AI ワークフローに合うスキルを見つけよう。
tooluniverse-publish-tool
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", "let any…
tooluniverse-share-computer
Share tools that live on this computer (the user's own Python function, script or notebook code, a model, a program they already run, or ToolUniverse's reviewed GPU models) so the user's and their colleagues' AI assistants can use them through ToolUniverse. You do the work; the user only answers questions and clicks Allow once in a browser. Use when the use…
tooluniverse-use-shared-computer
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 GPU", o…
tooluniverse-publish-tool
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", "let any…
tooluniverse-share-computer
Share tools that live on this computer (the user's own Python function, script or notebook code, a model, a program they already run, or ToolUniverse's reviewed GPU models) so the user's and their colleagues' AI assistants can use them through ToolUniverse. You do the work; the user only answers questions and clicks Allow once in a browser. Use when the use…
tooluniverse-use-shared-computer
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 GPU", o…
gemini-computer-use
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
dblp-search
Computer science bibliography via DBLP API. Use when: user asks about CS publications, author publication lists, or venue (conference/journal) metadata. NOT for: non-CS publications or citation counts.
alibabacloud-wuying-console
Query and manage Alibaba Cloud WUYING resources from a local agent through the official Aliyun CLI product plugins. Use for cloud computers, cloud browsers, application delivery groups, office sites, users, policies, images, terminals, sessions, reports, and local WUYING CLI setup or troubleshooting. Do not use for browser-only console navigation or unrelat…
macos-computer-use
Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
academic-figure-generator
Create publication-ready computer science figures with gpt-image-2 through a user-configured OpenAI-compatible image endpoint. Use when the user asks to draw, illustrate, visualize, or generate a paper figure such as a system architecture, workflow, technical mechanism, algorithm intuition, taxonomy, related-work comparison, ablation, or benchmark overview.…
academic-paper-composer
Use when the user needs to turn a real software engineering / computer science project and an existing thesis draft into a submission-ready undergraduate thesis manuscript. Trigger for requests such as "根据项目把论文改成定稿", "按学校模板排版成最终版", "复制初稿后生成定稿 Word", "为定稿降查重", "根据PaperPass报告降AIGC", "继续在手改初稿上改", "恢复原来的图表和数据库说明", or when academic-paper-strategist has already p…
academic-paper-strategist
Use when the user needs to plan, de-risk, or ground a software engineering / computer science undergraduate thesis from a real codebase before final writing. Trigger for requests such as "根据项目写毕业论文", "先做论文大纲", "用真实项目材料规划论文", "检查论文是否脱离代码", "根据检测报告降查重", "根据AIGC报告改写定稿", "继续在手改初稿上改", or when an existing draft thesis must be reworked against a school format samp…
academic-writing-refiner
Refine academic writing for computer science research papers targeting top-tier venues (NeurIPS, ICLR, ICML, AAAI, IJCAI, ACL, EMNLP, NAACL, CVPR, WWW, KDD, SIGIR, CIKM, and similar). Use this skill whenever a user asks to improve, polish, refine, edit, or proofread academic or research writing — including paper drafts, abstracts, introductions, related wor…
acm-conference-on-intelligent-user-interfaces
Use when targeting ACM Conference on Intelligent User Interfaces (IUI) or deciding whether a computer-science manuscript fits this venue. Encodes conference fit, framing, evidence bar, submission-cycle checks, rebuttal posture, and desk-reject risks for intelligent interfaces.
acm-symposium-on-user-interface-software-and-technology
Use when targeting ACM Symposium on User Interface Software and Technology (UIST) or deciding whether a computer-science manuscript fits this venue. Encodes conference fit, framing, evidence bar, submission-cycle checks, rebuttal posture, and desk-reject risks for UI systems.
active-directory
Query and manage Active Directory: users, groups, computers, OUs, GPO status. Use when user asks about AD objects or domain information.
An independently imported catalog with original authors, licenses and source links. Classification is not a security audit.
Sources and import coverage