CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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'.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, well-structured validation workflow: numbered steps, prerequisites, an error table with runnable fixes, a defined report format, and clearly signaled one-level-deep references that all exist in the bundle. Its main weaknesses are moderate duplication of validation-checks.md content in the body, a few check steps described rather than commanded, and orphaned bundle files (ARD.md, PRD.md) that are never referenced.

Suggestions

Collapse steps 2-4 and 8 to one-line summaries with links, since references/validation-checks.md already holds the complete field/file/marketplace check lists, and remove the duplicate allowed-fields row in the error table.

Add an explicit final step to the main instructions: apply the fix commands, then re-run the validation to confirm PASSED (currently the fix-verify loop exists only in an example).

Either link ARD.md and PRD.md from the Resources section or remove them from the bundle, so every reference file is discoverable from SKILL.md; consider also giving concrete grep patterns for the step 7 security scans instead of describing them.

DimensionReasoningScore

Conciseness

The body is checklist- and table-driven with no concept explanations Claude already knows and includes ready commands ("jq empty <file>", "chmod +x <script>"), but steps 2-4 and 8 restate full field/file/marketplace lists already in references/validation-checks.md, and the error table repeats the entire allowed-fields list from step 3 — minor trimming opportunities that fit anchor 4 rather than 3.

4 / 5

Actionability

Concrete guidance dominates: exact paths ("plugins/[category]/[name]/", "marketplace.extended.json"), specific field constraints, and runnable fix commands ("pnpm run sync-marketplace"), but steps 7, 9, and 10 describe checks ("search for hardcoded secrets...", "confirm it contains installation...") without giving the actual commands, leaving minor gaps versus the fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The 11 numbered steps form a clear, well-sequenced workflow backed by a prerequisites section, an error-cause-solution table, and a defined output report; however, the main instructions lack an explicit fix-then-revalidate loop (it appears only in the "Debug CI failures" example), which keeps it at "clear sequence with minor validation gaps" rather than 5.

4 / 5

Progressive Disclosure

References are well-signaled inline at the relevant steps plus a Resources section, all one level deep and all real files (validation-checks.md, validation-report-format.md, examples.md, errors.md); minor gaps remain — ARD.md and PRD.md sit in references/ but are never linked (undiscoverable orphans), and the body duplicates substantial check detail that references/validation-checks.md already fully contains.

4 / 5

Total

16

/

20

Passed

Description

71%Weight 40%Scale 1-5

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 communicates a clear niche (plugin structure/schema/compliance validation) with natural trigger phrases and explicit what/when guidance, but it is marred by broken, redundant grammar ("Validate automatically validates") and an overly broad when-clause ("validating configurations or code" plus generic 'validate'/'check'/'verify' triggers) that invites conflict with other validation skills.

Suggestions

Fix the broken opening ("Validate automatically validates...") and drop the vague filler "runs comprehensive validation specific to... repository standards" so the description reads cleanly in third person.

Narrow the when-clause from "Use when validating configurations or code" to plugin-specific triggers, e.g., "Use when validating Claude Code plugins, checking plugin.json schemas, or debugging marketplace/CI plugin failures".

Replace the bare generic trigger words ('validate', 'check', 'verify') with plugin-qualified phrases and add natural synonyms like "plugin validation", "marketplace compliance", and "plugin.json" to improve trigger quality and distinctiveness.

DimensionReasoningScore

Specificity

"validates AI assistant code plugin structure, schemas, and compliance" lists several concrete action areas, matching the anchor for several specific actions with minor gaps in coverage; it is not a 5 because phrases like "runs comprehensive validation specific to... repository standards" are vague filler and coverage is not comprehensive.

4 / 5

Completeness

Both what ("validates... plugin structure, schemas, and compliance") and when ("Use when validating configurations or code") are explicit, but the when-clause is overly broad and not tied to concrete plugin-validation triggers, matching anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Natural user phrases are present ("validate plugin", "check plugin", "plugin errors"), giving good keyword coverage, but common variations like "plugin validation", "marketplace", or file terms are missing, so it falls short of the comprehensive synonym/extension coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

The what-clause establishes a clear niche, but "Use when validating configurations or code" combined with bare trigger words like "validate", "check", or "verify" would fire on nearly any validation-related request, creating overlap risk with linting, testing, and schema-validation skills (anchor 3), though it is not as broadly generic as anchor 2.

3 / 5

Total

15

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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

14

/

16

Passed

Repository

jeremylongshore/tons-of-skills-marketplace

Path

plugins/examples/jeremy-plugin-tool/skills/plugin-validator/SKILL.md

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.