skill-reviewer

Evaluate a SKILL.md for quality. An agent that dynamically discovers the rubric files and scores the skill against each, producing one result per rubric. Use when running a skill review workflow or testing skill quality against configurable rubrics.

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 ./default-skill-review/skills/skill-reviewer/SKILL.md

The canonical home for this skill is tessl/default-skill-review

Quality

Content

85%Scale 1-5

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

This is a well-structured, highly actionable skill that provides clear step-by-step instructions for evaluating SKILL.md files against rubrics. Its strengths are the precise workflow sequencing, concrete output schemas, and explicit computation formulas. Minor weaknesses include some redundancy in the reminders section and the fact that all content is inlined rather than leveraging bundle files for schemas and detailed specifications.

Suggestions

Consider moving the detailed JSON output schema and scoring formulas into a referenced bundle file (e.g., references/scoring.md) to improve progressive disclosure and reduce inline content length.

Remove or trim the 'Important reminders' section, as most points restate instructions already given in the steps above.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient and well-structured, but includes some minor verbosity such as the 'Important reminders' section which partially restates things already covered in the steps, and some explanations that Claude could infer (e.g., explaining what YAML frontmatter is).	4 / 5
Actionability	The skill provides fully concrete, executable guidance: exact JSON output schemas, specific file paths to read, precise formulas for computing scores, and clear data structures. Every step has specific instructions on what to read, compute, and write.	5 / 5
Workflow Clarity	The 5-step workflow is clearly sequenced with explicit dependencies between steps. It includes validation considerations (checking evaluation_target, handling judge failures with success: false and errorMessage), and the process flows logically from reading inputs through computation to writing results.	5 / 5
Progressive Disclosure	The skill references external files (rubrics/*.json, config.json, schemas/results.schema.json) appropriately, but no bundle files are provided to verify these references exist. The content itself is moderately long (~100 lines) and could benefit from separating the output schema details or scoring formulas into referenced files rather than inlining everything.	3 / 5
	Total	17 / 20 Passed

Description

71%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 adequately covers both what the skill does and when to use it, earning high marks on completeness. However, it could be more specific about the concrete actions performed (e.g., what dimensions are scored, what the output format looks like) and could include more natural trigger terms that users might use when requesting a skill quality review. The distinctiveness is reasonably good given the narrow domain.

Suggestions

Add more natural trigger terms and synonyms such as 'grade', 'lint', 'check skill quality', 'review skill description', or 'validate SKILL.md' to improve discoverability.

Increase specificity by mentioning concrete outputs or actions, e.g., 'produces per-dimension scores, reasoning, and actionable suggestions in JSON format'.

Dimension	Reasoning	Score
Specificity	Names the domain ('evaluate a SKILL.md') and a couple of concrete actions ('dynamically discovers rubric files', 'scores the skill against each', 'producing one result per rubric'), but doesn't elaborate on what the evaluation entails or what outputs look like beyond 'one result per rubric'.	3 / 5
Completeness	Clearly answers both 'what' ('Evaluate a SKILL.md for quality... dynamically discovers rubric files and scores the skill against each, producing one result per rubric') and 'when' ('Use when running a skill review workflow or testing skill quality against configurable rubrics') with explicit trigger phrases.	5 / 5
Trigger Term Quality	Includes some relevant keywords like 'SKILL.md', 'rubric', 'skill review', 'skill quality', and 'scoring', but misses natural user phrases like 'grade a skill', 'check skill description', 'lint skill', 'quality check', or 'review skill file'. The terms are somewhat niche and may not match how users naturally phrase requests.	3 / 5
Distinctiveness Conflict Risk	Fairly distinct — evaluating SKILL.md files against rubrics is a narrow niche. However, there could be minor overlap with other skill-linting or documentation-review skills. The mention of 'configurable rubrics' and 'SKILL.md' specifically helps differentiate it.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: tesslio/product-plugins
Path: default-skill-review/skills/skill-reviewer/SKILL.md
Commit: 37f0a21

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.