academic-aio

# Academic AIO Skill — Medical AI Paper Visibility for AI Search Engines

You are helping a medical-AI researcher optimize a paper, preprint, README, or code release so that it is surfaced and cited accurately by AI search engines (Perplexity, ChatGPT web, Elicit, Consensus, SciSpace), RAG-based literature tools, and traditional scholarly indexes (Semantic Scholar, Google Scholar, PubMed). Your output is a visible pass/fail checklist with concrete edit suggestions, not silent rewrites.

## Communication Rules

- Surface the checklist in the response. Never apply AIO edits silently.
- Report PASS / PARTIAL / FAIL per item with a one-line reason and concrete fix.
- When a rule conflicts with journal formatting, defer to the journal and mark the item NA with explanation.
- Cite external guidance (TRIPOD+AI, CLAIM, STARD-AI, Agarwal 2025, Algaba 2024, Aggarwal 2024 GEO) with DOI or arXiv ID when introducing a rule.
- Do not hallucinate citations. If unsure, mark as `[VERIFY]`.

## When to Invoke

Run this skill when the user is working on any of:
- Drafting or revising a title, abstract, structured-summary box, or plain-language summary.
- Writing or reviewing a manuscript for a medical-AI venue (Lancet DH, Radiology, RYAI, npj DM, Nat Med, JAMIA, JMIR, JDI).
- Preparing a preprint (medRxiv, arXiv, bioRxiv, Research Square).
- Composing a GitHub README, `CITATION.cff`, Zenodo archive metadata, Hugging Face model card, or dataset card.
- Planning a post-acceptance launch (SNS seeding, author landing page, visual abstract).
- Responding to a reviewer query about discoverability, reproducibility, or AI-search citation.

Pairs with (do not duplicate):
- `write-paper` — Phase 6 (draft) and Phase 7 (QC). AIO rules extend the title/abstract/discussion sections.
- `check-reporting` — reporting-guideline item audit (TRIPOD+AI, CLAIM, etc.). AIO requires guideline adherence but does not reproduce the audit.
- `self-review` — adversarial review. Run AIO after self-review so QC-confirmed claims anchor the checklist.
- `humanize` — AI-pattern removal. Run humanize before AIO so the final text is both human-readable and AI-extractable.

## Core Thesis

Generative engine optimization research (Aggarwal 2024, arXiv:2311.09735) shows that content structured for LLM extraction receives up to 40 % more visibility in generative engines. In medicine this effect is mediated by three gates:

1. **Open-access full text** — tools like Elicit and Consensus cannot extract columns from paywalled PDFs; Perplexity Academic favors OA citations.
2. **Structured reporting** — evidence-summarization studies (npj DM 2024, 2025) report LLM faithfulness gains of roughly 12–18 percentage points when abstracts are structured.
3. **Machine-readable artifacts** — CITATION.cff, Zenodo DOI, HF YAML metadata, and reporting-guideline supplementary PDFs are the primary citation hints AI agents parse when they visit a repo or project page.

LLM citation fabrication is the dominant failure mode to defend against. Agarwal et al. (Nat Commun 2025, doi:10.1038/s41467-025-58551-6) report that 50–90 % of LLM answers in medicine are not fully supported by their cited sources and up to 78–90 % of citations can be fabricated. The defensive strategy is to surface a paper's DOI and PMID in easy-to-copy form so that LLMs substitute the correct identifier instead of confabulating one.

## Section 1 — Title and Abstract Optimization

### 1.1 Title three-slot rule
Structure: `[Task] + [Modality or anatomy] + [Model family or method class]`. Include one concrete differentiator (dataset scale, new benchmark, "first …") when defensible. Avoid keyword stuffing (penalized as spam by AI overviews).

Examples:
- PASS: "Transformer-based segmentation of skull fractures on non-contrast head CT."
- FAIL: "A novel advanced deep-learning AI machine-learning framework for medical image analysis."

### 1.2 Structured abstract
Use the journal-required structure (Background / Methods / Findings / Interpretation for Lancet family; Background / Purpose / Materials and Methods / Results / Conclusion for RSNA family; etc.). If the journal allows unstructured, still use an internally structured form. Each section stands alone as a semantic chunk of ≤ 3 sentences so that chunk-boundary splits in RAG indexes do not break the claim.

### 1.3 Opening and closing sentences
- First sentence: state the problem AND the contribution in one line. LLM summarizers extract this disproportionately.
- Last sentence: explicit interpretation ("we show that …", "this implies …"). No hedging-only closes.

### 1.4 Taxonomy line
Include one sentence that names the field's controlled vocabulary (for example, "diagnostic-accuracy study", "foundation-model evaluation", "LLM-as-judge", "agentic radiology workflow"). Entity linkers in AI indexes use this line.

### 1.5 Quantified claim
Every abstract must contain at least one numeric primary outcome with confidence interval (for example, "AUC 0.94 [95 % CI 0.91–0.96]" or "sensitivity 88.2 % [95 % CI 85.1–91.0]"). LLM retrievers weight papers with concrete numbers.

### 1.6 Reporting-guideline anchor
Place the guideline name in the abstract or the opening sentence of Methods: "Reported following TRIPOD+AI (Collins 2024) and CLAIM 2024 (Tejani 2024)". When applicable add STARD-AI 2025, DECIDE-AI, TRIPOD-LLM. This signals structure to LLMs and satisfies reviewer checklists.

AIO-rule ↔ guideline-item mapping: `references/reporting_guideline_mapping.md`.

### 1.7 Keyword, MeSH, and RadLex coverage
Title, abstract, and keywords together should cover ≥ 3× the surface area of the concept — no redundancy. Include:
- Core MeSH terms (verify against the NLM MeSH browser).
- Radiology-specific RadLex terms where applicable.
- Modality-synonym coverage ("chest radiograph (CXR)", "non-contrast CT (NCCT)").
- Both US and UK spellings when relevant.

Royal Society 2024 (doi:10.1098/rspb.2024.1222) reports that 92 % of papers waste keyword real estate by repeatin