CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-epub-kw

Use when testing keyword categorization

Quality

44%

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/epub_kw/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

32%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 content is an auto-generated documentation index: well-structured references to real bundle files, but padded with repeated statistics, emoji headers, and truncated filler code that add no executable value. It reads as scrape output rather than purposeful skill guidance.

Suggestions

Remove the repeated statistics blocks and decorative emoji headers, keeping only the section overview and navigation to cut padding.

Replace the truncated x0…x37 filler example and trivial 'pip install thing' / print('hello') snippets with complete, relevant examples or delete them.

Add a brief workflow or usage note so the skill tells Claude how to use the references rather than only listing them.

DimensionReasoningScore

Conciseness

The body repeats metadata ('Total Sections: 3' appears multiple times), uses decorative emoji headers, and includes a truncated filler example (x0=0 through x37=37), making it noticeably verbose with several padded sections per the anchor 2 description.

2 / 5

Actionability

Code examples are decorative or trivial ('pip install thing', print('hello'), and a truncated nonsense function) rather than executable guidance for a real task, matching 'minimal concrete guidance; high-level hints but missing specific steps'.

2 / 5

Workflow Clarity

There is no sequenced multi-step process or validation checkpoints; the body is a documentation index/browser, so it sits at the 'rough or absent sequence; validation absent' level rather than the clearly-sequenced anchors above.

2 / 5

Progressive Disclosure

A dedicated Navigation section clearly signals one-level-deep reference files (references/section_s1-s1.md, section_s2-s2.md, section_s3-s3.md, and index.md, all verified to exist), giving good structure with only minor organization gaps; it falls short of level 5 only because the overview itself is padded rather than concise.

4 / 5

Total

10

/

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 terse trigger-only line that names a domain but gives no concrete capabilities, leaving it without a 'what' statement and with weak trigger terms. It is minimally distinct but fails to communicate what the skill actually does.

Suggestions

Add a 'what' clause stating concrete actions, e.g. 'Categorizes text by keyword, returns tagged groups and frequency counts.'

Expand trigger terms to natural user phrasing and file/signal mentions, e.g. 'Use when the user asks to group, tag, or classify keywords and phrases.'

Replace the bare 'Use when testing keyword categorization' with a combined what+when sentence to lift completeness beyond 2.

DimensionReasoningScore

Specificity

The phrase 'testing keyword categorization' names the domain but provides only the minimal generic action 'testing' with no concrete capabilities, matching the 'names the domain but actions are minimal' anchor rather than the multi-action level above.

2 / 5

Completeness

A 'Use when…' clause is present, but no 'what does this do' statement accompanies it, so only 'when' is present without 'what' per the anchor 2 description; it does not reach level 3 which requires a clear 'what'.

2 / 5

Trigger Term Quality

It offers one generic keyword ('keyword categorization') and lacks the natural phrases a user would actually say, fitting the 'one or two generic keywords; missing natural phrases' anchor.

2 / 5

Distinctiveness Conflict Risk

'Keyword categorization' is a recognizable niche that is somewhat distinct, yet the generic 'testing' framing leaves overlap risk with other testing/categorization skills, matching the 'somewhat specific but could still overlap' 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/epub_kw/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.