples - could any be more concrete/helpful?") with no concrete review method, criteria, output format, or example deliverable. It describes what to think about rather than instructing how to execute, matching the minimal-guidance anchor.	2 / 5
Workflow Clarity	Each operation lists a coherent 4-step sequence, but no validation checkpoints or feedback loops exist (e.g., how to verify a found improvement is real, or how to prioritize the output list). The operations are read-only, so the destructive-cap rule does not apply.	3 / 5
Progressive Disclosure	No bundle files exist and none are needed at this size; the body is well organized with clear section headers, a consistent per-operation structure, and easy navigation. Minor gaps — the redundant summary table and repeated integration notes — keep it from 5.	4 / 5
	Total	12 / 20 Passed

Description

62%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.

A solid description with an explicit "Use when" clause, correct third-person voice, and deliberate positioning against review-multi. Its main weaknesses are an abstract "what" and repetitive, narrow trigger phrasing that misses natural synonyms.

Suggestions

Enumerate the concrete operations in the description (e.g., "run content, usability, integration, and efficiency reviews to produce prioritized improvement lists") to raise specificity.

Diversify trigger terms with natural user phrasings such as "make a good skill better", "find improvements", or "plan skill enhancements" instead of three variants of "improvement opportunities".

Dimension	Reasoning	Score
Specificity	"Identify improvement opportunities in Claude Code skills through targeted review operations" names the domain and one concrete action, but does not enumerate what the targeted review operations are. It stops short of the several specific actions needed for a 4.	3 / 5
Completeness	Both a "what" (identify improvement opportunities via targeted review operations) and an explicit "when" with multiple trigger phrases are present. Not a 5 because the "what" remains abstract — the nature of the review operations is never made concrete.	4 / 5
Trigger Term Quality	The "Use when" clause offers three trigger phrases ("seeking specific improvements", "conducting improvement-focused reviews", "identifying enhancement opportunities"), but these are near-synonyms of one concept rather than diverse natural phrasings; common variations like "make this skill better" or "refine" are missing.	3 / 5
Distinctiveness Conflict Risk	"Complements review-multi by focusing on actionable improvements rather than scoring" explicitly differentiates it from the closest sibling skill. Minor overlap risk remains with general skill-review or skill-updater skills, so not a 5.	4 / 5
	Total	14 / 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: fernandezbaptiste/Skrillz
Path: skills/skill-reviewer/SKILL.md
Commit: 93ed392

Reviewed: 14 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.