validate-skills
Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.
81
73%
Does it follow best practices?
Impact
95%
1.30xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/validate-skills/SKILL.mdQuality
Discovery
75%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 is functional and clearly scoped with a distinct trigger command and specific validation target. Its main weakness is that it lacks detail about what concrete validation actions are performed (e.g., checking frontmatter, verifying structure, reporting errors) and could include more natural language trigger terms beyond the slash command.
Suggestions
Add specific concrete actions like 'checks frontmatter fields, verifies file structure, reports formatting errors' to improve specificity.
Include additional natural trigger terms such as 'check skills', 'lint skills', 'skill format', 'skill errors' to broaden discoverability beyond the slash command.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skill validation) and mentions what it validates against (agentskills.io spec and Claude Code best practices), but doesn't list specific concrete actions like checking frontmatter fields, verifying file structure, or reporting errors. | 2 / 3 |
Completeness | Clearly answers both what ('Validates skills in this repo against agentskills.io spec and Claude Code best practices') and when ('Use via /validate-skills command'), providing an explicit trigger mechanism for invocation. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'validate-skills', 'agentskills.io spec', and 'Claude Code best practices', but misses natural user phrases like 'check skills', 'lint skills', 'skill errors', or 'skill format'. The '/validate-skills command' is a specific trigger but narrow. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche — validating skills against a specific spec (agentskills.io) with a specific command trigger (/validate-skills). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 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 is a well-structured, concise validation skill with clear tables for spec compliance and best practices checks. Its main weakness is that the validation steps are descriptive rules rather than executable checks, and the workflow lacks a feedback loop for fixing and re-validating issues. The output format example is a nice touch that adds actionability.
Suggestions
Add a feedback loop step: after reporting issues, suggest fixing them and re-running validation to confirm all checks pass.
Consider adding more concrete validation logic (e.g., a regex pattern for the name format check, or a line-count command for body length) to make the checks more directly executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The tables are compact and scannable, no unnecessary explanation of what validation is or how Claude should think about it. The content is lean and assumes Claude's competence. | 3 / 3 |
Actionability | Provides a clear checklist and output format, plus a concrete bash command for discovery. However, the actual validation logic is described as rules in tables rather than executable code—Claude must interpret and implement the checks itself. The report format example is helpful but the validation steps are more descriptive than executable. | 2 / 3 |
Workflow Clarity | The three-step workflow (find directories, check rules, report) is clear and sequenced, but there's no validation/feedback loop—no guidance on what to do if issues are found (e.g., auto-fix, re-validate after fixes). For a validation tool, the absence of a retry/fix loop is a gap. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections (checklist tables, how to run, references). External references to the spec and best practices are one level deep and clearly signaled with markdown links. The skill is under 50 lines and appropriately self-contained. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- callstackincubator/agent-skills
- Commit
ace14e4
- 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.