CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-html-kw

Use when testing keyword categorization

Quality

47%

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 ./tests/golden/phase2/html_kw/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%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 an auto-generated documentation index that correctly delegates detail to one-level-deep reference files, but it is padded with redundant boilerplate, decorative headers, and a broken truncated code example. It functions as a navigational overview more than actionable skill content.

Suggestions

Remove the redundant statistics block and decorative emoji headers, and drop or complete the truncated x0-x37 Python example to recover token budget.

Replace the trivial/broken code examples with at least one complete, copy-pasteable example that reflects an actual keyword-categorization task.

Move the inlined table summary and code-example catalog into a reference file, keeping SKILL.md as a lean overview that only points to references.

DimensionReasoningScore

Conciseness

The body is padded with redundant statistics (Total Sections stated twice), decorative emoji headers, and a large truncated x0-x37 Python code block that adds no value, fitting 'noticeably verbose; several padded sections' rather than the lean score-4/5 anchors.

2 / 5

Actionability

Concrete guidance is minimal: the code examples are broken/trivial ("pip install thing", a truncated example, "print('hello')") and only the reference file pointers in Navigation are concrete, matching 'high-level hints but missing the specific steps to execute'.

2 / 5

Workflow Clarity

As a simple reference index it has no multi-step workflow, but content is loosely organized by section with a Navigation pointer to reference files; the simple-skill exception keeps this from sinking below 3, though no sequence or checkpoints exist.

3 / 5

Progressive Disclosure

References are one level deep and all referenced files (references/index.md, section_s1-s1.md, section_s2-s2.md, section_s3-s4.md) are real and clearly signaled in the Navigation section, though the SKILL.md over-inlines code/tables/statistics that could live in references, keeping it just below a 5.

4 / 5

Total

11

/

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 a near-tautological single clause ('Use when testing keyword categorization') that restates the skill name as its own trigger. It provides a trigger but no concrete statement of what the skill does, making it vague and low-information.

Suggestions

Add a concrete 'what' clause before the trigger, e.g. 'Indexes and summarizes documentation for keyword-categorization topics. Use when the user needs API references or code examples for keyword categorization.'

Replace the jargon 'keyword categorization' with natural user-facing terms (e.g. 'categorize keywords', 'tag and group keywords') so the trigger matches what users actually say.

List 1-2 concrete capabilities (e.g. 'look up API references and code examples') to raise specificity beyond a single generic action.

DimensionReasoningScore

Specificity

The description 'Use when testing keyword categorization' names the domain ('keyword categorization') but the only action ('testing') is minimal and generic, matching the score-2 anchor 'Processes PDF files' more closely than the concrete multi-action examples at 4-5.

2 / 5

Completeness

Only the 'when' is present via the explicit 'Use when' clause; the 'what' the skill actually does is absent, fitting the score-2 anchor 'Use when working with documents' rather than a score with a clear what.

2 / 5

Trigger Term Quality

'keyword categorization' is technical jargon rather than a phrase a user would naturally say, and 'testing' is generic, leaving only one or two generic keywords as the score-2 anchor describes.

2 / 5

Distinctiveness Conflict Risk

'keyword categorization' is a specific niche that limits conflict risk, but the bare minimal phrasing still leaves overlap risk with similar testing/categorization skills, matching the score-3 anchor.

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

yusufkaraaslan/Skill_Seekers

Path

tests/golden/phase2/html_kw/SKILL.md

Revision

5b5d8df

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill