validate-skills
Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.
Install with Tessl CLI
npx tessl i github:callstackincubator/agent-skills --skill validate-skills77
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
57%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 establishes a clear, distinct purpose for skill validation but lacks depth in explaining specific validation actions and natural trigger terms. The slash command provides a concrete invocation method, but the description would benefit from listing what validations are performed and when users should invoke it beyond the command.
Suggestions
Add specific validation actions like 'checks YAML frontmatter syntax, validates required fields, verifies file structure'
Include natural trigger terms users might say: 'check skill', 'lint skill', 'skill errors', 'skill syntax'
Expand the 'Use when...' clause beyond the slash command: 'Use when checking skill file validity, debugging skill loading issues, or before committing new skills'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skills validation) and mentions what it validates against (agentskills.io spec and Claude Code best practices), but doesn't list specific concrete actions like 'checks YAML frontmatter', 'validates required fields', or 'reports errors'. | 2 / 3 |
Completeness | Describes what it does (validates skills against spec and best practices) but the 'when' is limited to just the slash command. Missing explicit guidance like 'Use when checking skill file syntax, debugging skill issues, or before committing skill changes'. | 2 / 3 |
Trigger Term Quality | Includes '/validate-skills' as a trigger term which is useful, but lacks natural language variations users might say like 'check my skill', 'skill syntax', 'lint skills', or 'skill errors'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche - validates skills against agentskills.io spec. The combination of 'skills', 'agentskills.io', and '/validate-skills' creates a clear, distinct trigger that's unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
87%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 skill that provides clear validation criteria in an efficient table format. The actionable checklist and specific output format are strengths. The main weakness is the workflow section lacks error handling guidance - what should Claude do when validation fails?
Suggestions
Add a brief section on common fixes for validation failures (e.g., 'If name doesn't match directory: rename directory or update name field')
Consider adding a validation checkpoint: 'After fixing issues, re-run validation to confirm all checks pass'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables to compress information. No unnecessary explanations of concepts Claude already knows - it jumps straight to actionable checklists. | 3 / 3 |
Actionability | Provides concrete validation rules in table format, an executable bash command to find skills, and a specific output format template. The checklist items are specific and verifiable. | 3 / 3 |
Workflow Clarity | The 3-step process is clear but lacks validation checkpoints or error handling. No guidance on what to do if validation fails or how to fix common issues. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (checklist tables, how to run, references). External references are one-level deep and clearly signaled with markdown links. | 3 / 3 |
Total | 11 / 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 | |
- 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.