Extract Python examples from markdown docs and run them (including LLM examples). Use when validating documentation, after doc changes, or to verify all doc examples execute correctly.
88
82%
Does it follow best practices?
Impact
100%
1.51xAverage score across 3 eval scenarios
Passed
No known issues
CI doc-example validation with Ollama skip
Pytest invocation
0%
100%
Verbose flag
0%
100%
Uses .venv Python
100%
100%
Does not use system python
100%
100%
Ollama skip marker
0%
100%
Run from project root
50%
100%
Results summary command
100%
100%
Results summary outcome
100%
100%
Shell script exists
100%
100%
CLI runner failure resume mechanism
Fail index filename
100%
100%
Fail index content
100%
100%
Exits on first failure
100%
100%
Resume by re-running
100%
100%
Reset by deleting
100%
100%
Extracted examples file
100%
100%
CLI command used
100%
100%
Uses .venv
100%
100%
Does not use system python
100%
100%
LLM extras setup and manual two-step run
Extras installation
100%
100%
Correct pip extras syntax
100%
100%
ollama serve
100%
100%
llama3.2 model pull
100%
100%
Embedding model pull
0%
100%
OpenAI env var
0%
100%
Two-step: extract script
0%
100%
Two-step: run extracted
0%
100%
Uses .venv
100%
100%
0cf1686
Table of Contents
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.