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 SPYfighting/my-academic-skills --skill scientific-ppt-drawinggit clone --depth 1 https://github.com/SPYfighting/my-academic-skillsWrote 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/spyfighting/my-academic-skills/scientific-ppt-drawing)<a href="https://agentmods.dev/skills/spyfighting/my-academic-skills/scientific-ppt-drawing"><img src="https://agentmods.dev/badge/skills/spyfighting/my-academic-skills/scientific-ppt-drawing/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/spyfighting/my-academic-skills/scientific-ppt-drawing"><img src="https://agentmods.dev/badge/skills/spyfighting/my-academic-skills/scientific-ppt-drawing.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 | $0.00052 | $0.01422 |
| Opus 5.5 | $0.00021 | $0.00569 |
| Sonnet 5.5 | $0.00010 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
scientific-ppt-drawing 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 18d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific PPT Drawing
Version 0.1.0. Create a scientific figure whose key biological structures and instruments are recognizable at the intended slide size, while keeping its lines, paths, shapes, and text editable in PowerPoint. This skill creates one figure per slide, then can transfer its native objects to an existing deck. It does not need a data file or vector source when the user asks for a conceptual figure.
Start and route
Resolve skill_dir from this SKILL.md. Read setup and application control on a new machine or when opening an existing deck. Run the bundled CLI with a CPython 3.11–3.13 environment containing requirements.lock:
<python> <skill_dir>/scripts/figure_cli.py doctor
Choose the user's actual input route:
- Description alone: plan the scientific story, panels, labels, iconography, and hierarchy; draw a structured SVG from scratch using paths, basic shapes, and real
<text>. If useful, consult relevant papers for visual conventions and cite them. Illustrative measurements must be visibly identified as illustrative; never infer experimental values from a picture. - Reference image: inspect and redraw the scientific content as intentional PowerPoint objects. Follow semantic drawing: one continuous line should normally become one editable path; construct each instrument or icon from a small set of meaningful parts. Recreate text as live text. Use raster reconstruction only for selected details that cannot reasonably be redrawn by hand, and simplify those traces before delivery. Never place an unchanged full-panel screenshot into the PPTX as the figure.
- Existing SVG: validate it and render it directly. Resolve unsupported effects explicitly; the parser rejects them rather than omitting them.
Treat papers and web pages as visual references, not as evidence that the user's figure contains measured results. Preserve the user's original file and use new output filenames for iterations.
What ships with it
22 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.
- .gitignore 36 B
- agents/openai.yaml 122 B
- assets/blank-native.pptx 11 KB
- examples/compatibility-smoke.svg 374 B
- LICENSE 1.1 KB
- NOTICE.md 1.1 KB
- references/quality-gates.md 3.1 KB
- references/raster-reconstruction.md 1.8 KB
- references/semantic-drawing.md 2.6 KB
- references/setup-and-app-control.md 4.4 KB
- references/svg-and-qa.md 2.2 KB
- requirements-vtracer.lock 69 B
- requirements.lock 311 B
- scripts/figure_cli.py 6.5 KB runs code
- scripts/figurelib/__init__.py 74 B runs code
- scripts/figurelib/common.py 2.1 KB runs code
- scripts/figurelib/powerpoint.py 12 KB runs code
- scripts/figurelib/preview.py 4.6 KB runs code
- scripts/figurelib/svg.py 17 KB runs code
- scripts/figurelib/text.py 8.6 KB runs code
- scripts/figurelib/trace.py 13 KB runs code
- scripts/selfcheck.py 3.5 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.
- 18d ago First seen · 52 lines · 52 tokens per session scan A 43087a57ddba
scientific-ppt-drawing is a skill published in the GitHub repository SPYfighting/my-academic-skills (22 stars, last pushed 17d ago), licensed MIT. It adds 52 tokens to every session and 1,422 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
figure-design
Use when creating, updating, or reviewing a research figure (plot, chart, brain map, heatmap, schematic) — guides chart-type selection, typography, colorblind-safe palette, layout, and journal-specific export specs. Dispatches a figure-reviewer subagent after rendering. Complements claims-audit (which checks figure…
scientific-schematics
Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex…
figure-composer
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data refs, OR from an existing figure via deriveoutlinetask(png). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → fan-out one subagent per panel (each loads figure-style) → tile + stamp letters → adversarial…
academic-poster
A guide for turning a research paper or abstract into a printable academic conference poster. It covers large single-page layouts, including traditional columns and a design that enlarges the main finding.
ieee-figure
Produce publication-grade result figures for IEEE communications papers (JSAC, TWC, TC/TCOM, WCL, CL) — correct column widths, embedded fonts, vector output (PDF/EPS), grayscale- and colorblind-safe palettes, readable fonts, and the comms-standard plot types: BER/outage vs SNR on a log y-axis, achievable/sum rate vs…
academic-figure-figma
Use when the user wants a paper figure (framework, pipeline, architecture, method overview) drawn, rebuilt, or refined as an editable vector in Figma via Claude Code — including reproducing a candidate/reference image (e.g. studio-pro C01-C04) at exact print size. Also use when the user needs to set up or fix the…