CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-check

Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.

52

Quality

58%

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/AI-Agents-Safe-Coding-Skills-claude/skills/skill-check/SKILL.md

The canonical home for this skill is skill-check in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%Scale 1-5

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

This skill provides a well-structured overview of a validation workflow with clear steps, concrete examples of expected output, and an explicit scoring formula. Its main weaknesses are: the actual validation rules are not documented (only check IDs and categories are listed), some sections add unnecessary verbosity (Best Practices, Common Pitfalls), and the repeated references to 'SkillCheck Pro' read as promotional content rather than technical documentation.

Suggestions

Document the actual validation rules for each check ID (e.g., what exactly does '1.2-desc-when' look for?) either inline or in a referenced CHECKS.md file, so Claude can actually perform the validation.

Remove or minimize the 'SkillCheck Pro' promotional references—they don't help Claude execute the skill and consume tokens.

Trim the 'Best Practices' and 'Common Pitfalls' sections or fold their essential content into the workflow steps to improve conciseness.

DimensionReasoningScore

Conciseness

The skill includes some unnecessary sections like 'Best Practices' and 'Common Pitfalls' that explain things Claude could infer. The 'When to Use This Skill' section is reasonable but the 'Do NOT use' line is essentially an ad for a paid product. The Limitations section has useful constraints but is somewhat verbose. The table in Step 2 is efficient, but overall there's room to tighten.

3 / 5

Actionability

The skill provides a clear 4-step process with concrete check categories, scoring formula (critical=-20, warning=-5, suggestion=-1), and two example outputs showing exact format. However, it lacks the actual validation rules/logic—the check IDs are listed but the implementation details of what constitutes each check are absent, making it more of a specification than executable guidance.

4 / 5

Workflow Clarity

The 4-step workflow (Parse → Validate → Score → Report) is clearly sequenced with concrete outputs at each stage. The scoring formula is explicit. However, there are no validation checkpoints or error handling for edge cases like malformed YAML, missing frontmatter, or unreadable files. The 'read-only' constraint is clearly stated which is good for safety.

4 / 5

Progressive Disclosure

The content is reasonably structured with clear sections, but everything is inlined in a single file with no bundle files. The check categories table is a good summary, but the actual check rules (what constitutes each of the 31+ checks) are not documented anywhere—neither inline nor in referenced files. References to 'SkillCheck Pro' are external product links rather than documentation references.

3 / 5

Total

14

/

20

Passed

Description

53%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 identifies a clear, specific domain (skill validation) and mentions the types of issues it catches, but lacks an explicit 'Use when...' clause that would help Claude know when to select it. The trigger terms are somewhat technical and may not match how users naturally phrase requests for skill validation.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user asks to validate, lint, or check a SKILL.md file, or when verifying skill format and structure.'

Include more natural user-facing keywords and synonyms such as 'SKILL.md', 'lint', 'check skill file', 'skill format', 'frontmatter validation' to improve trigger term coverage.

Enumerate a few more specific actions (e.g., 'checks frontmatter fields, validates file naming conventions, verifies required sections') to increase specificity.

DimensionReasoningScore

Specificity

Names the domain (Claude Code skills validation) and mentions a couple of concrete actions ('validate', 'catches structural, semantic, and naming issues'), but doesn't enumerate specific checks or outputs comprehensively.

3 / 5

Completeness

The 'what' is reasonably clear (validates skills against a spec, catches issues), but there is no explicit 'when' clause. The description lacks a 'Use when...' trigger phrase, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes some relevant terms like 'validate', 'skills', 'agentskills specification', 'structural', 'semantic', 'naming issues', but misses natural user phrases like 'lint skill', 'check skill file', 'SKILL.md', 'skill format', or file extensions. Users might not naturally say 'agentskills specification'.

3 / 5

Distinctiveness Conflict Risk

The description targets a fairly specific niche — validating Claude Code skills against the agentskills specification — which is unlikely to overlap with most other skills. Minor overlap risk with general linting or validation skills, but the domain is well-scoped.

4 / 5

Total

13

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.