skill-quality-reviewer

This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report". Evaluates local skills across description quality, content organization, writing style, and structural integrity.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-quality-reviewer/SKILL.md

Quality

Content

61%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 a well-structured, actionable meta-skill with clear sequencing and real, verified reference files. Its weaknesses are conciseness (criteria duplicated across step tables and back-matter) and a missing validation checkpoint for its batch-portfolio mode, which caps workflow clarity.

Suggestions

Add a validation checkpoint to the workflow (e.g., a final step verifying the quality-report and improvement-plan files were written and are non-empty), especially for batch-portfolio mode where many skills are processed at once.

Remove the duplicated scoring criteria from "Common Quality Issues" and "Grade Benchmarks", replacing them with brief pointers to references/scoring-criteria.md to tighten conciseness.

Move the full Quality Report and Improvement Plan templates into references/ (e.g., references/report-templates.md) and inline only concise skeletons, since the detailed scoring rubrics already live in references/scoring-criteria.md.

Dimension	Reasoning	Score
Conciseness	The body duplicates its own criteria: the Step 3-8 scoring tables are restated in "Common Quality Issues" and "Grade Benchmarks", and usage-example narration blocks add padding, fitting the score-3 anchor of mostly-efficient-but-could-be-tightened.	3 / 5
Actionability	Concrete 8-step workflow, point-based scoring tables, a weighted formula, and copy-paste-ready output templates with exact filenames provide mostly-executable guidance; minor gaps are the trivial sole bash example and the absence of shown script invocations with arguments, fitting score-4.	4 / 5
Workflow Clarity	Eight clearly sequenced steps are present, but the batch-portfolio mode reviews many skills at once with no output-validation or verify checkpoint, so the feedback-loops cap limits this to the score-3 anchor.	3 / 5
Progressive Disclosure	Real, verified bundle files (references/, scripts/) are signaled clearly at one level deep, but full scoring tables and report templates that duplicate references/scoring-criteria.md are inlined in the body, the minor organization gap of the score-4 anchor.	4 / 5
	Total	14 / 20 Passed

Description

95%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.

The description is strong: it uses the prescribed third-person "should be used when" trigger format, names five concrete trigger phrases, and clearly states both what it evaluates and when to invoke it. Only minor gap is that it omits mention of the actual outputs (weighted scores, letter grades, improvement plans) it produces.

Dimension	Reasoning	Score
Specificity	"Evaluates local skills across description quality, content organization, writing style, and structural integrity" names the domain plus four concrete evaluation actions, fitting the score-4 anchor with minor coverage gaps (outputs like reports/grades are unstated).	4 / 5
Completeness	It explicitly answers both "what" (Evaluates local skills across four dimensions) and "when" ("This skill should be used when the user asks to..." with concrete trigger phrases), matching the score-5 anchor.	5 / 5
Trigger Term Quality	"analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", "generate quality report" provide comprehensive natural-term coverage with strong synonym variation, matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	The skill-quality-review niche with distinct triggers ("analyze skill quality", "review skill quality") has minimal overlap risk, matching the score-5 anchor.	5 / 5
	Total	19 / 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
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/skill-quality-reviewer/SKILL.md
Commit: 6ed46da

Reviewed: 8 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.