Two-skill presentation system: analyze your speaking style into a rhetoric knowledge vault, then create new presentations that match your documented patterns. Includes an 88-entry Presentation Patterns taxonomy for scoring, brainstorming, and go-live preparation.
96
Quality
96%
Does it follow best practices?
Impact
96%
1.57xAverage score across 15 eval scenarios
A prolific conference speaker has years of talk materials scattered across directories — markdown files with talk metadata (conference, date, video link, slides link), and PowerPoint files organized by conference and year. They need a system to inventory everything: which talks exist, which have video recordings, which have slide decks, and which are ready for analysis.
The speaker wants a JSON-based tracking database that maps all their talks and presentation files, identifies which talks have enough source material for analysis, and flags which ones are incomplete. Some PowerPoint files are duplicates or static exports and should be filtered out. The system should also try to match presentation files to their corresponding talk metadata entries.
Produce the following files:
tracking-database.json — A JSON database that tracks all discovered talks and presentation filesbuild_tracker.py — The Python script that scans the input directories and builds the databasescan_report.txt — A human-readable report summarizing what was foundThe following files are provided as inputs. Extract them before beginning.
A talk about rethinking DevOps culture in the age of platform engineering.
Deep dive into securing your software supply chain with SLSA and Sigstore.
Exploring how AI can transform software testing practices.
Busting common misconceptions about containers.
=============== FILE: inputs/presentations/DevOps Days Chicago/2024/DevOps Reframed.pptx =============== (Create an empty .pptx file at this path using python-pptx)
=============== FILE: inputs/presentations/DevOps Days Chicago/2024/DevOps Reframed static.pptx =============== (Create an empty .pptx file at this path — this is a static export that should be skipped)
=============== FILE: inputs/presentations/DevOps Days Chicago/2024/DevOps Reframed (1).pptx =============== (Create an empty .pptx file at this path — this is a Google Drive conflict copy that should be skipped)
=============== FILE: inputs/presentations/KubeCon/2024/Software Supply Chain Security.pptx =============== (Create an empty .pptx file at this path)
=============== FILE: inputs/presentations/Templates/Presentation Template DOTCs 2023.pptx =============== (Create an empty .pptx file at this path — this is a template that should be skipped)
=============== FILE: inputs/presentations/DockerCon/2023/Container Myths Busted.pptx =============== (Create an empty .pptx file at this path)
Create the .pptx files using python-pptx (pip install python-pptx) as minimal valid presentations with at least one slide each.
Install with Tessl CLI
npx tessl i jbaruch/speaker-toolkit@0.6.2evals
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
skills
presentation-creator
references
patterns
build
deliver
prepare
rhetoric-knowledge-vault