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 uses insert-placeholder-slides.py to insert visually loud placeholder slides at specified positions in an existing deck, preserving original slide order and producing the correct final slide count.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Output deck exists and opens",
"description": "adapted-deck.pptx exists in the working directory and can be opened with python-pptx without errors",
"max_score": 5
},
{
"name": "Correct total slide count",
"description": "The output deck has exactly 9 slides (6 original + 3 placeholders)",
"max_score": 10
},
{
"name": "Placeholder at position 3",
"description": "Slide 3 (0-indexed: 2) contains text with '[PLACEHOLDER]' and 'Cloud Cost Analysis'. It is between the original Introduction and Problem Statement slides",
"max_score": 10
},
{
"name": "Placeholder at position 5",
"description": "Slide 5 (0-indexed: 4) contains text with '[PLACEHOLDER]' and 'Migration Strategy'. It is between the original Current Architecture and Performance Results slides (accounting for earlier insertions)",
"max_score": 10
},
{
"name": "Placeholder at position 8",
"description": "Slide 8 (0-indexed: 7) contains text with '[PLACEHOLDER]' and 'Q&A Prep'. It is near the end of the deck, after the original Performance Results slide",
"max_score": 10
},
{
"name": "Yellow background on placeholders",
"description": "The placeholder slides have a visually distinct background — a yellow or bright-colored rectangle shape that makes them stand out in thumbnail view. Not the same as the original slides' appearance",
"max_score": 10
},
{
"name": "Original slides preserved in order",
"description": "The 6 original slides (Title, Introduction, Problem Statement, Current Architecture, Performance Results, Conclusion) are all present and in their original relative order, interleaved with the new placeholders",
"max_score": 15
},
{
"name": "Skill script used",
"description": "The adaptation-log.md references insert-placeholder-slides.py as the tool used. The agent did not write its own slide insertion code from scratch using raw python-pptx calls",
"max_score": 15
},
{
"name": "Subtitles present on placeholders",
"description": "The placeholder slides include subtitle text describing what the slide needs to become (e.g., 'AWS vs GCP pricing comparison', 'Step-by-step migration path', 'Anticipated questions')",
"max_score": 10
},
{
"name": "Non-destructive output",
"description": "The output deck is saved as adapted-deck.pptx (not overwriting the original input base-deck.pptx). The --output flag or a copy was used to preserve the original",
"max_score": 5
}
]
}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