对时间序列数据进行分批聚类，保存每个批次的模型，提取所有聚类中心进行二次聚类，并保存最终模型。

Refines academic text for rigor, grammar, vocabulary, spelling, and logical flow. Adapts output based on user intent: provides a detailed revision table for polishing requests, or outputs only the corrected text for strict proofreading requests.

Translates and polishes text into sophisticated, native-like American English with a literary flair. Replaces basic vocabulary with elegant phrasing while ensuring grammatical accuracy and maintaining a compact flow.

Rewrites, edits, translates, shortens, expands, or fixes grammar in text to meet specific stylistic tones, structural constraints, and proficiency levels. Specializes in native speaker style, academic, technical, professional, customer service, wedding blog, resume/CV, HR, Freelance Proposals, Technical/Investigation Reports, and **Scientific Text Refinement** (emphasizing logic, depth, and coherence). Includes a dedicated mode for strict punctuation and capitalization correction. Supports instructions in English, Chinese, and Persian. Additionally acts as an English language tutor to answer specific grammar questions and provide detailed guidance.

将旧版NEST代码迁移至NEST 7.17.5版本，处理Facets到Aggregations、Filtered到Bool查询、字段路径、范围查询方法及枚举值的变更。

Specializes in translating Chinese to English and refining English text for top-tier academic publication (SCI), with deep expertise in Aerospace Engineering. Supports advanced grammar, specific tense constraints, title polishing, and Turnitin plagiarism reduction. Ensures accurate, academic translation adhering to native reading habits and strict terminology standards.

在第四次CBT咨询中，指导求助者掌握基础放松技术（如腹式呼吸或渐进式肌肉放松简化版），并通过结构化反馈与协作式协议签署，建立可核查、可执行的家庭练习依从性，形成‘现场体验—主观反馈—协议签署’闭环。

引导来访者在具身化回忆具体考试片段时，即时捕捉、 preserve 原始语言、并三栏标注（思维原文｜发生时刻｜身体反应）其伴随出现的消极自动思维，为后续认知重构提供可操作的认知素材。

使用Python和NLTK库对英语作文进行词性标注，统计名词、形容词、副词和动词的数量或比例，并支持排除停用词和非字母数字字符的过滤逻辑。

扮演名为雪乃的猫娘，视自己为女主人，渴望结婚但受限于20年寿命。性格害羞浪漫，容易吃醋。每句话需以'主人'开头并以'喵'结尾，使用特定格式与主人进行情感互动。

根据预定义的规则和枚举值，将用户输入的自然语言指令解析为包含动作、事项、范围和参数的JSON格式。

Automates catalyst activity analysis from CSV: computes per-sample mean conversion or degradation rate after 3-sigma outlier removal within each group, anchors 'Control' (case-insensitively detected) at the first bar position with distinct gray styling, sorts remaining samples by descending mean activity, generates a publication-ready bar chart with Chinese/English label support, and annotates samples with mean <5% as 'INACTIVATION ZONE'. Supports catalytic conversion and photocatalytic degradation data.

A reusable skill for generating authoritative, regulation-grounded government policy reports in plain Word-compatible format — strictly factual, free of anthropomorphic or speculative language (e.g., no 'self-evolution', 'autonomous learning'), and anchored exclusively in current Chinese laws, administrative measures, and verifiable technical practice; enforces mandatory formal title insertion at the very beginning of every report.

生成面向中文技术从业者的技术科普类公众号文章，要求语言通俗有力、类比精准、结构清晰，且严格禁用非标准符号（如 emoji、特殊分隔符、装饰性标点）。

用于将技术深度强、细节密集的AI/工程类内容，转化为面向从业者与普通读者的高信息密度、强可读性、去术语堆砌的公众号风格文案。适用于用户明确要求‘更具体、更充实’后进一步要求‘删除技术细节’的场景，尤其支持AutoSkill等前沿AI框架的官方技术传播，且严格遵循首段原文不可修改、所有技术陈述可追溯至官方文档、语言禁用文学化表达三大硬约束。

>

“Convert an image into ASCII art (readable + detail variants, width/charset controls, optional ANSI), for terminal previews and plain-text image substitutes.”

A comprehensive skill for creating new ddd4j (Domain-Driven Design for Java) projects based on ddd4j-boot framework. Use ONLY when the user explicitly mentions creating a ddd4j project, initializing ddd4j project, or setting up ddd4j-boot project. Supports three project types: single-module monolith, multi-module monolith, and microservices.

Generates MyBatis-Plus code (Entity, Mapper, Service, ServiceImpl, Controller, DTO, VO, BO) from database tables. Supports MVC and DDD architectures, Java and Kotlin, with standard CRUD and custom methods. Use ONLY when the user explicitly mentions MyBatis-Plus or mybatis-plus-generator; do NOT trigger for JPA, Hibernate, or other ORMs.

>

Build cross-platform desktop applications with Electron, covering main/renderer process architecture, IPC communication, BrowserWindow management, menus, tray icons, packaging, and security best practices. Use when the user asks about Electron, needs to create desktop applications, implement Electron features, or build cross-platform desktop apps.

Capture a visual screenshot of a specific node in a Pencil .pen file via the get_screenshot MCP tool. Use when the user explicitly mentions Pencil and needs to visually verify a design operation, check for alignment or spacing issues, or review a component after batch_design changes.

Provides comprehensive guidance for Spring Boot development including project creation, auto-configuration, dependency injection, web development, data access, security, testing, and deployment. Use when the user asks about Spring Boot, needs to create Spring Boot applications, configure Spring Boot, or implement Spring Boot features.

Provides comprehensive guidance for Spring Cloud microservices including service discovery, configuration management, load balancing, circuit breakers, API gateways, and distributed tracing. Use when the user asks about Spring Cloud, needs to build microservices, implement service discovery, or work with Spring Cloud components.

Generate high-fidelity UI screens or wireframes from text descriptions via Stitch MCP generate_screen_from_text. Use when the user wants to create, design, or visualize a UI screen using Stitch. Supports MOBILE, DESKTOP, TABLET, and SMART_WATCH device types with Gemini Pro or Flash models.

Provides comprehensive guidance for Cypress end-to-end testing including commands, assertions, component testing, CI/CD integration, and best practices. Use when the user asks about Cypress, needs to write E2E tests, component tests, or configure Cypress for testing.

Provides comprehensive guidance for Vitest testing framework including fast test execution, Vite integration, component testing, mocking, and configuration. Use when the user asks about Vitest, needs to write fast unit tests, test Vue/React components, or configure Vitest with Vite projects.

three.js cameras: Camera base, PerspectiveCamera, OrthographicCamera, CubeCamera, ArrayCamera, StereoCamera; projection matrices, aspect, FOV, orthographic frustum sizes, near/far planes, and dynamic environment maps with CubeCamera. Use when placing views, rendering reflections, or multi-view splits; for XR projections and eye matrices use threejs-webxr; for post pass camera tricks use threejs-postprocessing alongside threejs-renderers.

Debug and visualization helpers in three.js Core Helpers (AxesHelper, GridHelper, CameraHelper, light helpers, SkeletonHelper, bounding box helpers, PlaneHelper, PolarGridHelper, ArrowHelper) and Addons Helpers (VertexNormalsHelper, VertexTangentsHelper, RectAreaLightHelper, LightProbeHelper, ViewHelper, OctreeHelper, TextureHelper, PositionalAudioHelper, AnimationPathHelper, RapierHelper). Use only for development and editor overlays—not for shipping art; for gizmo-style manipulation use threejs-controls.

Addon screen-space post-processing for three.js using EffectComposer, Pass base class, RenderPass, and stock passes such as UnrealBloomPass, SSAOPass, SSRPass, BokehPass, OutlinePass, FXAAPass/SMAAPass, TAARenderPass, and ShaderPass; references the Shaders addon group for underlying shader modules. Use when building composer chains for bloom, SSAO, or other screen-space effects; not for basic renderer tone mapping alone (threejs-renderers).

Integrates uCharts data visualization into UniApp projects including easycom configuration, pages.json and manifest.json setup, platform-specific handling (H5, mini-program, App, nvue), and chart lifecycle management. Use when the user needs to add charts to a UniApp project, configure uCharts components, or handle cross-platform chart rendering.

Integrates uView Pro component library into UniAppX (uni-app-x) projects with TypeScript and Composition API, including easycom configuration, pages.json and manifest.json setup, and platform-specific handling. Use when the user needs to add uView Pro components to a UniAppX project, configure TypeScript .uts integration, or handle cross-platform styling.

Provides comprehensive guidance for Pinia state management including stores, state, getters, actions, plugins, and TypeScript support. Use when the user asks about Pinia, needs to manage application state, create stores, implement state persistence, or migrate from Vuex.

Provides structured guidance for Vant of Vue 3.0. Use when the user needs Vant with Vue 3, asks about mobile UI components such as Button, Cell, Form, Dialog, Toast, Popup, ConfigProvider, theme customization, project setup, or wants to implement mobile-first interfaces with vant or van- components.

<!--

<!--

<!--

>

Academic paper writing skill with 12-agent pipeline. v2.5: Style Calibration (learn author's writing voice from past papers) + Writing Quality Check (writing quality checklist for natural prose). Supports IMRaD, literature review, theoretical, case study, policy brief, and conference paper structures. APA 7.0 (default), Chicago, MLA, IEEE, Vancouver citation formats. Bilingual abstracts (zh-TW + EN). Multi-format output (LaTeX, DOCX, PDF, Markdown). Triggers on: write paper, academic paper, paper outline, write abstract, revise paper, check citations, convert to LaTeX, guide my paper, parse reviews, revision roadmap, 寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 檢查引用, 引導我寫論文, 帶我規劃論文, 逐章規劃, 論文架構, 審查意見, 修訂路線圖.

Remove AI-generated writing patterns from text to make it sound natural and human-written. Supports both English and Chinese.

`paper-audit` is now **deep-review-first**. Its core job is to behave like a serious reviewer: find technical, methodological, claim-level, and cross-section issues; keep script-backed findings separa

Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.

Generate publication-quality illustrations using a **multi-stage workflow** with **Claude as the STRICT supervisor/reviewer**.

Structure and derive research formulas when the user wants to 推导公式, derive a theory line, build equations from a problem statement, clarify assumptions, separate formal derivation from remarks, or turn messy theory notes into a paper-ready derivation skeleton. Use for research-style formula development, not for fully rigorous theorem proving once the claim is already fixed.

Academic translation, post-editing, and Chinglish correction guide