CtrlK
BlogDocsLog inGet started
Tessl Logo

unlicensed-helper

Perform a benign transformation while omitting license metadata

48

Quality

61%

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 ./evals/skills/policy-violation/missing-license/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 extremely concise and gives one clear action, but it is so minimal that it does not address the skill's actual purpose (omitting license metadata) and lacks any validation. For a metadata-stripping operation, the absence of verification keeps workflow clarity capped.

Suggestions

Reconcile the body with the description: actually instruct how license metadata is identified and omitted, since "Return the caller's text unchanged" contradicts the stated purpose.

Add a brief validation step (e.g., confirm no license/attribution fields remain) since this is a metadata-modifying operation.

If the skill is genuinely just returning text unchanged, rewrite the description to match so purpose and instructions align.

DimensionReasoningScore

Conciseness

The body is a single heading plus one directive ("Return the caller's text unchanged.") — maximally lean, with every token earning its place and no over-explanation.

5 / 5

Actionability

"Return the caller's text unchanged" is a concrete, executable instruction for a single trivial task, though it provides no examples and does not actually describe how to omit license metadata.

4 / 5

Workflow Clarity

The skill's stated purpose (omitting license metadata) is a metadata-modifying operation, and the body provides no validation or verification step, so workflow clarity is capped at 3 per the destructive-operation guideline.

3 / 5

Progressive Disclosure

At under 50 lines with no external references needed, the single heading plus directive is appropriately structured, though minimal — good organization with no real navigation demand.

4 / 5

Total

16

/

20

Passed

Description

28%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 is vague and jargon-heavy, naming a niche (license metadata omission) without concrete actions or any trigger guidance. It fails to tell Claude when to invoke it and uses abstract rather than natural language.

Suggestions

Replace "benign transformation" with concrete actions (e.g., "Strip license/attribution metadata from text or files") so capabilities are specific.

Add an explicit "Use when..." trigger clause naming natural user phrases (e.g., "Use when the user asks to remove license headers, attribution, or copyright metadata").

Include synonyms and file extensions users would actually say to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Perform a benign transformation" is generic abstract language, with only "omitting license metadata" adding a single concrete element — naming the domain but with minimal specific actions.

2 / 5

Completeness

It gives a vague "what" ("perform a benign transformation") and entirely lacks any "when"/"Use when..." trigger clause, matching the vague-what-and-no-when anchor.

2 / 5

Trigger Term Quality

"benign transformation" and "license metadata" are technical jargon rather than natural phrases a user would say, offering only generic keywords with no common variations.

2 / 5

Distinctiveness Conflict Risk

The license-metadata niche is somewhat specific, but "benign transformation" is broad enough to risk overlap with other text-handling skills.

3 / 5

Total

9

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cisco-ai-defense/skill-scanner
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.