Four-skill presentation system: ingest talks into a rhetoric vault, run interactive clarification, generate a speaker profile, then create new presentations that match your documented patterns. Includes an 88-entry Presentation Patterns taxonomy for scoring, brainstorming, and go-live preparation.
96
93%
Does it follow best practices?
Impact
97%
1.21xAverage score across 30 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent produces a correct PPTX visual audit: right files skipped, right data extracted (colors, fonts, shapes, footers), and results structured for downstream consumption.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Skips static files",
"description": "Files with 'static' in the name are skipped and not present in extraction results",
"max_score": 10
},
{
"name": "Skips conflict copies",
"description": "Files matching a (N).pptx pattern (e.g., 'Deck (1).pptx') are skipped and not present in extraction results",
"max_score": 10
},
{
"name": "Skips template files",
"description": "Files with 'template' in the name are skipped and not present in extraction results",
"max_score": 10
},
{
"name": "Background colors extracted",
"description": "The output includes background color data per slide as hex values or color names, including slides that inherit their background from the slide layout",
"max_score": 10
},
{
"name": "Per-slide breakdown present",
"description": "Each slide in the output includes at least: slide number, background color, layout info, shape count, and whether images or speaker notes are present",
"max_score": 10
},
{
"name": "Global design statistics",
"description": "Output includes aggregate statistics across all slides: font usage frequency, background color frequency, and the sequence of colors across slides",
"max_score": 10
},
{
"name": "Shape type detail",
"description": "The output distinguishes auto-shape subtypes (e.g., callout, starburst, cloud) rather than just reporting everything as generic 'shape'",
"max_score": 8
},
{
"name": "Font extraction",
"description": "Extracts font name, font size, and font color from text content within shapes",
"max_score": 8
},
{
"name": "Footer detection",
"description": "Identifies footer text — detecting text elements in the bottom portion of slides",
"max_score": 10
},
{
"name": "Recursive directory scan",
"description": "Finds .pptx files in subdirectories, not just the top-level directory",
"max_score": 8
},
{
"name": "Valid JSON output",
"description": "extraction_results.json is valid, parseable JSON with clearly separated per-file and per-slide data",
"max_score": 6
}
]
}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
rules
skills
presentation-creator
references
patterns
build
deliver
prepare
scripts
vault-clarification
vault-ingress
vault-profile