skills/academic-presentation-crafter/SKILL.md
Creates and refines academic presentations from research papers. Use this skill for tasks involving the conversion of scientific or technical documents into slide decks for conferences, seminars, lectures, thesis defenses, or academic reviews. Supports beamer LaTeX (.tex), PowerPoint (.pptx), and Markdown output formats.
npx skillsauth add mr-fang-vlsi/edagent academic-presentation-crafterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides a structured, multi-phase workflow for transforming dense research papers into clear, concise, and academically rigorous presentations. It ensures the final slide deck accurately reflects the paper's core contributions, data, and terminology.
The process is divided into four distinct phases. Follow these steps sequentially to ensure a high-quality outcome. For detailed checklists on rigor and visual polish, refer to the references/ directory.
When the audience is external (advisor, committee, collaborator), enforce:
Baseline, Variant-B).Case-A, Case-B) and move raw identifiers to private appendix only if requested.beamer (.tex) and compile to .pdf; otherwise keep a clean Markdown deck as fallback.Action: follow references/external_reporting_sanitization_checklist.md before finalizing.
The goal of this phase is to deeply understand the source material and create a logical structure for the presentation.
.md) with --- page separators. A typical academic structure is recommended (Motivation, Methods, Results, Conclusion). Start with 8-12 slides and expand only if necessary.This phase focuses on populating the slides with content and integrating the necessary visual aids.
This phase ensures the presentation meets academic standards. Apply the full checklist in references/academic_rigor_checklist.md, paying special attention to these critical items:
Feedback loop: After applying the checklist, revisit Phase 2 slides, update any corrected content, and re-verify data placeholders.
Apply the full checklist in references/visual_polish_checklist.md, focusing on these high-impact items:
Feedback loop: Do a full sequential walkthrough of the deck. If any slide feels unclear or visually inconsistent, return to the relevant earlier phase before finalizing.
A results slide in Markdown format:
## Results: Timing Closure Improvement
- Proposed flow achieves **12% WNS reduction** vs. baseline (Table 3)
- Area overhead: +2.1% (within PPA budget)
- Runtime: 3.2x faster than conventional approach

<!-- Source: Fig. 5, Section IV-B -->
> Speaker notes: Emphasize the WNS improvement first, then address
> the area-runtime tradeoff. Reference Table 3 for detailed breakdowns.
development
Create immutable stage checkpoints for Innovus flows. Use when users ask for fixed golden files or restart-from-stage workflows (place/cts/route) with matched DEF+V+SDC and reproducible manifests.
tools
Capture and maintain reusable script-writing experience across wrappers, helpers, parsers, validators, and runtime shims so future script work can reuse proven patterns and avoid repeated anti-patterns.
testing
Summarize local paper PDFs into structured, citation-grounded evidence notes. Use when the user provides local PDF paths and asks for methods/assumptions/results/limitations extraction or wants evidence mapped to current EDA hypotheses.
development
Fetch primary-source paper metadata when evidence is missing or weak for EDA/model/flow claims. Use for requests like building reproducible paper candidate lists, generating user-download queues, and recording citation metadata for local validation.