Agent skill

Academic Presentation Maker

by OpenLAIR in OpenLAIR/dr-claw

Turns a research paper into a slide deck and, optionally, a narrated demo video, through script, slide generation, text-to-speech and video assembly stages you control.

Custom licenceAuto-check passedDocuments & Office

Install Academic Presentation Maker

skills CLI
$ npx skills add OpenLAIR/dr-claw --skill making-academic-presentations -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenLAIR/dr-claw making-academic-presentations --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenLAIR/dr-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/making-academic-presentations .claude/skills/making-academic-presentations && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
making-academic-presentations
GitHub stars
1.2k
Token cost
~1.5k tokens
SKILL.md length
504 words
Files
6 (incl. scripts, references)
Skills in repo
36
Repo updated
First seen
Licence
Custom licence

At a glance

Turns a research paper into a slide deck and, optionally, a narrated demo video, through script, slide generation, text-to-speech and video assembly stages you control.

  • Works in 4 steps: Script / Outline → Slide Generation → TTS Audio (optional) → …
  • Turning a research paper into a conference talk deck
  • SKILL.md covers Pipeline, Stage 1: Script / Outline, Stage 2: Slide Generation and Stage 3: TTS Audio (optional), plus 5 more sections
  • Runs Python scripts from its folder; calls ffmpeg, brew and pip; reaches github.com; needs ELEVENLABS_API_KEY

What it does

The skill produces academic slide decks, and optionally narrated demo videos, from research papers. The human drives every outline and visual decision and the agent executes. The pipeline has four stages: a script or outline draft from the paper and your plan, slide generation, optional TTS audio and optional video assembly. You can enter at any stage, or skip the last two for slides only.

Slides are generated with nanobanana, a Gemini CLI extension, preferring its /edit command on existing paper figures, existing slides or your reference decks over generating from scratch, with a deck-style.md written once per deck and prepended to prompts for slides generated from scratch. For narration, edge-tts is the default, Kokoro is a local engine for offline batch runs and ElevenLabs is also listed, each with a reference or batch script. Video is assembled with ffmpeg.

Reference files cover slide generation, TTS engines and PPTX conversion. The agent drafts scripts from your outline but does not choose the slide count, order or what to emphasize.

When your agent uses it

  • Turning a research paper into a conference talk deck
  • Producing narration scripts and TTS audio for each slide
  • Assembling a demo video from slides and audio
  • Converting generated slides into a PPTX file

Example prompts

  • “Make a conference talk deck from ./papers/diffusion-survey.pdf using my outline in ./talk/outline.md.”
  • “Draft narration scripts for each slide and generate the audio with Kokoro.”
  • “Assemble the slides and audio in ./talk into a demo video.”

Requirements

  • The nanobanana extension for Gemini CLI
  • edge-tts or Kokoro, for narration
  • ffmpeg, for video assembly

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Script / Outline
  2. Slide Generation
  3. TTS Audio (optional)
  4. Video Assembly (optional)

What it can do on your machine

Read from SKILL.md and the folder at commit d51b64e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • ffmpeg
    • brew
    • pip
    • claude
    • soffice
    • pdftoppm
    • gemini

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ELEVENLABS_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Academic Presentation Maker loads about 1.5k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 504 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 504 words (~1,521 tokens).

“Produce slide decks (and optionally narrated demo videos) from research papers. The human drives all outline and visual decisions — the agent executes.”

— opening of SKILL.md by OpenLAIR, Custom licence
name
making-academic-presentations

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (scripts, references) in skills/making-academic-presentations of OpenLAIR/dr-claw.

  • SKILL.md
  • references/pptx-conversion.md
  • references/slide-generation.md
  • references/tts-engines.md
  • scripts/batch_tts_edge.py
  • scripts/batch_tts_kokoro.py

Open the folder on GitHubat commit d51b64e

Compare with similar skills

Academic Presentation Maker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Academic Presentation Maker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Academic Presentation Maker this skillOpenLAIR/dr-claw1.2k—~1.5kAutomated safety check: PassCustom licence
Video Productionspeechlab0210/video-production-skill105—~4.1kAutomated safety check: NotesMIT
Render Hand Swipe Flavor Listiclegooseworks-ai/goose-skills1.2k—~2.9kAutomated safety check: PassMIT
Render Ig Live Gallerygooseworks-ai/goose-skills1.2k—~1kAutomated safety check: PassMIT
Render Search Gridgooseworks-ai/goose-skills1.2k—~1.1kAutomated safety check: PassMIT
Roadshow Video Generatoranbeime/skill7.7k—~1.4kAutomated safety check: NotesNone

Similar skills

  • Video Production

    speechlab0210/video-production-skill

    AI educational video production pipeline. An agent skill from speechlab0210/video-production-skill.

    105 GitHub stars~4.1k tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes
  • Render Hand Swipe Flavor Listicle

    gooseworks-ai/goose-skills

    Render a 'hand-swipe flavor listicle' video from a config — the brand's REAL product cutouts each float on a flat flavor-matched color field under a persistent title and slide RIGHT-TO-LEFT one to…

    1.2k GitHub stars~2.9k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Render Ig Live Gallery

    gooseworks-ai/goose-skills

    Render an 'Instagram-Live social-proof gallery' video from a config — ~5 real brand product stills each framed as an Instagram-LIVE card (IG gradient-ring avatar, username, verified check, red LIVE…

    1.2k GitHub stars~1k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Render Search Grid

    gooseworks-ai/goose-skills

    Render a 'search-grid' (Pinterest search-moodboard) video from a config — a real-DOM page with four continuous beats (masonry search grid + typing hook with counter-drift columns → 3 cards slide in…

    1.2k GitHub stars~1.1k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Turns a document into a narrated roadshow video through ten staged roles, from document analysis and slide planning to audio, subtitles and final composition.

    7.7k GitHub stars~1.4k tokensUpdated yesterday
    Media & CreativeAuto-check: notes
  • AI Presenter Video

    NousResearch/hermes-agent

    Produces a presenter-led video from a topic or script plus one authorized presenter image, with captions, lip-sync checks and acceptance reports.

    252k GitHub stars~2.3k tokensUpdated today
    Media & CreativeAuto-check passed

More from OpenLAIR/dr-claw

All 36 skills in this repo
  • Analyzes reviewer comments and drafts venue-specific rebuttals for AI and computer science conferences, with an issue board, task list and paper edit plan.

    1.2k GitHub stars~4.9k tokensUpdated 22 days ago
    Auto-check: notes
  • Clusters the latest news-feed results by topic and writes a briefing of research idea seeds with citations, plus a structured seeds file, without crawling new sources.

    1.2k GitHub stars~1.3k tokensUpdated 22 days ago
    Auto-check: notes
  • ML Dataset Discovery

    OpenLAIR/dr-claw

    Searches Hugging Face Hub, OpenML, GitHub and paper references for datasets that fit a research task and returns a ranked, de-duplicated table.

    1.2k GitHub stars~741 tokensUpdated 22 days ago
    Auto-check passed
  • Gemini Deep Research

    OpenLAIR/dr-claw

    Runs multi-source web research through Google's Gemini Deep Research Agent with a bundled Python script and saves a structured, cited report as files.

    1.2k GitHub stars~996 tokensUpdated 22 days ago
    Auto-check passed
  • Six-phase workflow for writing, revising and adapting grant proposals for NSF, NIH, DOE, DARPA, NASA and China's NSFC, from profiling through simulated peer review.

    1.2k GitHub stars~9.2k tokensUpdated 22 days ago
    Auto-check passed
  • Inno Rclone To Overleaf

    OpenLAIR/dr-claw

    Access Overleaf projects via CLI. An agent skill from OpenLAIR/dr-claw.

    1.2k GitHub stars~1.2k tokensUpdated 22 days ago
    Auto-check passed

Questions about Academic Presentation Maker

What does Academic Presentation Maker do?

Turns a research paper into a slide deck and, optionally, a narrated demo video, through script, slide generation, text-to-speech and video assembly stages you control. The skill produces academic slide decks, and optionally narrated demo videos, from research papers. The human drives every outline and visual decision and the agent executes.

When should I use Academic Presentation Maker?

Academic Presentation Maker fits situations like: turning a research paper into a conference talk deck; producing narration scripts and TTS audio for each slide; assembling a demo video from slides and audio; converting generated slides into a PPTX file.

How do I install Academic Presentation Maker in Claude Code?

Run `npx skills add OpenLAIR/dr-claw --skill making-academic-presentations -a claude-code`. Or copy the skill folder (skills/making-academic-presentations in OpenLAIR/dr-claw) into .claude/skills/making-academic-presentations in your project. Claude Code loads it when a task matches its description.

How do I install Academic Presentation Maker in Codex?

Run `npx skills add OpenLAIR/dr-claw --skill making-academic-presentations -a codex`. Or copy the skill folder (skills/making-academic-presentations in OpenLAIR/dr-claw) into .agents/skills/making-academic-presentations in your project. Codex loads it when a task matches its description.

Can I use Academic Presentation Maker in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenLAIR/dr-claw --skill making-academic-presentations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/making-academic-presentations, .gemini/skills/making-academic-presentations, .github/skills/making-academic-presentations and .opencode/skills/making-academic-presentations in your project.

What does Academic Presentation Maker need to run?

Going by SKILL.md and its folder, Academic Presentation Maker needs Python for the scripts in its folder, the command-line tools its instructions call (ffmpeg, brew, pip, claude, soffice and pdftoppm) and credentials named ELEVENLABS_API_KEY. Our summary lists: The nanobanana extension for Gemini CLI; edge-tts or Kokoro, for narration; ffmpeg, for video assembly.

Does Academic Presentation Maker access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Academic Presentation Maker safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Academic Presentation Maker use?

Academic Presentation Maker has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Academic Presentation Maker use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Academic Presentation Maker?

Skills that share tags, products or a category with Academic Presentation Maker: Video Production (speechlab0210/video-production-skill, 105 stars), Render Hand Swipe Flavor Listicle (gooseworks-ai/goose-skills, 1.2k stars), Render Ig Live Gallery (gooseworks-ai/goose-skills, 1.2k stars) and Render Search Grid (gooseworks-ai/goose-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Academic Presentation Maker?

OpenLAIR (a GitHub organization) maintains it in OpenLAIR/dr-claw, which has 1,155 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on September 17, 2026.

Source: OpenLAIR/dr-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.