Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MaoranSun/paper-to-storyboard --skill skillgit clone --depth 1 https://github.com/MaoranSun/paper-to-storyboardWrote 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/maoransun/paper-to-storyboard/skill)<a href="https://agentmods.dev/skills/maoransun/paper-to-storyboard/skill"><img src="https://agentmods.dev/badge/skills/maoransun/paper-to-storyboard/skill/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/maoransun/paper-to-storyboard/skill"><img src="https://agentmods.dev/badge/skills/maoransun/paper-to-storyboard/skill.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 | $0.00086 | $0.03119 |
| Opus 5 | $0.00043 | $0.01559 |
| Sonnet 5 | $0.00017 | $0.00624 |
| Haiku 4.5 | $0.00009 | $0.00312 |
Grade A, and why
paper-to-storyboard 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 12d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-to-storyboard
Turn an academic paper PDF into a dark, scroll-snap, single-page website with the same chassis as the reference example. The chassis (HTML scaffold, CSS layout/animations, vanilla JS IntersectionObserver) is fixed. Only the color palette and per-section content change per paper.
Run this skill on a strong model (Opus). The hard part isn't the scripts — it's the judgement: mapping a paper onto the 9-slot narrative arc, rewriting body copy to fit display type, picking layouts and a palette, and composing the cover concept. Weaker models (e.g. Sonnet) tend to produce flat narratives, mis-assigned layouts, and verbatim-dumped paragraphs. If you're not on Opus, tell the user to switch with
/model opusbefore invoking.
Inputs
pdf_path(required, absolute path)out_dir(default:./storyboard/)palette(optional:warm | cool | earth | clinical | tech) — if omitted, ask the user via AskUserQuestionmode(optional:dark | light) — if omitted, ask the usertypography(optional:editorial | modern | tech | academic) — if omitted, ask the usergenerate_cover(optional:true | false) — if omitted, ask the usertitle_override,subtitle_override(optional)
When any of palette, mode, typography, generate_cover is explicitly supplied by the user when they invoke the skill, skip the corresponding question and use the supplied value.
Style options
- palette — color family. Auto-pick from topic keywords; explicit
palettearg wins. - mode —
darkkeeps the reference chassis (white-on-dark with animated gradient + noise).lightflips text to near-black, bg to light tints of the palette, button colors, overlays, and animation opacities. - typography — font pairing:
editorial: Playfair Display + Inter (default — newspaper/longform feel)modern: Space Grotesk + Inter (clean, product-design)tech: JetBrains Mono + Inter (engineering / lab notebook)academic: Crimson Pro + Source Sans (journal / scholarly)
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/reference_storyboard.json 4.4 KB
- palettes/themes.json 9.5 KB
- schemas/storyboard.schema.json 5.1 KB
- scripts/extract_figures.py 6.9 KB runs code
- scripts/extract_text.py 13 KB runs code
- scripts/generate_cover.py 3.9 KB runs code
- scripts/make_transparent.py 3.2 KB runs code
- scripts/preview.py 1.0 KB runs code
- scripts/render.py 11 KB runs code
- templates/index.html.tmpl 540 B
- templates/script.js.tmpl 794 B
- templates/section_snippets.html 7.6 KB
- templates/style.css.tmpl 16 KB
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.
- 12d ago First seen · 184 lines · 86 tokens per session scan A 396811e996e4
paper-to-storyboard is a skill published in the GitHub repository MaoranSun/paper-to-storyboard (5 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 3,119 once invoked, about $0.0004 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.
Other skills, from other repositories
mapping-documents
Generate navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all page-anchored. Produces MAP.md (progressive disclosure), .symbols.json (definition index), .anchors.json (claim references), and a USAGE.md…
transcribing-images
Reads the visual content of slides, pages, and images the way a human would, not just their embedded text. Use when a PPTX or PDF has image slides, screenshots, charts, scanned figures, or flattened-to-image layouts that the built-in pptx/pdf skills read as empty; when asked to transcribe, describe, OCR, or extract…
jangbu-import
A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.
deepread-pii
Redact PII from documents before sharing or sending to LLMs. 14 PII types (names, SSN, credit cards, medical records, etc.) detected with context-aware AI — not regex. Knows patient vs. doctor, personal vs. institutional. Black bar redaction on PDFs, scanned images, and text files. Free tier: 2,000 pages/month.
deepread-form-fill
AI-powered PDF form filling via DeepRead. Upload any PDF form + your data as JSON — AI detects fields, maps data semantically, fills the form with quality checks, returns a completed PDF. Works with scanned, non-editable forms — no AcroForm required.
deepread-bank-statements
Extract structured data from bank statements — account holder, period, opening/closing balances, and every transaction as typed JSON. Works on PDF and scanned statements from any bank. Per-field confidence flags. PII redaction for compliant sharing. Free 2,000 pages/month.