Name: bapfernandez/article-creator
Rating: 90.1 (1 reviews)
Author: bapfernandez

bapfernandez/article-creator

Content creator for tessl.io — generates publish-ready blog articles with SEO metadata, Tessl house style, and technical authority.

1.18x

Quality

82%

Does it follow best practices?

Impact

91%

1.18x

Average score across 10 eval scenarios

Securityby

Passed

No known issues

Evaluation results

95%

19%

Task: Comparison Article on Agent Evaluation Frameworks

Criteria

Without context

With context

Comparison structure complete

100%

Comparison table present

100%

Expanded dimension analysis

100%

Opinionated when-to-use

100%

Specific numbers over qualitative claims

100%

Suggestive language for third-party claims

87%

75%

No excessive bolding

33%

50%

No em dashes

100%

Non-generic closing

100%

No hype or sycophantic language

100%

SEO metadata complete

41%

100%

Word count

100%

98%

Task: News/Analysis Article on a Major MCP Update

Criteria

Without context

With context

News structure complete

100%

Concrete details present

100%

Suggestive language for claims

100%

No sycophantic language

100%

Analysis section quality

100%

Skills terminology

100%

What to watch closing

100%

No hype language

100%

No em dashes

100%

SEO metadata complete

50%

80%

Word count

100%

99%

15%

Task: Skill Showcase Article for the Tessl Blog

Criteria

Without context

With context

Showcase structure

91%

100%

Eval scores included

100%

Install commands shown

100%

Worked example with output

100%

CTA to Registry

100%

Internal links

87%

Meta description length

25%

100%

Skills terminology

100%

Features framed by problems

87%

100%

No hype or em dashes

33%

100%

SEO metadata complete

87%

100%

Word count

80%

100%

93%

34%

Task: Thought Leadership Article on Context Engineering

Criteria

Without context

With context

Problem-first structure

90%

80%

Named framework

91%

100%

Featured snippet definition

12%

87%

Concrete example per section

60%

90%

Counterargument pre-empted

37%

100%

Closing with question

50%

100%

No hype or sycophantic language

100%

No em dashes

100%

SEO metadata complete

33%

75%

H2 structure

50%

100%

Word count and product mentions

83%

100%

Developer-first framing

83%

100%

89%

-4%

Task: Tutorial Article on Running Agent Evals Locally

Criteria

Without context

With context

Outcome-first hook

100%

90%

Tutorial structure complete

100%

75%

Numbered steps with code blocks

100%

Prerequisites section

100%

66%

Advanced usage section

100%

83%

Troubleshooting section

100%

H2 with keyword

87%

75%

URL slug format

100%

Developer-first framing

100%

Concrete and internally consistent

100%

No hype or em dashes

16%

100%

SEO metadata complete

90%

80%

98%

23%

Task: Thought Leadership on Skill Reusability

Criteria

Without context

With context

Zero em dashes

100%

No hype words

100%

No sycophantic words

100%

Uses 'skills' not 'tiles'

100%

Title does not mirror brief

100%

Named framework

80%

100%

Concrete example per major section

62%

87%

Suggestive tone for third-party claims

83%

Counterargument pre-empted

100%

SEO metadata complete

40%

100%

H2 structure

62%

100%

Word count discipline

100%

91%

46%

Task: Content on AI Agent Evaluation Practices

Criteria

Without context

With context

Single article type declared

100%

Structure matches declared type

37%

75%

Word count matches declared type

50%

100%

Not a muddled hybrid

33%

58%

Hook matches declared type

62%

100%

Concrete specifics

100%

Zero em dashes

100%

No hype or sycophantic words

100%

SEO metadata complete

30%

100%

H2 structure appropriate to type

25%

100%

Closing matches type

75%

100%

Uses 'skills' not 'tiles'

100%

90%

Task: News Coverage of a Database Library Release

Criteria

Without context

With context

Zero Tessl product mentions

100%

No forced AI agent angle

100%

58%

Lead states what happened

100%

Specific technical details

100%

Analysis section present

100%

Suggestive tone for capability claims

87%

100%

What-to-watch closing

100%

Article type is News

83%

100%

Zero em dashes

100%

No hype or sycophantic words

100%

SEO metadata complete

40%

80%

Internal links do not force Tessl topics

100%

25%

94%

13%

Task: Comparison Article on Skill Distribution Approaches

Criteria

Without context

With context

Alternative wins at least one dimension

100%

Explicit when-to-use-each guidance

100%

Four to six comparison dimensions

100%

Comparison table included

100%

Suggestive tone maintained

75%

87%

No marketing copy paragraphs

70%

80%

Zero em dashes

100%

No hype or sycophantic words

100%

Uses 'skills' not 'tiles'

100%

SEO metadata complete

50%

70%

Article type is Comparison

50%

100%

Closing restates key differentiator

100%

69%

-13%

Task: Article on Skill Filename Conventions

Criteria

Without context

With context

Length matches topic

100%

Article type matches length

90%

No filler paragraphs

90%

70%

Concrete filename examples

100%

Sharp opinion stated

100%

Zero em dashes

100%

No hype words

100%

SEO metadata complete

50%

70%

Title not padded

83%

100%

Uses 'skills' not 'tiles'

100%

Closing is not generic

100%

H2 discipline

33%

83%

Evaluated: 11 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Task: Comparison Article on Agent Evaluation Frameworks Task: News/Analysis Article on a Major MCP Update Task: Skill Showcase Article for the Tessl Blog Task: Thought Leadership Article on Context Engineering Task: Tutorial Article on Running Agent Evals Locally Task: Thought Leadership on Skill Reusability Task: Content on AI Agent Evaluation Practices Task: News Coverage of a Database Library Release Task: Comparison Article on Skill Distribution Approaches Task: Article on Skill Filename Conventions