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 PlutoLei/paperbanana-skill --skill paperbanana-slide-deckgit clone --depth 1 https://github.com/PlutoLei/paperbanana-skillWrote 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/plutolei/paperbanana-skill/paperbanana-slide-deck)<a href="https://agentmods.dev/skills/plutolei/paperbanana-skill/paperbanana-slide-deck"><img src="https://agentmods.dev/badge/skills/plutolei/paperbanana-skill/paperbanana-slide-deck/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/plutolei/paperbanana-skill/paperbanana-slide-deck"><img src="https://agentmods.dev/badge/skills/plutolei/paperbanana-skill/paperbanana-slide-deck.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 | $0.00133 | $0.03333 |
| Opus 5.5 | $0.00053 | $0.01333 |
| Sonnet 5.5 | $0.00027 | $0.00667 |
| Haiku 4.5 | $0.00013 | $0.00333 |
Grade B, and why
paperbanana-slide-deck scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
LOCAL_STYLES="$(find ~/.claude/skills .claude/skills -maxdepth 1 -name 'paperbanana-slide-deck' -type d 2>/dev/null | head -1)/references/styles" How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PaperBanana Slide Deck
End-to-end slide deck creation and modification. Two deck modes (image and editable, chosen explicitly in Phase M), and within image mode two workflows: creating new decks from scratch, and regenerating existing decks after prompt edits.
Image pipeline: Content → Style Selection → Outline → Prompts → Image Generation → PPTX Merge
Editable pipeline: Content → slide-spec.json (native text/table/chart/shape/line/group) → validate → build PPTX → render previews → Critic review → revise spec → rebuild
Phase M: Deck mode selection
Record exactly one line in deck-mode.txt: image or editable.
- Use
editablewhen the user asks to edit text/tables/charts/connectors in PowerPoint or explicitly asks for editable PPTX. - Use
imagewhen the user asks for generated full-slide artwork or preserves the existing PaperBanana image workflow. - If both are plausible, ask before generation. Do not infer from file presence.
editablerequiresslide-spec.json; a missing or invalid spec is an error. Never fall back to image mode while claiming editability.
Mode Detection (image mode)
Within image mode, determine the workflow by checking the target directory:
| Condition | Mode | Start Phase |
|---|---|---|
Target dir missing OR no outline.md |
New | Phase R (full RDIV) |
Target dir has outline.md + prompts/ |
Modify | Phase I (generate + merge) |
In Modify mode, the user has already edited prompts or outline externally. Skip directly to Phase I.
Dependencies
| Component | Role | Location |
|---|---|---|
google-genai SDK |
Path B image generation | pip install google-genai |
| PaperBanana CLI | Path A image generation | python -m paperbanana.cli slide-batch |
| merge-to-pptx.ts | PPTX merge (image mode) | plugins/paperbanana-slide-deck/scripts/merge-to-pptx.ts |
| build-deck.ts | Explicit --mode image|editable router |
plugins/paperbanana-slide-deck/scripts/build-deck.ts |
| Editable renderer | slide-spec.json → native PPTX |
plugins/paperbanana-slide-deck/scripts/editable/ |
| Style libraries | Style presets (4 sources, 150+) | See R1 for discovery paths |
| Bun | Run build/merge scripts | bun |
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.
- 2mo ago First seen · 286 lines · 133 tokens per session scan B 6afc0a1301b3
paperbanana-slide-deck is a skill published in the GitHub repository PlutoLei/paperbanana-skill (58 stars, last pushed 26d ago), licensed MIT. It adds 133 tokens to every session and 3,333 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
blog-notebooklm
Query Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents. Manages notebook library, handles Google authentication, and supports smart discovery. Works standalone via /blog notebooklm or internally from blog-write and blog-researcher for source-grounded research…
xiaobei-skill-academic-paper-to-ppt
A workflow that turns academic papers, reports, and technical documents into presentation slides, optionally following a supplied PowerPoint template. It creates a written outline, full-slide images, and a PowerPoint file.
youtube-fetcher
Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…
xiaobei-skill-rebuild-image-in-powerpoint
Use when a user wants Codex to directly operate PowerPoint and reconstruct an entire reference image as editable PowerPoint objects while preserving its full layout, labels, connectors, and visual relationships. Do not use for paper-to-deck generation or VBA-only output.
latex-setup
Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive…
venue-templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing…