Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/talk
Create and audit presentations (Beamer or Quarto RevealJS). Combines talk creation, visual audit, and compilation. Replaces /create-talk, /visual-audit, /compile-latex (for talks).
Passed 10 of 15 test cases with the skill, and 5 of 15 without it.
and 5 more in the full report
7 fixed7 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to compile our Quarto RevealJS slide deck located at paper/quarto/short_talk.qmd into final HTML presentation slides. What is the standard compilation command?
| Checked | Without skill | With skill |
|---|---|---|
| The compilation command executes quarto render from the paper/quarto directory. | Missed | Passed |
The instructions your model reads when the skill loads.
Create, audit, or compile presentations (Beamer or Quarto RevealJS).
Input: $ARGUMENTS — mode and format/path.
/talk create [format] — Create Beamer Talk/talk create [format] --quarto — Create Quarto RevealJS TalkGenerate a presentation from the paper.
Agents: Storyteller (creator) → storyteller-critic (reviewer)
| Format | Slides | Duration | Content Scope |
|---|---|---|---|
| job-market | 40-50 | 45-60 min | Full story, all results, mechanism, robustness |
| seminar | 25-35 | 30-45 min | Motivation, main result, 2 robustness, conclusion |
| short | 10-15 | 15 min | Question, method, key result, implication |
| lightning | 3-5 | 5 min | Hook, one result, so-what |
Step 1: Parse Arguments
job-market | seminar | short | lightningpaper/main.tex--quarto)Step 2: Dispatch Storyteller
Read the paper and extract: research question, identification strategy, main result, secondary results, robustness checks, key figures/tables, institutional background. Design narrative arc for the chosen format. Build the slide file with shared preamble if available.
The Storyteller follows these design principles:
test cases passed, vs 5 / 15 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.