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 QuZhan51496/paper2anything --skill paper2slidesgit clone --depth 1 https://github.com/QuZhan51496/paper2anythingWrote 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/quzhan51496/paper2anything/paper2slides)<a href="https://agentmods.dev/skills/quzhan51496/paper2anything/paper2slides"><img src="https://agentmods.dev/badge/skills/quzhan51496/paper2anything/paper2slides/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/quzhan51496/paper2anything/paper2slides"><img src="https://agentmods.dev/badge/skills/quzhan51496/paper2anything/paper2slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 93 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Output Handling · line 142 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
- medium Excessive Agency · line 176 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00120 | $0.03853 |
| Opus 5 | $0.00060 | $0.01927 |
| Sonnet 5 | $0.00024 | $0.00771 |
| Haiku 4.5 | $0.00012 | $0.00385 |
Grade A, and why
paper2slides 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 10d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper2slides
Turn an academic paper PDF into a presentation-ready .pptx. This is a conductor skill: you make the
editorial and design judgments, while the mechanical steps are handled by this skill's own self-contained
scripts — PDF parsing via the MinerU cloud API (scripts/parse_pdf.py) and .pptx rendering via a PptxGenJS
bridge (scripts/render_pptx.py). It orchestrates a "paper → outline → spec → render → QA" pipeline and
depends on no other skill.
Quick Reference
| Stage | Input | Output | Owner |
|---|---|---|---|
| 0.5. configure | user dialogue | <workdir>/config.json |
you (AskUserQuestion to confirm three items: length tier + whether to run visual QA + color scheme) |
| 1. extract | paper.pdf |
paper_meta.json + figures_index.json + figures/ + pages/ + equations + hi-res figure/table crops (produced in one shot by the MinerU cloud API) |
scripts/parse_pdf.py |
| 2. outline | paper_meta.json |
slide_outline.json |
you (per references/outline-heuristics.md) |
| 3. spec | slide_outline.json + figures |
slide_spec.json |
you (per references/design-style.md) |
| 4. render | slide_spec.json |
output.pptx |
scripts/render_pptx.py (PptxGenJS bridge) |
| 5. qa | output.pptx |
pass / fail + fix list | content QA always runs; visual QA is gated by Stage 0.5's config.json/visual_qa |
See references/pipeline.md for the detailed per-stage protocol.
Invocation Contract
Invocation form:
/paper2slides <paper.pdf> [output.pptx] [--from-stage <name>] [--force]
output.pptxomitted →<paper-dir>/<paper-stem>_slides/<paper-stem>.pptx; on a name collision the directory auto-appends_v2 _v3- Intermediate artifacts land in
<paper-dir>/.paper2anything/slides/<paper-stem>/; when the paper directory is read-only, fall back to~/.cache/paper2anything/slides/
Python environment: all scripts run in the paper2anything conda environment. Command prefix
conda run -n paper2anything --no-capture-output python -m scripts.<name> ...
(the prefix can be omitted once conda activate paper2anything is in effect). Every -m scripts.<name> must be run from this
skill's directory (the parent of scripts/), otherwise you get No module named 'scripts'; the prefix-omission convention is in
references/pipeline.md §General Conventions.
What ships with it
15 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.
- references/design-style.md 33 KB
- references/outline-heuristics.md 14 KB
- references/pipeline.md 17 KB
- references/pptxgenjs.md 8.0 KB
- references/qa.md 5.8 KB
- references/schemas.md 19 KB
- scripts/__init__.py 677 B runs code
- scripts/lib/__init__.py 0 B runs code
- scripts/lib/mineru_client.py 9.8 KB runs code
- scripts/lib/mineru_parser.py 29 KB runs code
- scripts/lib/sectionize.py 2.3 KB runs code
- scripts/page_screenshot.py 4.0 KB runs code
- scripts/parse_pdf.py 5.9 KB runs code
- scripts/render_pptx.py 13 KB runs code
- scripts/workdir.py 6.9 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.
- 10d ago First seen · 223 lines · 120 tokens per session scan A 87e3341daeaa
paper2slides is a skill published in the GitHub repository QuZhan51496/paper2anything (416 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 3,853 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
latex-expert
Professional LaTeX for official documents: class and engine choice, fonts, microtype, booktabs tables, biblatex/biber, KOMA letters, academic CVs, Eisvogel/pandoc PDFs, IEEE/Elsevier/Springer submission. Use whenever the user writes, reviews, or compiles .tex/.sty/.cls, mentions XeLaTeX/LuaLaTeX/latexmk, wants a…
academic-paper-to-chinese-insight-pdf
Turn an academic paper PDF into a high-quality Chinese insight report and export it as a polished Chinese PDF. Use when asked to read a paper, translate or summarize a paper into Chinese, extract the paper's core ideas, produce original insights/opinions, explain the paper in simpler language, or deliver a Chinese PDF…
chinese-pdf-document-workflows
Class-level workflow for extracting, converting, editing, and producing polished Chinese PDFs and document reports from PDFs, papers, webpages, markdown, and video transcripts. Use when asked to create Chinese PDF reports, fix Chinese font/glyph rendering, summarize academic papers into Chinese insight reports…
figure-quality-standards
Use whenever generating figures or tables for a research paper — enforces publication-quality visual standards including style consistency, readability, accessibility, and venue-appropriate formatting.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
paper-length-gate
Deterministic artifact-backed manuscript readiness gate for meta-paper-write. Validates the workspace LaTeX artifact before compilation while leaving final page-count enforcement to compilepdf.