plugin-validator
Validate automatically validates AI assistant code plugin structure, schemas, and compliance when user mentions validate plugin, check plugin, or plugin errors. runs comprehensive validation specific to AI assistant-code-plugins repository standards. Use when validating configurations or code. Trigger with phrases like 'validate', 'check', or 'verify'.
73
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/examples/jeremy-plugin-tool/skills/plugin-validator/SKILL.mdQuality
Discovery
67%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 covers both what the skill does and when to use it, which is good for completeness. However, it suffers from overly generic trigger terms ('validate', 'check', 'verify') that could easily conflict with other validation-related skills, and the specific capabilities could be more concretely enumerated. The description is also somewhat redundant, stating the validation purpose multiple times in slightly different ways.
Suggestions
Narrow the 'Use when...' clause to be more specific, e.g., 'Use when working with AI assistant code plugin repositories, plugin manifest files, or plugin schema validation' rather than the overly broad 'validating configurations or code'.
Make trigger terms more distinctive by focusing on domain-specific phrases like 'plugin manifest', 'plugin schema', 'plugin compliance', 'code-plugins repo' rather than generic terms like 'validate', 'check', 'verify'.
List more concrete actions the skill performs, e.g., 'validates plugin manifest.json schemas, checks required field compliance, verifies directory structure, reports schema violations' instead of the vague 'comprehensive validation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI assistant code plugin) and some actions (validate structure, schemas, compliance), but the specific actions are somewhat vague—'comprehensive validation' and 'validating configurations or code' are broad rather than listing concrete validation steps. | 2 / 3 |
Completeness | Explicitly answers both 'what' (validates plugin structure, schemas, and compliance against repository standards) and 'when' (Use when validating configurations or code, with explicit trigger phrases). Has a clear 'Use when...' clause and trigger phrase guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant trigger terms like 'validate plugin', 'check plugin', 'plugin errors', 'validate', 'check', 'verify', but misses natural variations users might say such as 'lint', 'schema errors', 'plugin config', or 'compliance check'. The terms are reasonable but not comprehensive. | 2 / 3 |
Distinctiveness Conflict Risk | The specificity to 'AI assistant-code-plugins repository standards' helps distinguish it, but the broad 'Use when validating configurations or code' clause could easily overlap with general linting, code review, or other validation skills. The trigger terms 'validate', 'check', 'verify' are very generic and could conflict with many other skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
70%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 skill with excellent workflow clarity and progressive disclosure. The 11-step validation process is clearly sequenced and the references to supporting files are well-organized. The main weakness is actionability — the steps describe what to validate but don't provide enough executable commands or concrete code snippets that Claude could directly run, relying instead on narrative descriptions and external reference files.
Suggestions
Add concrete, executable command examples inline for key validation steps (e.g., the exact `jq` command to validate plugin.json schema, the `grep` patterns for security scanning) rather than only describing what to check.
Replace the narrative examples with concrete input/output pairs showing actual command invocations and expected validation report output.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some verbosity that could be tightened. The error handling table and examples section add useful information but could be more compact. Some items like explaining what `jq empty` does are borderline unnecessary for Claude. | 2 / 3 |
Actionability | The instructions provide a clear numbered checklist of validation steps with specific field names, patterns, and tool references. However, it lacks executable code/commands inline — most steps describe what to check rather than providing copy-paste ready commands or scripts. The examples section describes processes narratively rather than showing concrete command sequences. | 2 / 3 |
Workflow Clarity | The 11-step workflow is clearly sequenced with explicit validation categories, a defined output format, and error handling with specific solutions. The process flows logically from file existence checks through schema validation, security scans, and marketplace compliance, culminating in a structured report. The error handling table provides feedback loops for common failures. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to detailed materials (validation-checks.md, validation-report-format.md, examples.md, errors.md). The main content stays at the right level of detail while pointing to reference files for complete specifications. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3e83543
- 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.