CtrlK
BlogDocsLog inGet started
Tessl Logo

content-research-writer

A token-efficient writing partner that uses bounded research, numbered citations, evidence packets, and parallel sub-agents to outline, draft, and refine high-quality content with minimal context growth.

59

1.34x
Quality

40%

Does it follow best practices?

Impact

94%

1.34x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/content-research-writer/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

92%

41%

Setting Up a Research Project for a Technical Article

Evidence packet structure and folder organization

Criteria
Without context
With context

Folder structure prefix naming

0%

20%

Evidence packet file naming

70%

100%

Packet ID field

0%

100%

Target claim field

100%

100%

Evidence bullets cap

0%

100%

Quote cap

100%

100%

Does not prove field

50%

100%

Confidence field

100%

100%

Intended placement field

0%

100%

Citation-ready reference entry

40%

100%

One packet per claim (atomic)

100%

100%

100%

17%

Research Planning for a Cloud Cost Optimization Article

Research brief and source planning

Criteria
Without context
With context

Claims-to-prove count

100%

100%

Claim type labels

0%

100%

Audience definition

100%

100%

Goal and success criteria

100%

100%

Scope boundaries

100%

100%

Voice constraints

100%

100%

Source log file exists

100%

100%

Selected/rejected decisions

100%

100%

First-party source preference

100%

100%

Publication date noted

80%

100%

91%

15%

Write a Cited Technical Blog Post on Observability

Citation-first drafting with numbered references

Criteria
Without context
With context

Numbered in-text citations

100%

100%

No uncited factual claim

80%

100%

References section present

100%

100%

Reference entry format: author/org

100%

100%

Reference entry format: date and URL

50%

75%

Reference entry format: accessed date

0%

75%

Evidence packets exist

100%

100%

No large verbatim evidence blocks

100%

100%

Source budget respected

100%

50%

Draft file naming

0%

100%

Repository
0xrabbidfly/eric-cartman
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.