一个技能，一个新的可能。找到适合你的 AI 工作流。
tooluniverse-publish-tool
【开发与工程】Help the user publish one tool from their shared computer to ToolUniverse so other scientists' AI assistants can find and run it, choosing whether only they, specific colleagues, or everyone can use it. Prepares and tests the tool for them; the user makes the final Publish click. Use when the user says "publish my tool", "put my model in Discover", "…
tooluniverse-use-shared-computer
【开发与工程】Use tools that run on a colleague's computer (for example models on their lab GPU) or tools other scientists published, through ToolUniverse. Covers redeeming a share code that starts with TU-SHARE-, finding the tools, and running them. Use when the user has a TU-SHARE- code or an invitation, says "use my colleague's model", "run the tool on the lab …
tooluniverse-publish-tool
【开发与工程】Help the user publish one tool from their shared computer to ToolUniverse so other scientists' AI assistants can find and run it, choosing whether only they, specific colleagues, or everyone can use it. Prepares and tests the tool for them; the user makes the final Publish click. Use when the user says "publish my tool", "put my model in Discover", "…
tooluniverse-use-shared-computer
【开发与工程】Use tools that run on a colleague's computer (for example models on their lab GPU) or tools other scientists published, through ToolUniverse. Covers redeeming a share code that starts with TU-SHARE-, finding the tools, and running them. Use when the user has a TU-SHARE- code or an invitation, says "use my colleague's model", "run the tool on the lab …
career-development
【数据与研究】Help scientists choose career paths and improve applications, CVs, interviews, and offers. Exclude research-project choices and lab management.
causal-analyst
【文档与办公】A step-by-step way to answer 'did X cause Y?' from a table of data — for data scientists and non-experts alike. Use when someone asks 'did our loyalty program raise spend?', 'what's the real impact of the discount / training / campaign?', 'is this cause or just coincidence?', 'would X still have happened without Y?', or wants the effect of a treatmen…
agri-review
【数据与研究】Multi-reviewer peer-review system for agricultural manuscripts. Simulates an editorial panel — a coordinating editor, three domain reviewers (methodology, domain/novelty, integrity/ethics) and a devil's advocate — plus a formatting check against the target journal, all acting as senior agricultural scientists. Same machinery as food-review, including…
demog-writing-style
【数据与研究】Use when drafting or polishing a Demography (PAA / Duke University Press) manuscript so it reads for population scientists across components, follows the journal's house style (loosely APA), and fits the limits (Research Articles <= 8,000 words main text; Notes <= 4,000; Commentaries <= 2,000; abstract <= 200 words; up to 5 keywords; 3-5 highlights).…
epsl-writing-style
【数据与研究】Use when drafting or compressing prose for an Earth and Planetary Science Letters (EPSL) manuscript. The letters format demands a main text near the 6,500-word cap, a process-forward title and abstract, and prose legible to geochemists, geophysicists, and planetary scientists at once. It guides writing and cutting; it does not invent content.
grad-paradigms
【数据与研究】Apply Kuhn's paradigm theory to analyze scientific progress through the cycle of normal science, anomalies, crisis, and revolution. Use this skill when the user needs to understand why a field resists change, trace paradigm shifts in a discipline, analyze incommensurability between competing frameworks, or when they ask 'why do scientists ignore cont…
instrument-data-to-allotrope
【文档与办公】Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full ASM JSON, flattened CSV for easy i…
jpam-writing-style
【数据与研究】Use when drafting or polishing the prose of a Journal of Policy Analysis and Management (JPAM) manuscript — a clear policy implication stated without overclaiming, legible to economists, political scientists, public-management scholars, and practitioners. Improves clarity and calibration; it does not change the analysis.
lay-summary-for-cross-disciplinary-teams
【数据与研究】Rewrites technical research content into a structured lay summary that cross-disciplinary teams can quickly understand and act on. Use when the user wants to explain research to colleagues outside their specialty — clinicians, wet-lab scientists, bioinformaticians, product managers, or leadership. Trigger on: "lay summary", "explain my research to th…
nature-paper-workflow
【开发与工程】Revise scientific manuscripts or a single section such as the Abstract, Introduction or Discussion, make a technical draft readable for scientists outside the field, improve Results and Review article structure, audit submission evidence, or prepare responses to reviewers. Use for 优化论文、润色论文、改摘要、写引言、面向大同行、去 AI 味、投稿前检查 and 审稿回复. Apply the bundled Natur…
pnas-abstract
【效率与协作】Use to write the PNAS abstract — a single self-contained paragraph of ~250 words, quantified and accessible to a broad scientific audience. Distinguishes the abstract (what/how/found, for scientists) from the Significance Statement (why-it-matters, for everyone). Late-stage polish.
pnasnexus-abstract
【效率与协作】Use to write the PNAS Nexus abstract — a single self-contained paragraph of up to 250 words, with no headings, quantified and accessible to a broad scientific audience. Distinguishes the abstract (what/how/found, for scientists) from the 50–120-word Significance Statement (why-it-matters, for everyone). Late-stage polish.
scientific-problem-selection
【数据与研究】This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choos…
scientific-problem-selection
【数据与研究】This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choos…