jy1529098645-gif
User✍️ Turn your sources into polished academic writing — reviews, proposals, essays, SoPs, résumés — every citation cross-checked, not invented. Runs on Claude, ChatGPT & DeepSeek. A lite, open-source edition of AcademiCats. 用你的文献写出有据成稿、引用逐条核对 —— 可在 Claude / ChatGPT / DeepSeek 上使用。
Categories
Indexed Skills (7)
synthesis-lab
Write grounded academic and application documents from a set of source papers, with strict citation discipline — every specific claim traces to a real supplied paper and citations are cross-checked against those papers before delivery, not fabricated. Use this skill WHENEVER the user wants to draft scholarly or application writing from sources: a literature review, theoretical framework, research proposal, introduction, discussion, conclusion, abstract, or academic essay — or a personal statement / statement of purpose (PhD, grad, study-abroad application) or résumé/CV. Trigger on phrasing like "help me write the lit review for ...", "draft the discussion section from these papers", "write my statement of purpose", "turn these sources into a research proposal", even when the tool isn't named. The defining value is citation grounding: no invented authors, years, or findings.
paper-search
Find academic papers and read them — searches real scholarly databases for prior work on a topic, then resolves and deep-reads the open-access PDF of any paper you pick. Use this skill WHENEVER the user wants to discover literature or read a study: "find recent papers on X", "what does the research say about Y", "find sources for my thesis on Z", "search for prior work on ...", or "summarise / read / extract the findings from this paper / this arXiv id / this DOI / this PDF". Trigger even when the tool isn't named. Results are real papers from public APIs (OpenAlex, Crossref, arXiv, Semantic Scholar, Europe PMC) and reading reports use only the actual extracted PDF text — nothing is fabricated.
paper-review
Simulate a full academic peer-review panel on a draft — examine a manuscript through five independent review lenses (significance, rigor & validity, evidence, argument, clarity), with the methodological criteria adapted to the paper type (CONSORT / STROBE / PRISMA / COREQ / Toulmin), a rebuttal round, a moderator, and a chief editor, then deliver a referee letter plus a scored verdict (Accept / Minor / Major Revision / Reject). Use this skill WHENEVER the user wants critical feedback on their own academic writing: "review my paper / essay / thesis chapter", "give me peer review on this draft", "is this ready to submit?", "what would a reviewer say about my manuscript", "critique my research proposal", or pastes a draft and asks how to improve it. Trigger even when the tool isn't named. Feedback is calibrated to the draft's stage (final / working / sketch / student) so a student essay isn't judged like a journal submission.
citation-formatter
Format academic references into APA 7th, MLA 9th, Chicago Author-Date, IEEE, GB/T 7714-2015, or BibTeX from simple paper metadata (authors, title, year, source, DOI/URL). Deterministic, offline, no LLM needed. Use when a user wants a citation/reference formatted in a specific style, asks for "APA for this paper", "BibTeX entry", "format these references", or needs a bibliography built from paper details.
compare-papers
Distil a set of 2–20 papers into a tight 4–6 sentence comparison: what the set agrees on, the most important divergence or conflict, and which paper to read first and why. Speaks about the set as a whole, not paper-by-paper. Use when a user drops several papers and asks "how do these compare", "what's the consensus / disagreement here", "which should I read first", or wants a quick cross-paper take rather than a full literature overview.
extract-paper-table
Build an Elicit-style comparison table from a set of papers — one row per paper, columns you define (sample, method, setting, key finding, limitation, or anything custom). Each cell is a short, literal answer with "Not reported" when the paper doesn't say. Use when a user wants to extract structured data across multiple papers, compare studies in a table, build a data-extraction matrix for a systematic review, or asks to "tabulate", "extract method/sample size across these papers", or "make a comparison table".
literature-overview
Synthesise a set of papers into a structured, analytical Literature Overview (Field Overview / Core Findings / Methodological Profile / Research Gaps) with inline [P#] markers attributing every claim to its source. Use when a user has a handful of papers or abstracts and wants a synthesis, lit-review section, "related work", or "summarise these papers together" — NOT a per-paper summary, but a synthesis that reveals structure and tension across the set.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.