agentleFS
Sign inStart free
ScodiveScodive/Paper-Agent-Skills/skills/presentation-slides/SKILL.md

presentation-slides

Skill20 starsChanged 9 days agoMITView on GitHub

Turn a supplied research paper into a source-linked slide storyboard and speaker notes for a lab meeting or conference presentation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. saleem-hadad/presentation-slides★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If dependencies are missing, create a Python 3.10+ virtual environment and install scripts/requirements.txt from this skill.

    line 13
  2. Very specific:

    Use paper-agent instead of python3 src/main.py after installation.

    line 20
  3. Distinctive:

    Keep chart units, baseline names, uncertainty and dataset/split qualifiers.

    line 31
  4. Distinctive:

    Use a clear visual focus when it helps.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research presentation storyboard

For a standalone skill installation, use python3 <installed-skill-directory>/scripts/paper_agent.py instead of python3 src/main.py. Its readable runtime is bundled in scripts/runtime/. If dependencies are missing, create a Python 3.10+ virtual environment and install scripts/requirements.txt from this skill. No model key is needed by the tools.

python3 src/main.py slides --paper paper.pdf --out runs/slides-01

Use paper-agent instead of python3 src/main.py after installation. The command exports complete manuscript text and this skill for the host agent. Write storyboard.md with slide titles, messages, source locators and speaker notes. This workflow produces a storyboard, not a rendered PowerPoint file.

  • Derive the narrative from the actual problem, insight, method, evidence and limitations. Do not infer acceptance or oral status from the task request.
  • Choose length and timing for the stated audience and presentation slot; when unspecified, record the timing assumption.
  • For each scientific claim and chosen figure, cite a manuscript page or line. Identify existing figures to reuse rather than fabricating experimental visuals.
  • Keep chart units, baseline names, uncertainty and dataset/split qualifiers.
  • Use a clear visual focus when it helps. Avoid mandatory word counts or a fixed slide count when equations, comparisons or methods require another layout.
  • Flag missing evidence and required figure assets before final deck production.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free