CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-pdf-kw

Use when testing keyword categorization

Quality

49%

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/pdf_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 with real, well-signaled reference files (good progressive disclosure) but is padded with redundant statistics and low-quality placeholder code examples that hurt conciseness, actionability, and workflow clarity.

Suggestions

Remove the padded auto-generated blocks (the x0..x37 assignment example, 'print(\'hello\')', and the duplicated Documentation Statistics section) to tighten conciseness.

Replace junk code examples with one or two genuinely executable snippets relevant to keyword categorization, or drop the Code Examples section entirely.

Add a short, explicit lookup workflow (e.g. 1. check index.md 2. open the relevant section_*.md 3. cite the page) so the skill has a clear sequenced procedure.

DimensionReasoningScore

Conciseness

The body is padded with redundant auto-generated sections (emoji headers, statistics, a 38-line x0..x37 assignment block, 'print(\'hello\'')') that add no value, fitting "Noticeably verbose; several unnecessary explanations or padded sections."

2 / 5

Actionability

Code blocks exist but are junk or trivial (pip install thing; x0=0..x37=37; print('hello')) rather than executable guidance for any real task, matching "Minimal concrete guidance; high-level hints but missing the specific steps to execute."

2 / 5

Workflow Clarity

There is no sequenced process or validation; the body is a documentation index with navigation pointers but no actionable workflow steps, fitting "Rough sequence present but many gaps; steps poorly defined; validation absent."

2 / 5

Progressive Disclosure

The body is an overview that signals one-level-deep reference files (references/section_p1-p1.md, section_p2-p2.md, section_03.md, section_p3-p3.md) which all exist, plus an index.md; this is "Good structure; most content is appropriately placed; references mostly clear" but not a 5 because the inline padding should itself be trimmed/split.

4 / 5

Total

10

/

20

Passed

Description

40%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 terse and supplies a trigger condition but omits any statement of what the skill does, leaving it unbalanced and vague. Trigger phrasing is acceptable though thin on synonyms.

Suggestions

Add an explicit 'what' clause, e.g. 'Documents and indexes keyword categorization references. Use when testing keyword categorization.'

Expand trigger terms with natural synonyms or extensions a user might actually say (e.g. 'keyword classification', 'tagging', 'category mapping').

List 1-2 concrete actions (e.g. 'looks up keyword categorization patterns and code examples') to lift specificity above generic.

DimensionReasoningScore

Specificity

The phrase "testing keyword categorization" names a domain and a single generic action but offers no concrete capabilities; this matches "Names the domain but actions are minimal or generic" rather than the score-3 anchor which requires 1-2 clearly concrete actions.

2 / 5

Completeness

It provides a "Use when" clause (when) but never states what the skill actually does (what); this is "only 'when' is present without 'what'", which is below the score-3 anchor requiring a clear what.

2 / 5

Trigger Term Quality

"keyword categorization" is a reasonably natural phrase a user might say, but the description includes only that single term with no synonyms, variations, or file extensions, fitting "Some relevant keywords but missing common variations or synonyms."

3 / 5

Distinctiveness Conflict Risk

"keyword categorization" is a fairly specific niche unlikely to collide with unrelated skills, fitting "Mostly distinct; minor overlap risk"; it is not a score-5 because the wording is too terse to fully lock in a distinct trigger.

4 / 5

Total

11

/

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/pdf_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.