PPTX Scientific Poster Builder & Auditor
Builds macro-free, editable PowerPoint conference posters from an author-approved local manifest, with physical-size, printer, accessibility, and package-security audits.
Docs & OfficeAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026
What it does
- Generates a real one-slide editable .pptx research poster from a strict local JSON manifest — no HTML conversion, external templates, API keys, or network calls.
- Enforces provenance: source IDs,
author_verifiedflags, local image paths with SHA-256 hashes, licenses, approved alt text, explicit reading order, and visible QR fallback URLs. - Binds author approval to a canonical content hash, so any later edit invalidates the sign-off.
- Preflights effective DPI (pixels ÷ final placed inches), WCAG 2.2 sRGB contrast pairs, fonts, color mode, and printer trim/bleed/CMYK requirements.
- Ships a non-executing ZIP/XML inspector that rejects macros/VBA, ActiveX, OLE, embedded parts, external relationships, symlinks, and zip-bomb ratios.
- Layout checker catches overlaps, out-of-bounds shapes, and too-small final font sizes; a manual PowerPoint accessibility gate closes the loop.
Who it's for
- Grad students and researchers preparing conference posters
- Lab or comms staff who must hit exact printer and accessibility requirements
- Teams that need to screen incoming .pptx files for security risks
Example uses
- Conference poster build: fill the manifest with final text, figures, and citations →
validate_manifest.py --print-content-hash→ get PI approval on that hash →generate_poster.pyproduces poster.pptx plus a generation report. - Pre-print preflight: run
inventory_images.pyto confirm each figure's effective DPI at its placed size, andcheck_palette.pyto verify contrast and non-color-only encoding before sending to the printer. - Safety screen: run
inspect_pptx.pyon a poster received from a collaborator to detect macros, OLE objects, or remote linked images without ever opening the file.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/pptx-posters/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/pptx-posters folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/pptx-posters/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/pptx-posters ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and clone the repo:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git - Copy the skill into your Claude skills folder:
mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/pptx-posters ~/.claude/skills/ - Verify prerequisites: Python 3.10+ and
uv(python3 --version,uv --version). - Install the exact pinned dependencies:
cd ~/.claude/skills/pptx-posters && uv venv && uv pip install "python-pptx==1.0.2" "Pillow==12.3.0" "lxml==6.1.1" - Restart Claude Code and ask for something like "build my conference poster as an editable PowerPoint file".
- Copy
assets/poster_manifest_template.jsoninto your project, replace every token with real content, sources, and local image paths, then complete the hash-bound author approval step before generating.
View source on GitHub ↗License: MIT