ReddRadar
Agent skill
skill-quality
Scores Claude Code skills (1-5) across 6 weighted quality dimensions aligned with official Anthropic docs. Use when evaluating skill quality, rating skills, scoring customizations, comparing skill effectiveness, or checking if a skill follows best practices. Produces per-dimension scores with evidence, weighted totals, quality tier classification, and actionable improvement recommendations.
Install this agent skill to your Project
npx add-skill https://github.com/philoserf/claude-code-setup/tree/main/skills/skill-quality
SKILL.md
Reference Files
- scoring-guide.md - Unified rubric: dimension definitions, 1-5 criteria, evidence checklist, scoring tips
- examples.md - Real skill assessments (vc-ship, let-fate-decide, cc-lint) showing scoring in action
- report-template.md - Output formats: full report, abbreviated, and comparison
Quality Dimensions (Weighted)
| Dimension | Weight | Focus |
|---|---|---|
| Effectiveness | 28% | Does it achieve its stated purpose? |
| Clarity | 22% | Is it understandable to Claude and maintainers? |
| Best Practices | 17% | Follows official Claude Code skill design patterns |
| Documentation | 15% | Completeness and organization of supporting docs |
| Verification | 10% | Can you confirm the output is correct? |
| Trigger Coverage | 8% | Will users discover and invoke it? |
Quality Tiers
| Range | Tier |
|---|---|
| 4.5-5.0 | Production Ready |
| 3.5-4.4 | Good |
| 2.5-3.4 | Needs Work |
| 1.5-2.4 | Poor |
| 1.0-1.4 | Unusable |
Evaluation Process
- Locate the skill directory — find SKILL.md and all supporting files
- Measure SKILL.md size (lines, words) and count reference files
- Validate frontmatter against the documented field list
- Score each dimension using the rubric in scoring-guide.md
- Calculate weighted average and determine quality tier
- Generate report using the appropriate template
Scoring Principles
- Be specific — cite exact text, line numbers, files, or patterns as evidence
- Be fair — consider the skill's intended scope and type (task, analysis, reference)
- Be consistent — apply the same standards across all skills
- Be calibrated — a 5 is exemplary; see examples for calibration
Key Best Practices to Check
These are the highest-impact items from the official docs:
- Frontmatter: only documented fields (
name,description,argument-hint,disable-model-invocation,user-invocable,allowed-tools,model,effort,context,agent,hooks,paths,shell) - Description: third-person voice, three-part pattern ([What]. Use when [triggers]. [Capabilities].), 200-250 chars (truncated at 250 in listings)
- Size: SKILL.md under 500 lines; detailed content in references
- Invocation control:
disable-model-invocation: truefor side-effect skills;allowed-toolsto restrict tool access - Progressive disclosure: SKILL.md = overview + navigation, references = depth
Relationship to Other Tools
| Tool | Purpose |
|---|---|
cc-lint |
Structural validation (pass/fail) |
skill-quality |
Quality scoring (1-5 scale) |
skill-improve |
Improvement recommendations |
Run cc-lint first for structural issues, then skill-quality for quality scoring.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
philoserf/claude-code-setup
pre-release
Validates a project is ready to tag and ship. Use when tagging a release, cutting a version, shipping a package, or asking "are we ready to release?" Checks repo hygiene, CI status, docs, version sync, and build verification. Optimized for Obsidian plugins with fallback detection for other project types.
philoserf/claude-code-setup
local-issues
Reviews a codebase for bugs, design issues, and code cleanliness problems with specific file paths and line numbers. Use when auditing code quality, finding bugs, doing a code review, finding problems, or reviewing a project for issues. Creates issue files in `.issues/` directory.
philoserf/claude-code-setup
skill-improve
Generates prioritized improvement recommendations for Claude Code skills. Use when improving skills, enhancing customizations, or wanting actionable feedback on how to make a skill better. Provides impact/effort prioritization with specific fix suggestions.
philoserf/claude-code-setup
release
Executes the final release workflow for Obsidian plugins after pre-release checks pass. Use when tagging a release, publishing a version, or shipping an Obsidian plugin. Bumps version via bun run script, creates git tag, pushes to trigger GitHub Actions, and updates GitHub release notes from CHANGELOG.md.
philoserf/claude-code-setup
obsidian-cli
Interacts with Obsidian vaults using the Obsidian CLI to read, create, and manage notes, tasks, properties, tags, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, add to daily note, find notes about a topic, check tasks, append to a note, query the vault, list tags, list files, manage bookmarks, check sync status, view file history, use templates, query bases, run QuickAdd, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
philoserf/claude-code-setup
cc-check
Runs systematic tests on Claude Code customizations. Use when testing whether a customization works correctly, running functional and regression tests, smoke testing a skill, or validating that a skill or hook behaves as expected. Executes sample queries and validates responses against expected behavior.
Didn't find tool you were looking for?