CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

58

Quality

68%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/examples/jeremy-plugin-tool/skills/plugin-validator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

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 logically sequenced with clear criteria, and supporting details are appropriately delegated to reference files. The main weaknesses are moderate verbosity in some sections and a lack of inline executable commands—most actionable guidance is either narrative or deferred to reference files rather than being copy-paste ready.

Suggestions

Add inline executable command examples 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.

Trim the prerequisites section—Claude doesn't need to be told what `grep` and `find` are or that `jq empty <file>` validates JSON; just list the tool dependencies concisely.

DimensionReasoningScore

Conciseness

The content is mostly efficient and well-structured, but includes some sections that could be tightened. The error handling table and examples section add useful context but are somewhat verbose. The prerequisites section explaining what `jq` does and listing basic tools like `grep` and `find` is slightly unnecessary for Claude.

2 / 3

Actionability

The 11-step workflow provides specific checks and criteria (kebab-case, semver format, required fields), but lacks executable code/commands inline. Key validation logic is deferred to reference files rather than providing concrete commands or scripts. The examples section describes processes narratively rather than showing exact commands to run.

2 / 3

Workflow Clarity

The 11-step validation process is clearly sequenced and logically ordered (identify target → check files → validate schema → validate frontmatter → structure → permissions → security → marketplace → README → hooks → compile report). The output section defines a clear report format with pass/fail verdicts, and the error handling table provides explicit fix commands for each failure type, creating effective feedback loops.

3 / 3

Progressive Disclosure

The skill provides a clear overview with well-signaled references to detailed materials (validation-checks.md, validation-report-format.md, examples.md, errors.md). References are one level deep and clearly labeled in a Resources section. The main body contains enough context to understand the workflow without needing to read the references for basic operation.

3 / 3

Total

10

/

12

Passed

Description

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, earning good completeness marks. However, it suffers from overly generic trigger terms ('validate', 'check', 'verify') that could conflict with many other skills, and the capability description is somewhat repetitive rather than listing distinct concrete actions. The phrase 'validating configurations or code' is too broad and undermines the otherwise specific plugin-validation niche.

Suggestions

Narrow the generic trigger terms: instead of broad 'validate', 'check', 'verify', specify 'validate plugin manifest', 'check plugin schema', 'verify plugin compliance' to reduce conflict with other validation-related skills.

Replace the vague 'runs comprehensive validation' with specific concrete actions, e.g., 'checks plugin.json schema, validates required fields, verifies directory structure, ensures compliance with repository naming conventions'.

Remove or narrow the overly broad clause 'Use when validating configurations or code' to something more specific like 'Use when validating AI assistant code plugin configurations against repository standards'.

DimensionReasoningScore

Specificity

It names the domain (AI assistant code plugin) and some actions (validate structure, schemas, compliance), but the actions are somewhat repetitive and not comprehensively listed. 'Runs comprehensive validation' is vague rather than specifying concrete checks.

2 / 3

Completeness

It answers both 'what' (validates plugin structure, schemas, compliance for AI assistant-code-plugins repository) and 'when' (explicit trigger phrases and use cases like 'validate plugin', 'check plugin', 'plugin errors', 'validating configurations or code').

3 / 3

Trigger Term Quality

Includes some relevant trigger terms like 'validate plugin', 'check plugin', 'plugin errors', 'validate', 'check', 'verify', but these are fairly generic. Terms like 'schema validation', 'plugin compliance', 'lint plugin', or specific file/config names would improve coverage of natural user language.

2 / 3

Distinctiveness Conflict Risk

The specificity to 'AI assistant-code-plugins repository standards' helps distinguish it, but the broad trigger terms 'validate', 'check', 'verify' and 'validating configurations or code' could easily conflict with general linting, testing, or other validation skills.

2 / 3

Total

9

/

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.