CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-pdf

Use when testing the pdf golden build

Quality

46%

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/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

28%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 skill body is an auto-generated documentation index: well-sectioned and pointing to real reference files, but padded with redundant statistics and placeholder code, and it provides no actual workflow for 'testing the golden build'. It functions as a table of contents rather than actionable guidance.

Suggestions

Replace the placeholder code blocks (pip install thing, print('hello'), the x0..x59 list) with a real example of how to run a golden-PDF comparison and check the result.

Move the statistics and extracted code-example catalog into references/ and keep SKILL.md as a lean overview with a pointer, reducing the duplicated 'Total Pages' and language-breakdown sections.

Add a short numbered workflow with a validation step (e.g., run comparison -> inspect diff report -> fail/fix on mismatch) so the testing purpose is actionable.

DimensionReasoningScore

Conciseness

The body is padded with redundant auto-generated statistics (total pages repeated three times, code-quality metrics, language breakdown) and a 60-line x0..x59 placeholder example that earns no value, fitting 'noticeably verbose; several padded sections'; it avoids score 1 only because it does not lecture on concepts Claude already knows.

2 / 5

Actionability

Code blocks exist but are trivial placeholders ('pip install thing', 'print(\'hello\')', a truncated x0..x59 list) with no guidance tied to the skill's actual purpose, matching 'minimal concrete guidance; high-level hints but missing specific steps'.

2 / 5

Workflow Clarity

There is no sequenced process or validation checkpoint for what is ostensibly a testing skill; the 'When to Use' list enumerates use cases rather than steps, so it sits at 'rough sequence absent / steps poorly defined' rather than the clear-sequence anchors above.

2 / 5

Progressive Disclosure

References are real and clearly signaled in the Navigation section (references/manual.md and references/index.md both exist), but large chunks of content (code examples, statistics) are inlined in SKILL.md instead of living in the reference files, matching 'some structure but content that should be separate is inline'.

3 / 5

Total

9

/

20

Passed

Description

36%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 has an explicit trigger clause and a recognizable niche, but it is thin: it states only a single generic action and never says concretely what the skill does. It reads more as a trigger sentence than a capability description.

Suggestions

Add 2-3 concrete actions the skill performs (e.g., 'compares build output against the golden PDF, diffs pages, reports mismatches').

Expand trigger terms with natural synonyms a user might say (e.g., 'golden build', 'reference PDF', 'PDF regression', 'baseline comparison').

Combine 'what' and 'when' in one sentence, e.g. 'Compares a PDF build against the golden reference and reports diffs. Use when testing the PDF golden build or verifying output against the baseline.'

DimensionReasoningScore

Specificity

The description names the domain ("pdf golden build") and a single generic action ("testing") but lists no concrete capabilities, matching the 'names domain but actions minimal or generic' anchor rather than the multi-action anchor above.

2 / 5

Completeness

It provides an explicit 'when' ('Use when testing the pdf golden build') but only a vague 'what' (the act of testing), matching 'only when is present without what'; it does not reach 3 because no concrete actions are stated.

2 / 5

Trigger Term Quality

It includes a natural 'Use when testing' trigger plus the keywords 'pdf' and 'golden build', but offers no synonyms or common variations, fitting the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

'pdf golden build' is a fairly specific niche, but 'testing' combined with 'pdf' could still overlap with general PDF/testing skills, fitting 'somewhat specific but could still overlap'.

3 / 5

Total

10

/

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/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.