ai-news-digest
Multi-source AI news aggregation and digest generation with deduplication, classification, and source tracing. Supports 20+ sources, 5 theme categories, multi-language output (ZH/EN/JA), and image export.
sql-standards
SQL output standards and Hive dialect compatibility rules for data warehouse queries. This skill should be used when generating SQL for Hive/SparkSQL/GaussDB, or when reviewing SQL for compatibility issues.
tech-article-creator
|
x-tracker
>-
x-ai-digest
Scrape AI-related posts from X platform's "For You" feed, generate daily digest with reply suggestions. Features real-time scraping, AI topic filtering, share card generation, multi-language output (ZH/EN/JA).
my-skill
Describe what this skill does in one sentence, and in what context/task type it should be used. Include key features and supported languages if applicable.
mistral-pdf-to-markdown
Convert PDFs to Markdown using Mistral OCR API with image extraction. Use when you need to extract structured text and images from PDFs, especially for scanned documents or documents with complex formatting. Outputs Markdown with embedded images.
work-summary
Create factual working journal entries in Notes/WorkingJournal/ after completing analysis work. Use when user asks to "summarize work", "document results", or "create working journal entry". Ensures code is committed, copies figures to attachments, and creates objective summaries with citations.
zotero-paper-reader
Read and analyze academic papers from Zotero library. Use when the user requests to read, access, or analyze a paper by title, author, or topic from their Zotero library. Automatically searches Zotero, converts PDFs to markdown, saves to Notes/PaperInMarkdown, and provides analysis.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
ask-dont-assume
Uses an ask-first workflow when requirements, scope, permissions, or tradeoffs are unclear. Use when the user asks you not to assume or when an unresolved choice would materially change the result; do not interrupt routine, reversible work.
browser-devtools
Inspect and debug Chrome web apps with the native agent-browser CLI and Chrome DevTools. Use for network requests, console errors, source debugging, storage, performance/CPU/memory analysis, React component trees and render profiling, and browser-driven reproduction. Start with a compact overview, then inspect relevant details using installed APIs.
caching
Diagnoses stale data and defines HTTP/CDN caching, freshness, and invalidation policies. Use for cache headers, ETags, hashed assets, or cache-layer investigations. Service-worker lifecycle and TanStack APIs are separate workflows.
code-quality
Reviews and simplifies code for maintainability and correctness. Use for a requested code review, refactor, removal of unnecessary abstractions or dependencies, or investigation of tangled logic. Not a default checklist for every small edit.
css
Implements or debugs CSS layout, responsive sizing, cascade, selectors, and styling performance. Use for concrete stylesheet work; visual-system design and UX reviews belong to web-design-guidelines.
database-guardrails
Plans database-backed changes with an ask-first safety gate, minimal schema growth, programmatic versioned migrations, and evidence-based indexes. Use for database modeling, schema changes, migrations, data repair, or database performance work; do not access or change a database by default.
git
Manages Git commits, branches, conflict resolution, and recovery. Use when the task requires Git operations or history analysis; follow the repository workflow.
html
Implements semantic HTML, forms, document structure, and head metadata. Use for markup and native accessibility behavior, rather than general visual design or CSS layout.
javascript
Implements or debugs JavaScript/TypeScript language behavior, async work, data transformations, and runtime memory. Use for JS/TS logic issues; React rendering and UI design have separate workflows.
low-level-web-rendering
Chooses between DOM, SVG, Canvas, WebGL, WebGPU, and worker rendering, or evaluates experimental HTML-in-Canvas. Use for renderer selection or architecture tradeoffs, not routine work in an already-selected GPU library.
react-best-practices
Builds and reviews React components, hooks, state, data loading, and rendering performance. Use for React correctness, effect cleanup, slow renders, or unresponsive component interactions. TanStack-specific API work and React Three Fiber scenes have separate workflows.
react-three-fiber
Builds and optimizes scenes using @react-three/fiber and drei. Use for R3F frame loops, React scene ownership, assets, and instancing; do not select solely because a task mentions 3D or Three.js.
security
Reviews and implements web security boundaries, authorization, output encoding, session protection, and secret handling. Use for security-sensitive changes or a requested security review.
service-worker
Implements service-worker lifecycle, offline routing, cache ownership, update flows, and PWA behavior. Use for a worker or offline/PWA task; HTTP/CDN header policy alone belongs to caching.
tanstack
Uses TanStack Query, Router, Table, Form, Virtual, or Start in an existing or explicitly selected TanStack project. Use for its query keys, mutations, loaders, URL state, and library APIs; do not introduce the stack for generic React work.
vgpu
Builds shader effects, materials, particles, and 3D visual surfaces with Vercel vgpu. Use when vgpu is requested or installed, including integration and GPU debugging. Read version-matched docs; do not migrate other renderers implicitly.
wasm-rust
Implements Rust/WebAssembly modules and wasm-bindgen integration. Use for measured CPU kernels, wasm packaging, and JS-WASM transfers; not GPU shader execution or DOM styling.
web-design-guidelines
Designs or reviews web interfaces for visual hierarchy, coherent tokens and themes, interaction states, responsiveness, and accessibility. Use for a UI redesign, design-system decisions, or a screen/flow review. Pure CSS debugging and HTML markup implementation are separate tasks.
web-performance
Diagnoses browser loading, Core Web Vitals, main-thread work, and layout/paint bottlenecks. Use for a slow page or measured browser-performance issue; isolated React renders and GPU passes have specialist workflows.
webgl
Implements or debugs raw WebGL/WebGL2 contexts, GLSL, buffers, textures, and GL draw calls. Use for direct WebGL API work, not generic 3D tasks owned by a higher-level renderer.
webgpu
Implements or debugs raw browser WebGPU/WGSL pipelines, compute, buffers, textures, and device loss. Use for direct GPU API work; vgpu-library APIs and R3F scenes have separate workflows.
webview2-winui
Embeds web content in WinUI 3 through WebView2. Use for virtual host mapping, native/web messages, lifecycle, and desktop packaging; not generic browser React development.
business-rule-patterns
Write ServiceNow business rules (before/after/async/display) — current vs previous, changesTo/changesFrom, recursion avoidance, setAbortAction, and async dispatch for heavy work.
gliderecord-patterns
Write efficient ServiceNow GlideRecord queries — addQuery vs addEncodedQuery, setLimit, GlideAggregate for counts, avoiding N+1 in loops, query operators, and safe CRUD with workflow control.
rest-integration
Make outbound REST calls from ServiceNow with sn_ws.RESTMessageV2 — basic/bearer/OAuth/API-key auth, error handling by status code, response parsing, sys_rest_message records, and retry with exponential backoff.
update-set-workflow
Manage ServiceNow update sets — create named sets before any development, ensure auto_switch tracks API changes under the OAuth service account, complete on done, and export for promotion. Mandatory for all change-producing work.
widget-coherence
Build Service Portal widgets (sp_widget) with synchronized server/client/HTML — data.* initialization, ng-click + controller method matching, c.server.get action handlers, and Angular directive usage.
background-script-execution
What actually happens when you call snow_execute_script — the Scripted REST endpoint Serac auto-deploys on first use, the scheduled-job fallback, what scheduled_job_pending means, and how to get output back when the call comes home empty.
change-rollback
Undo a change already written to a ServiceNow instance — recover the prior payload from sys_update_version, write it back without corrupting it, and know which damage update set back-out, Deleted Records, or nothing at all can reverse.
inbound-email
Handle email arriving at a ServiceNow instance — inbound email action ordering and stop-processing, the real sysevent_in_email_action column names, and reading sys_email when a message created no record.
table-api-reads
What a Table API read through this MCP actually returns — the 200-character truncation in snow_query_table, the three different display_value defaults, reference fields as {link, value} objects, why work_notes come back empty, and which reported totals are real counts and which are guesses.
run-claude
向助手发出协助请求，适用于需要在隔离的独立环境中执行复杂编程任务、任务规划、文稿撰写的场景。
run-codex
向助手发出协助请求，适用于代码审核、逻辑推理、科学与哲学思考、深度分析、策略制定、市场分析等任务场景。
run-gemini
向助手发出协助请求，适用于长文阅读理解、网络搜索、网页读取、文章翻译、网页与前端界面制作等任务场景。
run-iflow
向助手发出协助请求，适用中华文化理解、中文古文理解、中国特色作品创作、小红书与抖音的宣发文案编写、编写测试用例、信息检索等任务场景，同时也是其他专家助手的强力替补与协助，可以作为大部分认为的备选候补方案。
chinese-output
在输出包含中文字符与中文标点符号、编写中文文档、根据中文文档生成中文的交互回应、回复用户用中文提出的问题或任务、需要进行中文与非中文混排操作等涉及中文文字与标点符号的使用的场景中，必须使用本 Skill 以获得专业的中文字符的操作指导与行为规范引导。
commit
当需要对 git repo 生成提交（commit）信息时，务必使用本Skill
reminder
当用户提到需要记住的未来任务、约会或事件时创建提醒和日历事件。在诸如"提醒我"、"设置提醒"、"我有个会"、"别忘了"或任何提及未来基于时间的任务时触发。
running-skills-edd-cycle
Guides evaluation-driven development (EDD) process for agent skills. Use when setting up skill testing workflows, creating skill evaluation scenarios, or establishing Claude A/B feedback loops for skill validation. Provides development methodology, not content guidance.
creating-effective-skills
Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency.
Page 585 of 1646 · 82256 results