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 JeanDiable/academic-research-plugin --skill poster-slides-makergit clone --depth 1 https://github.com/JeanDiable/academic-research-pluginWrote 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/jeandiable/academic-research-plugin/poster-slides-maker)<a href="https://agentmods.dev/skills/jeandiable/academic-research-plugin/poster-slides-maker"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/poster-slides-maker/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/jeandiable/academic-research-plugin/poster-slides-maker"><img src="https://agentmods.dev/badge/skills/jeandiable/academic-research-plugin/poster-slides-maker.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 | $0.00104 | $0.03130 |
| Opus 5 | $0.00052 | $0.01565 |
| Sonnet 5 | $0.00021 | $0.00626 |
| Haiku 4.5 | $0.00010 | $0.00313 |
Grade C, and why
poster-slides-maker scanned grade C 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 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- INSERT FIGURE 1 HERE: System architecture diagram showing three main components: preprocessing (left), neural network model (center), post-processing (right) --> How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The poster-slides-maker skill generates publication-quality presentation materials from academic papers. It produces standalone HTML files that work in any browser with no dependencies—all resources are loaded from CDN. The skill supports generating:
- Slides — Interactive reveal.js presentations with speaker notes, optimized for export to PDF
- Poster — Single-page responsive HTML poster with grid layout, suitable for printing at A0 or display on screen
- Both — Generate slides and poster in one command
All output files are self-contained and can be opened immediately in any modern browser (Chrome, Firefox, Safari, Edge).
Arguments
<paper-path> (required)
Path to the source material: either a PDF file (paper.pdf) or a LaTeX project main file (main.tex).
--type (optional, default: both)
What to generate: slides, poster, or both.
--template (optional)
Path to a custom HTML template to match your desired style. If provided, the generated slides or poster will adopt the color scheme, fonts, and CSS patterns from this template.
--pages (optional, default: 10)
Target number of slides. Used to scale the method and results sections. For example, --pages 15 will expand the presentation with more detailed methodology and results breakdown.
Workflow
The skill executes five sequential steps to transform raw academic content into polished presentation materials.
Step 1: Extract Content
From PDF input:
- Read the PDF with pagination to handle large documents (pages 1-20, then 21-40, etc.)
- Extract text, identify section boundaries, and locate references
From LaTeX input:
- Read all
.texfiles in the project directory and subdirectories - Parse the structure to identify: title, author list, affiliations, abstract, sections, subsections
- Identify all figure and table references
Extract these key elements:
- Paper title
- All author names
- Institutional affiliations for each author
- Abstract text
- Section structure and headings
- Key equations (preserve as displayed in the original)
- Main results: important numbers, benchmark scores, accuracy metrics
- Tables with experimental results
- Key citations (extract author + year + title)
- Conclusion and future work sections
What ships with it
1 file 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.
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.
- 9d ago First seen · 317 lines · 104 tokens per session scan C 18d36cd7f66a
poster-slides-maker is a skill published in the GitHub repository JeanDiable/academic-research-plugin (21 stars, last pushed 5mo ago), licensed MIT. It adds 104 tokens to every session and 3,130 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-zhangzara-monochrome
A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
paper2video
Turn a research paper, a paper2assets package, or an existing PPT deck into a narrated MP4 video by fully delegating slide authoring to the installed ppt-master skill and fully delegating rendering, subtitles, timeline assembly, and strict media QA to the installed pptx2video skill and its public CLI. Resolves one…
figure-composer
Compose one publication-grade multi-panel figure. Start from a one-line claim plus immutable data Artifact Version references, or inspect an existing figure and draft its outline directly. Plan a 12-column panel outline, delegate one worker per panel, compose and inspect the result, then run at most three adversarial…