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.
Install with Tessl CLI
npx tessl i github:fernandezbaptiste/claude-code-skills --skill skill-reviewer83
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 strong description that clearly explains what the skill does (reviews/improves Claude Code skills in three modes) and when to use it. The main weakness is trigger term coverage - while it includes some natural keywords, it could benefit from additional variations that users might naturally say when needing skill validation or improvement.
Suggestions
Add more natural trigger terms users might say, such as 'lint skill', 'validate skill.md', 'skill best practices', or 'improve my skill file'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Reviews and improves Claude Code skills', 'validate your own skills', 'evaluate others' skills', 'fork, improve, submit'. Clearly describes three distinct modes of operation. | 3 / 3 |
Completeness | Clearly answers both what ('Reviews and improves Claude Code skills against official best practices' with three modes) AND when ('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', but missing natural variations users might say like 'lint skill', 'check my skill.md', 'skill validation', or 'skill best practices'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche focused on 'Claude Code skills' and 'skill repositories' - unlikely to conflict with general code review or documentation skills. The three modes (self-review, external review, auto-PR) create clear boundaries. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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, concrete examples, and good progressive disclosure to reference files. The main weaknesses are missing validation/feedback loops in workflows (especially for the Auto-PR mode which involves destructive-adjacent operations) and some verbosity in the setup section that could be trimmed.
Suggestions
Add explicit validation checkpoints to the Auto-PR workflow (e.g., 'If respect check fails: revert changes and re-evaluate before proceeding')
Trim the setup section's bash comments - Claude understands what 'find' and 'if' statements do without inline explanations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some redundancy (e.g., the setup section's bash comments explain obvious steps). The checklist table and common issues sections are well-structured but could be tighter. | 2 / 3 |
Actionability | Provides concrete, executable bash commands, specific YAML before/after examples, and copy-paste ready checklists. The three modes have clear workflows with actionable steps. | 3 / 3 |
Workflow Clarity | Workflows are listed with checkboxes but lack explicit validation checkpoints and feedback loops. The Auto-PR workflow mentions 'respect check passed?' but doesn't specify what to do if it fails. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview, three distinct modes, and well-signaled one-level-deep references to external files (evaluation_checklist.md, pr_template.md, marketplace_template.json). | 3 / 3 |
Total | 10 / 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.
- 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.