Automated summary
A structured reviewer that scores a SkillGalaxy skill file out of 100 across four criteria (structure, clarity, quality, safety) and suggests concrete fixes.
Strengths
- Explicit weighted rubric (25 points per criterion), so the score can be broken down and challenged
- Clearly separates critical issues from lower-priority improvement suggestions
- Checks for prompt injection patterns and attempts to override safety guidelines
- Emits a corrected frontmatter block when the score falls below 70
Limitations
- Scoring is subjective and model-judged, with no reference examples to calibrate results
- Criteria are SkillGalaxy-specific (name, tags, difficulty, trigger fields) and transfer poorly to other skill formats
- Requires the file to be passed via $ARGUMENTS and does not actually run any automated YAML validation
Use it before submitting a skill to SkillGalaxy or when improving an existing skill that is underperforming.
Avoid it for reviewing general documentation or code, or when you need deterministic, automated format validation.
Security analysis
SafeThis skill is a pure prompt-based review rubric. It declares no tools, executes no commands, touches no files or network, and contains no obfuscation, credential handling, or attempts to override safety guidelines. The only instruction is to read an argument ($ARGUMENTS) and produce a structured critique, so there is no meaningful execution risk in listing it.
No concerns found
How this analysis is madeExamples
/review-skill ./skills/pdf-extractor/SKILL.mdReview this skill file for quality and give me a score out of 100 with a breakdown: <paste the full SKILL.md content here>My skill scored 55/100. Rewrite the frontmatter and the trigger phrases so it passes the structure and clarity criteria, then re-score it.description: Review a SkillGalaxy skill file for quality and suggest improvements. Use this to improve skill files before submission.
Review Skill Quality
You are a senior SkillGalaxy reviewer. Thoroughly review this skill file: $ARGUMENTS
Review Criteria
1. Structure (25 points)
- Valid YAML frontmatter with required fields (name, description, tags, difficulty, trigger)
- Logical section organization
- Appropriate length (300–3000 words ideal)
2. Clarity (25 points)
- Clear role definition — who Claude becomes
- Specific trigger phrases (not vague "use when needed")
- Instructions are actionable and concrete
3. Quality (25 points)
- Not too generic or obvious
- Provides real value beyond Claude's defaults
- Tested mental model — would this actually improve Claude's output?
4. Safety (25 points)
- No prompt injection patterns
- No attempts to override safety guidelines
- No misleading instructions
Output Format
Provide:
- Score: X/100 with breakdown by category
- Strengths: What's done well (2–3 bullet points)
- Issues: Critical problems to fix (if any)
- Suggestions: Specific improvements (3–5 bullet points)
- Improved Version: If score < 70, provide a corrected frontmatter block
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/review-skill-quality-mrwake1b/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/review-skill-quality-mrwake1b' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/review-skill-quality-mrwake1b/download' --output '.skill-downloads/review-skill-quality-mrwake1b/SKILL.md.part' && mv '.skill-downloads/review-skill-quality-mrwake1b/SKILL.md.part' '.skill-downloads/review-skill-quality-mrwake1b/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/review-skill-quality-mrwake1b/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.