CtrlK
BlogDocsLog inGet started
Tessl Logo

doc-example-formatting

Format code examples in markdown documentation for TalkPipe. Use when writing or editing doc examples. Covers unindented fences, standalone vs fragment intent, and skip-extract. Complements run-documentation-examples which runs the examples.

81

1.16x
Quality

73%

Does it follow best practices?

Impact

93%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/doc-example-formatting/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

88%

37%

TalkPipe Getting Started Guide

skip-extract and language tags in getting-started guide

Criteria
Without context
With context

skip-extract on setup block

0%

100%

skip-extract on fragment

0%

0%

skip-extract on LLM block

0%

100%

skip-extract position

0%

100%

Language tag on all blocks

50%

100%

Unindented fences

100%

100%

Standalone completeness

100%

100%

Fragment context annotation

100%

100%

No nested backticks

100%

100%

Runnable block not skip-extracted

100%

100%

95%

-3%

TalkPipe Pipeline API Reference

Standalone vs fragment intent in API reference docs

Criteria
Without context
With context

Standalone imports

100%

100%

Standalone completeness

100%

100%

Fragment context comment

80%

80%

Fragment skip-extract

100%

100%

skip-extract position

100%

100%

Language tag on all blocks

100%

70%

Unindented fences

100%

100%

No nested backticks

100%

100%

Runnable block not skip-extracted

100%

100%

Intent distinguishable

100%

100%

96%

4%

TalkPipe ChatterLang Syntax Guide

ChatterLang tagging and no mixed-language blocks

Criteria
Without context
With context

ChatterLang language tag

100%

100%

Python language tag

100%

100%

No mixed-language blocks

100%

100%

No nested triple backticks

100%

100%

Language tag on all code blocks

100%

100%

Unindented fences

100%

100%

Meta-section handled correctly

100%

100%

Fragment skip-extract or tagging

0%

50%

Repository
sandialabs/talkpipe
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.