Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment.
SkillScore78Maintained
Automatic
◆Marketing & Content pack
Last verified 10/9/2026
What it changes
Passed 14 of 18 test cases with the skill, and 5 of 18 without it.
Without skill28%
With skill78%
Checks it passed that the model alone missed
Enriches scoring with verified dates when timeline data is provided.
Classifies AI profiles and knowledge feeding under the AI Config category.
Requires a minimum threshold of 15 concepts for a standard summary evaluation.
and 7 more in the full report
9 fixed5 passed either way4 still failing0 broke4 errored
Pass-rate lift
+50 pp
Tokens
+37%
Agent turns
0%
Response time
-41%
Model gemini-3.6-flashMeasured 10/9/2026v214 of 22 cases passed with skill · 18 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
We are generating the concept catalog document from `talks/2024-frontend-perf-summary.md`. What minimum quantity of distinct concepts must be identified in the concept table to ensure adequate coverage before moving to positioning?
What was checked, without and with the skill
Checked
Without skill
With skill
Requires a minimum threshold of 15 concepts for a standard summary evaluation.
Missed
Passed
case-08 · gemini-3.6-flash · 10/9/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md152 linessingle file
Talk stage 3: Concepts
Builds an exhaustive catalogue of all identifiable concepts in the source material. Each concept is numbered, categorized, and scored for its talk potential.
When to use this skill
After Stage 1 (and Stage 2 if REX mode)
Before Stage 4 (Position needs the concept catalogue)
When you want a structured inventory of what's available before choosing an angle
What this skill does
Reads the summary: loads {slug}-summary.md
Reads the timeline (if available): enriches scoring with verified dates
Extracts concepts: full scan of the source material
Categorizes: assigns each concept to a domain category
Scores: HIGH / MEDIUM / LOW for talk potential
Optional repo enrichment: if repo_path is provided, analyzes AI config concepts
Writes output files
Input
talks/{YYYY}-{slug}-summary.md (required)
talks/{YYYY}-{slug}-timeline.md (optional, enriches REX concepts)
repo_path (optional, for config/infrastructure concept extraction)