Borrowing it
Nothing to install: this file belongs to alohays/paper2pr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alohays/paper2pr/main/.claude/skills/slide-excellence/SKILL.mdgit clone --depth 1 https://github.com/alohays/paper2prWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alohays/paper2pr/slide-excellence)<a href="https://agentmods.dev/skills/alohays/paper2pr/slide-excellence"><img src="https://agentmods.dev/badge/skills/alohays/paper2pr/slide-excellence/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alohays/paper2pr/slide-excellence"><img src="https://agentmods.dev/badge/skills/alohays/paper2pr/slide-excellence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00097 | $0.01777 |
| Opus 5.5 | $0.00039 | $0.00711 |
| Sonnet 5.5 | $0.00019 | $0.00355 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
slide-excellence scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slide Excellence Review
Run a comprehensive multi-dimensional review of a Quarto deck. Up to five components run independently and in parallel, then the results are synthesized into one summary. This is the one fan-out: the former standalone proofreading, pedagogy, and devil's-advocate skills were folded in here, and the fact check and render audit joined in WP6.
Read-only. No agent edits a source file. Fixes are applied separately after the presenter reviews the reports.
Steps
1. Resolve the deck and capture its premises
$ARGUMENTS is a deck name (bare name or genre/name). Resolve paths
through the scripts, never by hand, and capture three things every agent
will receive:
QMD=$(python3 scripts/deckpath.py <Deck> --field qmd)
PROFILE_JSON=$(python3 scripts/deckprofile.py <Deck>) # resolved profile, as JSON
DECK_YML=$(cat "$(python3 scripts/deckpath.py <Deck> --field config)") # <deck>.deck.yml verbatim
If the deck predates /new-deck and has no deck.yml, DECK_YML is empty:
say so, and the agents review against the genre's default profile (the
profile JSON still resolves).
Set DATE to today as YYYY-MM-DD. All reports for this run go under
quality_reports/reviews/ (mkdir -p it):
| Component | Report |
|---|---|
| slide-auditor | quality_reports/reviews/<Deck>-visual-<DATE>.md |
| pedagogy-reviewer | quality_reports/reviews/<Deck>-pedagogy-<DATE>.md |
| proofreader | quality_reports/reviews/<Deck>-proofread-<DATE>.md |
| domain-reviewer (fact check) | quality_reports/reviews/<Deck>-factcheck-<DATE>.md |
| render audit | quality_reports/reviews/<Deck>-render-<DATE>.md |
| synthesis (this skill) | quality_reports/reviews/<Deck>-<DATE>.md |
2. Decide which components run (by profile)
Read profile and sources from PROFILE_JSON:
lecture: all five components run, always. A lecture with an emptysourceslist still gets the fact-check agent - its report saying "no sources declared, these claims are unverifiable" is exactly the warning a lecture needs.paper-review,invited-talk, anything else: slide-auditor, pedagogy-reviewer, proofreader and the render audit run; the fact check runs only whensourcesis non-empty (a paper review's source of record is the paper itself - declare it indeck.yml: sources:to opt in).- A deck may force a component either way when the presenter asks; say so in the synthesis.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 165 lines · 97 tokens per session scan A 74b91112a9fb
slide-excellence is a skill published in the GitHub repository alohays/paper2pr (6 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,777 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
beamer-academic
Generate high-quality academic Beamer slides from a thesis/paper (PDF, Word, or LaTeX source). Compatible with Claude Code and Codex. Supports thesis defense, proposal presentations, and conference talks. Built-in layout library with 13 professional page types, 5 color schemes, and interactive editing loop. Use when…
beamer-presentation
Create academic presentations in Beamer with professional themes.
econ-slides
Build professional academic economics slide decks in LaTeX/Beamer: turn a paper into a conference, seminar, or job-market talk; build discussant slides; polish or shorten an existing deck. Use when the user mentions slides, presentation, talk, deck, beamer, seminar, conference, job talk, job market presentation…
beamer-presentation
Create academic presentations in Beamer with professional themes.
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.
yann-lecun-filosofia
Sub-skill filosófica e pedagógica de Yann LeCun.