skill-reviewer
Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills.
81
71%
Does it follow best practices?
Impact
100%
1.33xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skill-reviewer/SKILL.mdQuality
Discovery
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.
This is a well-crafted description that clearly communicates what the skill does (reviews/improves Claude Code skills in three modes) and when to use it. The three-mode breakdown adds excellent specificity. The main weakness is that trigger terms could be broader to capture more natural user phrasings.
Suggestions
Add more natural trigger term variations such as 'SKILL.md', 'lint skills', 'skill validation', or 'skill best practices' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Reviews and improves Claude Code skills', and describes three distinct modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (reviews and improves skills against best practices, with three specific modes) and 'when' (explicit 'Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills'). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'skill quality', 'skill repositories', 'open-source skills', 'review', 'improve', but misses natural variations users might say such as 'lint skills', 'skill validation', 'best practices check', 'SKILL.md', or 'skill file'. The terms are somewhat niche and may not cover all natural phrasings. | 2 / 3 |
Distinctiveness Conflict Risk | Very clear niche - specifically about reviewing and improving Claude Code skills against best practices. The three modes (self-review, external review, auto-PR) and the focus on 'skills' as the domain make it highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-structured with clear modes of operation, good progressive disclosure, and useful concrete examples for common issues and PR etiquette. Its main weaknesses are in workflow clarity (missing feedback loops and error recovery paths) and actionability (some workflows are abstract checklists rather than executable sequences). The 'Additive Only' principle and PR guidelines sections are particularly strong and well-illustrated.
Suggestions
Add explicit feedback loops to the Auto-PR and External Review workflows (e.g., 'If respect check fails → identify violating changes → revert or convert to additive → re-run check')
Provide fallback instructions for when the skill-creator plugin is unavailable, so the manual evaluation path is fully actionable without external dependencies
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary structure like the setup section with bash commands for installing a specific plugin that may not be universally applicable. The checklist table and multiple mode descriptions add bulk, though most content earns its place. | 2 / 3 |
Actionability | Provides concrete examples for common issues (YAML fixes, PR tone), executable bash commands for setup and validation, and checklists. However, the core review workflows are presented as checkbox lists rather than executable steps, and the validation scripts reference external tools without fallback guidance if they're unavailable. | 2 / 3 |
Workflow Clarity | Three modes are clearly delineated with checklists, but the workflows lack explicit validation checkpoints and feedback loops. For example, the Auto-PR workflow lists steps but doesn't specify what to do if the 'respect check' fails, and the External Review workflow doesn't include a validation-before-reporting step. | 2 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to evaluation_checklist.md, pr_template.md, and marketplace_template.json. The quick checklist is inline while the full version is referenced externally. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%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
- fernandezbaptiste/claude-code-skills
- Commit
4f0eae8
- Reviewed
Table of Contents
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.