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 RehgLab/ArcDeck --skill arcdeck-skillgit clone --depth 1 https://github.com/RehgLab/ArcDeckWrote 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/rehglab/arcdeck/arcdeck-skill)<a href="https://agentmods.dev/skills/rehglab/arcdeck/arcdeck-skill"><img src="https://agentmods.dev/badge/skills/rehglab/arcdeck/arcdeck-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/rehglab/arcdeck/arcdeck-skill"><img src="https://agentmods.dev/badge/skills/rehglab/arcdeck/arcdeck-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.05638 |
| Opus 5.5 | $0.00000 | $0.02255 |
| Sonnet 5.5 | $0.00000 | $0.01128 |
| Haiku 4.5 | $0.00000 | $0.00564 |
Grade A, and why
arcdeck-skill 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArcDeck: Academic Paper to Presentation Slides
Convert academic PDF papers into polished, narrative-driven PowerPoint presentations using 13 specialized AI agents orchestrated by Claude Code. Based on Rhetorical Structure Theory (RST) discourse parsing with a multi-agent critique-revise-judge refinement loop. Every slide is visually rich -- text-only slides get programmatic diagrams and charts rendered via PptxGenJS (Node.js). No template PPTX required -- slides are built from scratch with selectable presentation themes and strict layout rules.
Agents 10-13 are Claude Code native -- Claude Code acts as the LLM directly, following agent specs as instructions with no external API calls needed.
Paper: "Narrative-Driven Paper-to-Slide Generation via ArcDeck"
Core Principles
- Narrative over bullets -- Slides tell a coherent story guided by RST discourse trees
- Commitment-driven -- A global contract (commitments.md) guides ALL downstream agents
- Iterative refinement -- Narrative critique-revise-judge loop (up to 3 rounds) + aesthetic design critique-refine pass
- 13 specialized agents -- Each described in its own
agents/*.mdfile (A1-A13) - No text-only slides -- Every slide has either extracted figures OR programmatic visual elements (diagrams, charts, shapes)
- CARP+ design principles -- Aesthetic pipeline uses Contrast, Alignment, Repetition, Proximity, Content-Visual Alignment, Variety, Information Design
- Progressive disclosure -- Only load agent specs when needed for current phase
- Visual variety -- The model freely chooses from all available PptxGenJS shapes (187+), chart types (10), and diagram layouts to best represent each slide's content
Invocation
/arcdeck <pdf_path> [--audience <type>] [--duration <minutes>] [--template <theme>] [--speaker-notes]
Defaults: audience=researchers, duration=20, template=ocean, speaker-notes=off
Templates (Presentation Themes)
| Template | Style | Title Font | Colors |
|---|---|---|---|
ocean |
Ocean Gradient — navy/teal/cyan, light content slides | Georgia | 065A82 1C7293 0891B2 |
minimal |
Clean Minimal — white background, coral accent | Calibri Light | E63946 457B9D 2A9D8F |
dark |
Dark Mode — charcoal backgrounds, violet accent | Trebuchet MS | 7F5AF0 2CB67D FF6B6B |
warm |
Warm Academic — cream background, terracotta accent | Georgia | C45B3E 5B8A72 D4A84B |
What ships with it
40 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.
- agents/00-AGENT-OVERVIEW.md 9.6 KB
- agents/01-pdf-preprocessor.md 2.2 KB
- agents/02-asset-extractor.md 3.8 KB
- agents/03-commitment-builder.md 3.7 KB
- agents/04-discourse-parser.md 5.9 KB
- agents/05-slide-planner.md 5.1 KB
- agents/06-narrative-critic.md 4.8 KB
- agents/07-slide-reviser.md 4.7 KB
- agents/08-narrative-judge.md 5.5 KB
- agents/09-image-table-filter.md 3.9 KB
- agents/10-slide-composer.md 8.9 KB
- agents/11-design-critic.md 7.3 KB
- agents/12-design-refiner.md 8.0 KB
- agents/13-pptx-builder.md 7.6 KB
- prompts/outline/commitment_builder_lite.txt 2.0 KB
- prompts/outline/narrative_critic_no_commitment.txt 2.3 KB
- prompts/outline/narrative_critic.txt 3.5 KB
- prompts/outline/narrative_judge_no_commitment.txt 3.3 KB
- prompts/outline/narrative_judge.txt 5.2 KB
- prompts/outline/section_rst.txt 3.2 KB
- prompts/outline/slide_planner.txt 3.2 KB
- prompts/outline/slide_reviser.txt 3.6 KB
- prompts/pipeline/agentic_js_gen.yaml 12 KB
- prompts/pipeline/caption_fixer.yaml 1.1 KB
- prompts/pipeline/figure_match.yaml 5.2 KB
- prompts/pipeline/image_table_filter_agent.yaml 3.0 KB
- prompts/pipeline/layout_agent_xin_rst.yaml 15 KB
- prompts/pipeline/refine_slide_plan.yaml 11 KB
- prompts/pipeline/speaker_script.yaml 2.6 KB
- reference/LLM-CONFIG.md 2.9 KB
- reference/RST-RELATIONS.md 4.0 KB
- reference/SLIDE-TYPES.md 9.9 KB
- reference/TEMPLATES.md 4.3 KB
- reference/TROUBLESHOOTING.md 5.8 KB
- scripts/enhance_visuals.py 41 KB runs code
- scripts/extract_docling.py 5.4 KB runs code
- scripts/generate_pptx.js 38 KB runs code
- scripts/postprocess_figures.py 11 KB runs code
- scripts/render_pptx.py 36 KB runs code
- scripts/run_visual_pipeline.py 6.4 KB runs code
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 · 437 lines · 0 tokens per session scan A a7e20f131b2a
arcdeck-skill is a skill published in the GitHub repository RehgLab/ArcDeck (54 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,638 tokens. 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 2026-08-30.
Other skills, from other repositories
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…