academic-aio

Name: academic-aio
Author: Aperivue

208stars53forks

How to install academic-aio?

aperivue/medsci-skills/academic-aio

$npx -y skills add Aperivue/medsci-skills --skill academic-aio

Installs into the current project.

Summary

Medical AI paper optimization for AI search engines (Perplexity, ChatGPT web, Elicit, Consensus, SciSpace) and RAG-based literature tools. Applies when drafting or reviewing titles, abstracts, structured summary boxes (Key Points / Research in Context / Plain-Language Summary), m

Files · 1

View on GitHub

SKILL.md

1	# Academic AIO Skill — Medical AI Paper Visibility for AI Search Engines
2
3	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.
4
5	## Communication Rules
6
7	- Surface the checklist in the response. Never apply AIO edits silently.
8	- Report PASS / PARTIAL / FAIL per item with a one-line reason and concrete fix.
9	- When a rule conflicts with journal formatting, defer to the journal and mark the item NA with explanation.
10	- Cite external guidance (TRIPOD+AI, CLAIM, STARD-AI, Agarwal 2025, Algaba 2024, Aggarwal 2024 GEO) with DOI or arXiv ID when introducing a rule.
11	- Do not hallucinate citations. If unsure, mark as `[VERIFY]`.
12
13	## When to Invoke
14
15	Run this skill when the user is working on any of:
16	- Drafting or revising a title, abstract, structured-summary box, or plain-language summary.
17	- Writing or reviewing a manuscript for a medical-AI venue (Lancet DH, Radiology, RYAI, npj DM, Nat Med, JAMIA, JMIR, JDI).
18	- Preparing a preprint (medRxiv, arXiv, bioRxiv, Research Square).
19	- Composing a GitHub README, `CITATION.cff`, Zenodo archive metadata, Hugging Face model card, or dataset card.
20	- Planning a post-acceptance launch (SNS seeding, author landing page, visual abstract).
21	- Responding to a reviewer query about discoverability, reproducibility, or AI-search citation.
22
23	Pairs with (do not duplicate):
24	- `write-paper` — Phase 6 (draft) and Phase 7 (QC). AIO rules extend the title/abstract/discussion sections.
25	- `check-reporting` — reporting-guideline item audit (TRIPOD+AI, CLAIM, etc.). AIO requires guideline adherence but does not reproduce the audit.
26	- `self-review` — adversarial review. Run AIO after self-review so QC-confirmed claims anchor the checklist.
27	- `humanize` — AI-pattern removal. Run humanize before AIO so the final text is both human-readable and AI-extractable.
28
29	## Core Thesis
30
31	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:
32
33	1. Open-access full text — tools like Elicit and Consensus cannot extract columns from paywalled PDFs; Perplexity Academic favors OA citations.
34	2. Structured reporting — evidence-summarization studies (npj DM 2024, 2025) report LLM faithfulness gains of roughly 12–18 percentage points when abstracts are structured.
35	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.
36
37	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.
38
39	## Section 1 — Title and Abstract Optimization
40
41	### 1.1 Title three-slot rule
42	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).
43
44	Examp

People who liked this also viewed

6 picks

Type

academic-aio

208stars53forks

View on GitHub

How to install academic-aio?

aperivue/medsci-skills/academic-aio

$npx -y skills add Aperivue/medsci-skills --skill academic-aio

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Academic AIO Skill — Medical AI Paper Visibility for AI Search Engines
2
3	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.
4
5	## Communication Rules
6
7	- Surface the checklist in the response. Never apply AIO edits silently.
8	- Report PASS / PARTIAL / FAIL per item with a one-line reason and concrete fix.
9	- When a rule conflicts with journal formatting, defer to the journal and mark the item NA with explanation.
10	- Cite external guidance (TRIPOD+AI, CLAIM, STARD-AI, Agarwal 2025, Algaba 2024, Aggarwal 2024 GEO) with DOI or arXiv ID when introducing a rule.
11	- Do not hallucinate citations. If unsure, mark as `[VERIFY]`.
12
13	## When to Invoke
14
15	Run this skill when the user is working on any of:
16	- Drafting or revising a title, abstract, structured-summary box, or plain-language summary.
17	- Writing or reviewing a manuscript for a medical-AI venue (Lancet DH, Radiology, RYAI, npj DM, Nat Med, JAMIA, JMIR, JDI).
18	- Preparing a preprint (medRxiv, arXiv, bioRxiv, Research Square).
19	- Composing a GitHub README, `CITATION.cff`, Zenodo archive metadata, Hugging Face model card, or dataset card.
20	- Planning a post-acceptance launch (SNS seeding, author landing page, visual abstract).
21	- Responding to a reviewer query about discoverability, reproducibility, or AI-search citation.
22
23	Pairs with (do not duplicate):
24	- `write-paper` — Phase 6 (draft) and Phase 7 (QC). AIO rules extend the title/abstract/discussion sections.
25	- `check-reporting` — reporting-guideline item audit (TRIPOD+AI, CLAIM, etc.). AIO requires guideline adherence but does not reproduce the audit.
26	- `self-review` — adversarial review. Run AIO after self-review so QC-confirmed claims anchor the checklist.
27	- `humanize` — AI-pattern removal. Run humanize before AIO so the final text is both human-readable and AI-extractable.
28
29	## Core Thesis
30
31	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:
32
33	1. Open-access full text — tools like Elicit and Consensus cannot extract columns from paywalled PDFs; Perplexity Academic favors OA citations.
34	2. Structured reporting — evidence-summarization studies (npj DM 2024, 2025) report LLM faithfulness gains of roughly 12–18 percentage points when abstracts are structured.
35	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.
36
37	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.
38
39	## Section 1 — Title and Abstract Optimization
40
41	### 1.1 Title three-slot rule
42	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).
43
44	Examp

People who liked this also viewed

6 picks

Type