Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fangyuanopus/literature-report-ppt-buildernpx agentmods add skills/fangyuanopus/literature-report-ppt-builder/academic-slide-pragmatic-fallbackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fangyuanopus/literature-report-ppt-builder/academic-slide-pragmatic-fallback)<a href="https://agentmods.dev/skills/fangyuanopus/literature-report-ppt-builder/academic-slide-pragmatic-fallback"><img src="https://agentmods.dev/badge/skills/fangyuanopus/literature-report-ppt-builder/academic-slide-pragmatic-fallback/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fangyuanopus/literature-report-ppt-builder/academic-slide-pragmatic-fallback"><img src="https://agentmods.dev/badge/skills/fangyuanopus/literature-report-ppt-builder/academic-slide-pragmatic-fallback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01370 |
| Opus 5 | $0.00046 | $0.00685 |
| Sonnet 5 | $0.00019 | $0.00274 |
| Haiku 4.5 | $0.00009 | $0.00137 |
Grade A, and why
academic-slide-pragmatic-fallback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Slides with Safe Fallbacks
Create academic decks that are evidence-led, readable, and honest about their production route.
Non-negotiable rules
- Use scientific visuals only from the paper, SI, or user-provided sources. Never fabricate, redraw, or semantically alter data figures, microscopy, spectra, molecular structures, mechanisms, tables, or charts.
- Write conclusion-style titles, trace every visual in a figure-source manifest, and calibrate claims to evidence.
- Do not call an editable or code-built deck Image2-only.
Choose one route
Route A: Image2-only authoritative deck
Use only when a full-slide Image2 backend is confirmed and can faithfully preserve supplied scientific crops. Keep image2_manifest.json, package one approved full-slide image per PPTX slide, and run scripts/validate_image_only_pptx.py.
Route B: template-fidelity fallback
Use only after explicit user consent and a passed hygiene audit. The template owns its navigation, footer, and mapped slots; code edits inherited objects in place and must not add a second navigation layer.
When the user explicitly asks to reproduce the bundled sample template exactly, use Route B's exact-template mode. Preserve the sample's navigation labels and decorative chrome intentionally, map each output page to a distinct source-slide archetype, and replace or remove every source-specific scientific object. Do not describe a code-redrawn Route C deck as an exact reproduction. Read references/exact-template-fidelity.md before building.
python scripts/build_fallback_template_pptx.py edit_plan.json exact.pptx --strict --fail-on-warnings
python scripts/audit_fallback_template_pptx.py exact.pptx --build-report exact.build-report.json --check-masters --exact-template --fail-on-review
python scripts/audit_exact_template_fidelity.py exact.pptx --plan edit_plan.json --build-report exact.build-report.json --fail-on-review
python scripts/audit_fallback_template_pptx.py template.pptx --check-masters --fail-on-review
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 472 B
- assets/icon.svg 1.2 KB
- assets/sample-literature-report.pptx 3883 KB
- references/adaptive-navigation.md 3.3 KB
- references/annotation-language.md 1.4 KB
- references/backup-slides.md 2.4 KB
- references/batch-image-consistency.md 1.5 KB
- references/close-reading-rules.md 4.5 KB
- references/deck-diagnosis-mode.md 2.0 KB
- references/deck-order-map.md 1.9 KB
- references/delivery-package.md 6.8 KB
- references/domain-adaptation.md 3.3 KB
- references/editable-output-options.md 2.3 KB
- references/evidence-strength.md 1.9 KB
- references/exact-template-fidelity.md 2.9 KB
- references/failure-recovery.md 3.7 KB
- references/fallback-template-edit-spec.md 15 KB
- references/fallback-template-pptx.md 11 KB
- references/figure-extraction-and-naming.md 3.4 KB
- references/figure-readability-standard.md 2.0 KB
- references/figure-source-manifest.md 2.8 KB
- references/final-delivery-preview.md 1.1 KB
- references/final-page-lock.md 1.3 KB
- references/final-scoring-rubric.md 1.2 KB
- references/first-template-style-contract.md 1.8 KB
- references/full-deck-reorder-mode.md 1.6 KB
- references/generation-brief-template.md 4.2 KB
- references/high-quality-production-protocol.md 6.3 KB
- references/image-generation-status.md 1.1 KB
- references/image2-execution-gate.md 4.0 KB
- references/main-si-crosswalk.md 1.3 KB
- references/mainline-backup-boundary.md 1.6 KB
- references/navigation-examples-by-domain.md 1.8 KB
- references/page-brief-template.md 3.7 KB
- references/paper-analysis-contract.md 3.3 KB
- references/paper-analysis.example.json 3.8 KB
- references/paper-to-ppt-workflow.md 8.2 KB
- references/post-assembly-render-audit.md 1.0 KB
- references/pragmatic-fallback.md 2.1 KB
- references/pre-assembly-checklist.md 1.4 KB
- references/quality-gates.md 14 KB
- references/question-prep.md 2.0 KB
- references/question-risk-level.md 1.3 KB
- references/real-figure-annotation-rules.md 1.7 KB
- references/redraw-priority.md 1.6 KB
- references/sample-deck-rhythm.md 4.4 KB
- references/sample-layout-grammar.md 2.5 KB
- references/sample-style-spec.md 2.8 KB
- references/sample-template-intro.md 3.4 KB
- references/sample-template-slot-manifest.json 208 KB
- references/speaker-notes-template.md 2.3 KB
- references/speaker-notes-to-slide-check.md 1.2 KB
- references/style-checklist.md 4.4 KB
- references/template-hygiene.md 2.3 KB
- references/terminology-control.md 2.6 KB
- references/trend-emphasis-rules.md 2.0 KB
- references/version-control-and-final-folder.md 1.1 KB
- scripts/audit_exact_template_fidelity.py 18 KB runs code
- scripts/audit_fallback_template_pptx.py 14 KB runs code
- scripts/build_fallback_template_pptx.py 40 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 84 lines · 93 tokens per session scan A 8dc3529b6044
academic-slide-pragmatic-fallback is a skill published in the GitHub repository fangyuanopus/literature-report-ppt-builder (107 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 1,370 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
thesis-defense-pptx
Create, polish, and quality-check editable undergraduate or graduate thesis defense PowerPoint decks from a local thesis PDF/LaTeX project and an existing PPTX template. Use when the user asks for a formal defense PPT, thesis presentation, academic答辩PPT, template-matched PPTX, or local PowerPoint deck generation with…
keshav-three-pass
Tactic: Read one paper by Keshav's three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.
present-paper
Academic presentation preparation — paper-driven (journal club, grand rounds, seminar) and lecture/teaching decks (course material, workshop slides, conference talks). Analyzes source material, finds supporting references, drafts audience-adapted speaker scripts, generates or augments PPTX with speaker notes, and…
paper-slide-deck
Generate professional slide deck images from academic papers and content. Creates comprehensive outlines with style instructions, auto-detects figures from PDFs, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", or "slide deck" for papers.
challenge-operation
Non-threatening 'Why?' questioning of current practices (de Bono Challenge).
first-pass-skim
Keshav's first pass over one paper — a 5-10 minute skim of title, abstract, headings, figures, and conclusion only, producing skim notes and a read-deeper judgment. Use this as the first step whenever a paper is being read via the Keshav three-pass method; always precedes second-pass-grasp and never reads section…