Productivity & Collaboration paper-to-slidespdf-extractionpptx-generationacademic-presentationspeaker-notespptxgenjscitation-tracing

Paper-to-Presentation Pipeline

Turns a batch of academic papers into a rigorous, fully traceable course slide deck you can actually present.

FollowSkills review · FSRS-2.0
Use with care
53/ 100 5-point scale 2.7 / 5
1 2 3 4 5 6
1Trust16 / 25 · 3.2/5

The skill only reads/writes files within a local project directory (PDF inputs, intermediates, .pptx output); no network calls, no credential access, no destructive defaults; data flow is transparent and provenance is traceable. Deducted for: no rollback mechanism, no isolation/confirmation constraints over dependent skills (pdf/pptx/ppt-creator), and unverified publisher identity.

2Reliability9 / 20 · 2.3/5

Instructions are self-consistent with clear staging, abnormal-input handling (file-lock PermissionError fallback, figure-mismatch fallback, text-overflow prevention) and explicit failure markers (FIGURE-MISMATCH). Deducted for: no executed validation, no tests, and rules (DPI thresholds, collision checks) that depend on actual agent execution quality rather than mechanisms.

3Adaptability11 / 15 · 3.7/5

Triggers are explicit in both Chinese and English, audience is defined, 'Not For' states non-fit boundaries, and environment assumptions (Windows fonts) are declared. Deducted for: unverified assumption that required sub-skills ship with Claude Code, no version/environment compatibility notes, and partially semantic trigger boundaries.

4Convention8 / 15 · 2.7/5

SKILL.md and README are well-layered with directory conventions, thorough design rationale, and a clear MIT license. Deducted for: no versioning/changelog, no FAQ, no known-limitations section, and unclear ownership/maintenance/update path with an unverified publisher.

5Effectiveness6 / 15 · 2.0/5

The claimed output (a provenance-traceable deck) is plausibly designed, and the verification gates show genuine quality consideration. Deducted for: static review cannot confirm outputs are directly usable, no sample outputs or third-party usage evidence, and comparative benefit over manual workflows is inferred only.

6Verifiability3 / 10 · 1.5/5

The repo contains only instructional files — no tests, no CI, no execution records or independent corroboration. All quality claims (readability thresholds, collision rules) are author assertions with no fact/inference separation.

Evidence confidence:Low Reviewed Sep 10, 2026 Reviewed revision ff201f8daa03
Before you use it
  • This is a static review only; no pipeline stage was executed and actual output quality is unverified.
  • Availability of the pdf, ppt-creator and pptx sub-skills is assumed but unconfirmed; the pipeline fails without them.
  • Verification gates and layout rules rely on agent compliance, not hard mechanisms, so reproduction is not guaranteed.
  • Publisher identity is unverified and there is no versioning or changelog, so long-term maintenance is unclear.
Review evidence [1][2][3]
See the full review method →

What does this skill do, and when should you use it?

This is a Claude Code skill that transforms N paper PDFs into a 15–18 slide, ~20-minute course presentation through four sequential stages. Each stage produces verifiable intermediate artifacts, so failures only require re-running one stage. It enforces full claim provenance, locks the Ocean Gradient palette, requires every headline to be a complete assertion, and puts all citations in speaker notes. Built-in figure verification, a keyword-overlap guardrail, layout collision detection, and a readability check with automatic slide splitting catch the classic failure modes of AI-generated decks.

Reads PDFs from papers/ and runs: agent1 extracts all figures via the pdf skill (≥150 dpi, no content alteration) into an indexed inventory with section context and literal visual descriptions; agent2 extracts conclusive claims, quantitative results, and key metrics tagged to page/paragraph; agent3 applies the pyramid principle to produce a 10-field per-slide spec and runs a mandatory visual verification gate ([VERIFY] lines) on every referenced figure; agent4 generates final_presentation.pptx and speaker_notes.md page-by-page with pptxgenjs, applying a keyword-overlap guardrail, bounding-box collision detection, text-overflow estimation, aspect-ratio-aware sizing, and an effective-DPI/edge-density readability check that auto-splits slides with unreadable figures into a text page plus a full-figure page.

  1. An undergraduate or graduate student preparing a 15–20 minute course talk from papers related to their course
  2. A grad student giving a lab-group paper report that needs traceable citations
  3. Converting a conference poster into an oral presentation
  4. Visualizing a review article as a chapter-structured explanatory deck
  5. Presenters frustrated by garish AI palettes, vacuous headers, and inconsistent citations who want hard constraints

What are this skill's strengths and limitations?

Pros
  • 100% of claims trace to source papers, cited to page/paragraph in speaker notes
  • Four stages with independent verification gates—re-run one stage, not the whole pipeline
  • Locked palette and assertion headlines eliminate AI slop colors and empty section titles
  • Three-layer figure defense: visual verification gate, keyword-overlap guardrail, readability check with auto-split
  • Explicitly documents non-use cases (pitch decks, non-academic content, single-paper lightning talks)
Limitations
  • Strict four-stage sequencing is overkill for a quick single-paper task
  • Assumes an audience of STEM undergraduates past the intro course—wrong fit for lay audiences
  • Auto-splitting unreadable figures adds a slide per flagged figure
  • No test suite or sample outputs in the repo; quality depends on upstream Claude Code built-in skills
  • Fonts guaranteed only for Windows; behavior on other platforms is unverified

How do you install this skill?

Run git clone https://github.com/elinglijiaoqiao/presentation-ppt-maker.git, then ln -s "$(pwd)/presentation-ppt-maker" ~/.claude/skills/paper-to-presentation; or simply copy SKILL.md into ~/.claude/skills/paper-to-presentation/. The pdf, ppt-creator, and pptx skills ship with Claude Code—no extra installation; optionally pair with a paper-search CLI for upstream retrieval (the source does not document how to install it).

How do you use this skill?

1) Create a project directory and place paper PDFs in papers/; 2) execute agent1 → agent2 → agent3 → agent4 in strict order, verifying each output before proceeding; 3) trigger phrases include "presentation from papers", "论文 PPT", "做 pre", or "课程汇报"; 4) collect final_presentation.pptx and speaker_notes.md.

FAQ

Does it cost anything or require extra installs?
The skill is MIT-licensed and free; pdf, ppt-creator, and pptx ship with Claude Code. PPTX generation uses python-pptx and Pillow for image analysis, so you need a local Python environment.
Can I customize the palette or add animations?
No. The Ocean Gradient palette (#065A82/#1C7293/#21295C + white/light gray) is hardcoded, and animations, transitions, gradients, and decorative elements are explicitly banned—a deliberate design choice to avoid garish AI-generated styling.
What if a figure doesn't match its slide?
Three defenses: agent3 must open the actual image and write a [VERIFY] line, swapping the figure or falling back to text-only on mismatch; agent4 compares slide and figure keywords before placement and skips zero-overlap figures, appending a ⚠ FIGURE-MISMATCH warning for manual review.
How long a talk does it support?
It is spec'd for ~20 minutes across 15–18 slides with 45–60 seconds of speaker notes per slide. Longer talks are outside its design scope.

Related skills