paper2pr: Skill for Claude Code

.claude/skills/slide-excellence/SKILL.md

slide-excellence is a skill for Claude Code from alohays/paper2pr. It costs 97 tokens per session (1,777 once invoked), scanned A, original, MIT.

A read-only review workflow for Quarto slide decks, combining visual, teaching, proofreading, fact-checking, and screenshot checks.

In plain words
What is it for?
Use it to check a deck’s design, explanations, challenges to its argument, spelling, declared sources, and rendered slides.
Why use it?
It gathers different kinds of review before an important presentation milestone without changing the source files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

This is alohays/paper2pr's own configuration. It tells Claude Code how to work on paper2pr itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paper2pr configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is QMD=$(python3 scripts/deckpath.py <Deck> --field qmd).

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/alohays/paper2pr/main/.claude/skills/slide-excellence/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alohays/paper2pr

Made for: Claude Code.

Wrote 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.

agentmods badge for slide-excellence

README.md
[![agentmods](https://agentmods.dev/badge/skills/alohays/paper2pr/slide-excellence/github.svg)](https://agentmods.dev/skills/alohays/paper2pr/slide-excellence)
Your own site
<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.

agentmods 80×15 button for slide-excellence

Your own site · 80×15
<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>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.01777
Opus 5 $0.00048 $0.00889
Sonnet 5 $0.00019 $0.00355
Haiku 4.5 $0.00010 $0.00178

Measured 9d ago against content hash 74b91112a9fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 9d 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.

.claude/skills/slide-excellence/SKILL.md · 165 lines

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 empty sources list 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 when sources is non-empty (a paper review's source of record is the paper itself - declare it in deck.yml: sources: to opt in).
  • A deck may force a component either way when the presenter asks; say so in the synthesis.

Read the full file on GitHub · 165 lines

Changes

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.

  1. 9d ago First seen · 165 lines · 97 tokens per session scan A 74b91112a9fb

Subscribe to this mod's changes

slide-excellence is a skill published in the GitHub repository alohays/paper2pr (6 stars, last pushed 7d ago), licensed MIT. It adds 97 tokens to every session and 1,777 once invoked, about $0.0005 per session on Opus 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.

Related

Other skills, from other repositories

baoyu-comic

A creator for educational comics, including biographies and tutorials, that turns supplied content or topics into illustrated comic pages.

NousResearch/hermes-agent · 17 tokens

html-ppt-zhangzara-daisy-days

A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.

nexu-io/open-design · 49 tokens

html-ppt-zhangzara-retro-windows

An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.

nexu-io/open-design · 51 tokens

sprite-animation

A pixel / sprite-style animated explainer slide — full-bleed cream stage, bold display year, animated pixel-art mascot (e.g. Hanafuda card, mushroom, or 8-bit console), kinetic Japanese display type, ticking timeline ribbon. Reads like a single frame of an educational motion video — looping CSS keyframes, no JS, ready…

nexu-io/open-design · 141 tokens

style-clone

Building a new course inside someone else's deck — import the deck as a library of layouts, then produce each page of the new course by copying the layout that fits it and rewriting that copy's content element by element, so the result reads as though the original author made it. Use when the session has an imported…

THU-MAIC/OpenMAIC · 164 tokens

edu-math-tutorial

A Chinese-language guide for turning a maths problem into a step-by-step teaching video. It explains how to break down the solution, write narration, format equations, and structure scenes.

agentscope-ai/QwenPaw · 146 tokens