Auto-generated tile from GitHub (10 skills)
92
94%
Does it follow best practices?
Impact
92%
1.16xAverage score across 44 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent follows the Diátaxis tutorial conventions when writing a getting-started guide for new users of a software library. Focuses on title style, structural completeness, step-level verifiable results, and keeping the document free of conceptual digressions.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Verb-based title",
"description": "The tutorial document title starts with an action verb (e.g., 'Build', 'Create', 'Set up', 'Write', 'Deploy') rather than a noun phrase or 'How to...'",
"max_score": 12
},
{
"name": "Goal/intro statement",
"description": "The document opens with a clear statement of what the reader will accomplish by the end of the tutorial",
"max_score": 8
},
{
"name": "Prerequisites section",
"description": "The document includes an explicit prerequisites or requirements section listing what the reader needs before starting",
"max_score": 10
},
{
"name": "Numbered steps",
"description": "The tutorial body uses a numbered (ordered) list for the main steps, not bullet points or prose paragraphs",
"max_score": 10
},
{
"name": "Verifiable result per step",
"description": "At least two-thirds of the numbered steps include an explicit verifiable or visible result (something the reader can run, see, check, or confirm)",
"max_score": 20
},
{
"name": "Minimal explanation in steps",
"description": "Steps contain primarily instructions/commands rather than conceptual explanations — no step has a longer explanatory paragraph than the action it describes",
"max_score": 15
},
{
"name": "Final outcome statement",
"description": "The document ends with a summary or statement of the final outcome the reader has achieved",
"max_score": 8
},
{
"name": "No reference tables mixed in",
"description": "The document does NOT include parameter/option reference tables or API specification sections (stays a single doc type)",
"max_score": 9
},
{
"name": "No conceptual digression sections",
"description": "The document does NOT contain standalone 'Background', 'Why this works', or 'Understanding X' sections (those belong in an explanation doc)",
"max_score": 8
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
scenario-44
skills
documentation
fastify
init
linting-neostandard-eslint9
node
nodejs-core
rules
oauth
octocat
snipgrapher