Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
24,390
总 Skills
87.2M
总安装量
2,570
贡献者
# Skill 仓库 描述 安装量
21951 context-doctor jzocb/context-doctor
Context Doctor Diagnose and visualize how the context window budget is allocated. Quick Start Run the visualization script: python3 scripts/context-doctor.py The script auto-detects: Workspace path ( ~/.openclaw/workspace or OPENCLAW_WORKSPACE env) OpenClaw version (via openclaw --version ) Installed skills (system + workspace) Bootstrap file sizes and status Output Sections 1. Workspace Files Shows each bootstrap file with: Status : ✓ OK / ✗ MISSING / ⚠ TRUNCATED (symlink target missing = MISSI...
 41
21952 understanding-tauri-ipc dchuk/claude-code-tauri-skills
Tauri Inter-Process Communication (IPC) This skill covers Tauri's IPC system, including the brownfield and isolation patterns for secure communication between frontend and backend processes. Overview Tauri implements Inter-Process Communication using Asynchronous Message Passing . This enables isolated processes to exchange serialized requests and responses securely. Why Message Passing? Safer than shared memory or direct function access Recipients can reject or discard malicious requests Tauri ...
 41
21953 github-automation davepoon/buildwithclaude
GitHub Automation Skill Purpose GitHub workflow automation, PR management, and repository coordination. When to Trigger Creating pull requests Managing issues Setting up CI/CD workflows Code review automation Release management Commands Create Pull Request gh pr create --title "feat: description" --body " Summary \n ..." Review Code npx claude-flow github review --pr 123 Manage Issues npx claude-flow github issues list --state open npx claude-flow github issues create --title "Bug: ..." Setup Wo...
 41
21954 erpnext-syntax-controllers openaec-foundation/erpnext_anthropic_claude_development_skill_package
ERPNext Syntax: Document Controllers Document Controllers are Python classes that implement the server-side logic of a DocType. Quick Reference Controller Basic Structure import frappe from frappe . model . document import Document class SalesOrder ( Document ) : def validate ( self ) : """Main validation - runs on every save.""" if not self . items : frappe . throw ( _ ( "Items are required" ) ) self . total = sum ( item . amount for item in self . items ) def on_update ( self ) : """After save...
 41
21955 marketing-paid-ads gnoviawan/agentic-marketing
Paid Advertising Specialist You are a senior paid media strategist with deep expertise across Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, programmatic, and emerging ad platforms. You deliver actionable, modern campaign strategies grounded in the brand's SOSTAC plan. For modern and emerging practices across all platforms, consult ./references/best-practices.md . For platform and industry benchmarks, see ./references/benchmarks.md . For privacy-compliant tracking and attribution guidance, see ...
 41
21956 go-backend-reviewer jssfy/k-skills
你是一个专业的 Go 后端代码审查专家，专注于审查 Go 微服务项目的代码质量、性能和最佳实践。 先识别仓库实际技术栈，再决定启用哪些专项检查。通用 Go 规则始终适用；组织或框架特定规则仅在仓库中检测到对应模式时启用。 When to Use 当用户请求以下操作时触发： "review Go code" / "审查 Go 代码" / "Go code review" "检查这个 Go 项目" / "review this PR" (in a Go repo) 任何涉及 Go 后端代码审查的请求 核心职责 对 Go 后端代码进行全面审查，确保代码质量、可维护性、性能和安全性。 审查检查清单 1. 逻辑正确性（Critical） 断言转换检查 ：检查类型断言、类型转换是否安全，参数传递是否符合逻辑 边界条件 ：验证循环边界、数组索引、切片操作是否正确 错误处理 ：确保所有错误都被正确处理，不能忽略 error 返回值 nil 指针检查 ： 检查方法返回值是否可能包含未初始化的对象（如未初始化的 map、nil slice） 确保在使用指针前进行 nil 检查 并发安全 ：检查共享资源的并...
 41
21957 ucharts teachingai/full-stack-skills
Use this skill whenever the user wants to: - Install and set up uCharts in a project - Create charts in uni-app applications - Use uCharts in WeChat Mini Program - Use uCharts in H5 applications - Configure chart options - Use different chart types - Handle chart events - Customize chart appearance - Understand uCharts API and methods - Troubleshoot uCharts issues How to use this skill This skill is organized to match the uCharts official documentation structure ([https://www.uchart...
 41
21958 automation-scripts miles990/claude-software-skills
Automation & Scripts Overview Build automation, task runners, and scripting patterns for development workflows. npm Scripts Package.json Scripts { "scripts": { "dev": "next dev", "build": "next build", "start": "next start", "lint": "eslint . --ext .ts,.tsx", "lint:fix": "eslint . --ext .ts,.tsx --fix", "type-check": "tsc --noEmit", "test": "vitest", "test:watch": "vitest --watch", "test:coverage": "vitest --coverage", "test:e2e": "playwright test", ...
 41
21959 v3 swarm coordination ruvnet/claude-flow
V3 Swarm Coordination What This Skill Does Orchestrates the complete 15-agent hierarchical mesh swarm for claude-flow v3 implementation, coordinating parallel execution across domains while maintaining dependencies and timeline adherence. Quick Start Initialize 15-agent v3 swarm Task ( "Swarm initialization" , "Initialize hierarchical mesh for v3 implementation" , "v3-queen-coordinator" ) Security domain (Phase 1 - Critical priority) Task ( "Security architecture" , "Design v3 threat model and...
 41
21960 etl-sync-job-builder patricio0312rev/skills
ETL/Sync Job Builder Build reliable, incremental data synchronization pipelines. ETL Job Pattern // jobs/sync-users.ts interface SyncJob { name : string ; source : "database" | "api" | "file" ; destination : "database" | "warehouse" | "s3" ; schedule : string ; } export class ETLJob { constructor ( private name : string , private watermarkKey : string ) { } async run ( ) { console . log ( ` 🔄 Starting ${ this . name } ... ` ) ; try { // 1. Get last watermark const lastSync = await this . getWate...
 41
21961 friendliness-approachability dylantarre/animation-principles
Friendliness & Approachability Animation Create animations that welcome users and make interfaces feel warm and inviting. Emotional Goal Friendliness comes from gentle, welcoming motion that doesn't intimidate. Approachability means animations that invite interaction and make users feel comfortable. Disney Principles for Friendliness Squash & Stretch Moderate, soft deformation (10-20%). Enough to feel alive without being cartoonish. Like a friendly handshake—warm but appropriate. Anticipation Ge...
 41
21962 slidev-components yoanbernabeu/slidev-skills
This skill covers using Vue components in Slidev, including all built-in components and how to create custom interactive elements for your presentations. When to Use This Skill - Adding interactive elements to slides - Using built-in Slidev components - Creating custom Vue components - Building reusable presentation elements - Adding dynamic content Using Components Components can be used directly in Markdown: ``` My Slide <MyComponent /> <Counter :start="5" /> ``` Built-in Comp...
 41
21963 content-writer majesticlabs-dev/majestic-marketplace
Content Writer You write compelling marketing copy. Follow these principles: Voice Conversational but professional Active voice, present tense Short sentences, short paragraphs Structure Lead with the biggest benefit Use specific numbers over vague claims End with a clear call-to-action Rules No jargon unless the audience expects it No superlatives without proof ("best", "revolutionary") Every paragraph must earn its place
 41
21964 calendar-optimization majesticlabs-dev/majestic-marketplace
Calendar Optimization Balance your professional time across 4 essential categories. The 4 Types of Professional Time 1. Management Time (Red) What it includes: Meetings and calls Email processing Presentations Team and people management Administrative tasks The problem: Most professionals spend 70-90% here, leaving scraps for everything else. 2. Creation Time (Green) What it includes: Writing and content creation Coding and building Designing and prototyping Strategic document preparation Deep w...
 41
21965 nextjs-patterns ashchupliak/dream-team
Next.js 15 App Router Patterns File Structure app/ ├── layout.tsx Root layout (required) ├── page.tsx Home page (/) ├── loading.tsx Loading UI ├── error.tsx Error boundary ├── not-found.tsx 404 page ├── globals.css Global styles ├── environments/ │ ├── page.tsx /environments │ ├── [id]/ │ │ ├── page.tsx /environments/[id] │ │ └── loading.tsx Loading for this route │ └── new/ │...
 41
21966 kimi-pdf thvroyal/kimi-skills
Route Selection Route Trigger Route File HTML (default) All PDF creation requests routes/html.md LaTeX User explicitly requests LaTeX, .tex, or Tectonic routes/latex.md Process Work with existing PDFs (extract, merge, fill forms, etc.) routes/process.md Default to HTML. Only use LaTeX route when user explicitly requests it. MANDATORY: Read Route File Before Implementation Before implementation, you MUST: Determine the route (HTML / LaTeX / Process) Read the route file ( routes/html.md , routes/l...
 41
21967 podcast-splitter dkyazzentwatwa/chatgpt-skills
Automatically split audio files into segments based on silence detection. Perfect for dividing podcasts into chapters, creating clips from long recordings, or removing dead air. Quick Start ``` from scripts.podcast_splitter import PodcastSplitter Auto-split by silence splitter = PodcastSplitter("podcast_episode.mp3") segments = splitter.split_by_silence() splitter.export_segments("./chapters/") Remove long silences splitter = PodcastSplitter("raw_recording.mp3") splitter.remove_silence(mi...
 41
21968 gitea-tea beshkenadze/claude-skills-marketplace
Gitea CLI (tea) Overview Official command-line interface for Gitea. Manage issues, PRs, releases, and repos from terminal. Instructions Verify authentication : Run tea whoami to confirm login Check context : Run in git repo for auto-detection, or use --repo owner/repo Use non-interactive mode : Always use --output flag and provide all arguments Choose operation : See command reference sections below Installation macOS brew install tea Linux (binary) curl -sL https://dl.gitea.io/tea/main/tea-ma...
 41
21969 research-analyst erichowens/some_claude_skills
Research Analyst Purpose Provides systematic research capabilities for complex investigations requiring multi-source information gathering, critical analysis, and knowledge synthesis. Specializes in evidence evaluation, cross-domain analysis, and transforming disparate information into actionable insights. When to Use Conducting comprehensive market or technology research Synthesizing information from multiple sources into coherent reports Evaluating competing claims or technologies Building k...
 41
21970 pdd mikeyobrien/ralph-orchestrator
Prompt-Driven Development Overview This sop guides you through the process of transforming a rough idea into a detailed design document with an implementation plan and todo list. It follows the Prompt-Driven Development methodology to systematically refine your idea, conduct necessary research, create a comprehensive design, and develop an actionable implementation plan. The process is designed to be iterative, allowing movement between requirements clarification and research as needed. Parame...
 41
21971 uniapp-native-app teachingai/full-stack-skills
When to use this skill Use this skill whenever the user wants to: Package uni-app as native Android app Package uni-app as native iOS app Configure native app settings (manifest, permissions, etc.) Customize native app features Integrate native plugins Configure app signing and certificates Handle native app build and distribution How to use this skill To package native apps: Identify the platform from the user's request: Android → Use Android examples iOS → Use iOS examples Load the appro...
 41
21972 fix-code-vulnerability letta-ai/skills
Fix Code Vulnerability Overview This skill provides a systematic approach for identifying, analyzing, and fixing security vulnerabilities in codebases. It covers common vulnerability types (injection attacks, input validation issues, etc.) and provides verification strategies to ensure fixes are complete and correct. Workflow Phase 1: Initial Reconnaissance Start by understanding the scope and nature of the vulnerability: Run existing tests first - Execute the test suite to identify any fail...
 41
21973 agentdb learning plugins ruvnet/claude-flow
AgentDB Learning Plugins What This Skill Does Provides access to 9 reinforcement learning algorithms via AgentDB's plugin system. Create, train, and deploy learning plugins for autonomous agents that improve through experience. Includes offline RL (Decision Transformer), value-based learning (Q-Learning), policy gradients (Actor-Critic), and advanced techniques. Performance : Train models 10-100x faster with WASM-accelerated neural inference. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agenti...
 41
21974 pre-commit-manager rysweet/amplihack
No SKILL.md available for this skill. View on GitHub
 41
21975 devdocs-test-cases ab300819/skills
测试用例设计 基于需求文档设计测试用例，建立验收标准与测试用例的追溯关系。 语言规则 支持中英文提问 统一中文回复 使用中文生成文档 触发条件 用户已完成需求文档 用户要求设计测试用例 用户需要测试覆盖策略 前置条件 需求文档：docs/devdocs/01-requirements.md 如不存在，建议先运行 /devdocs-requirements 核心理念 测试用例来源 功能点 (F-XXX) │ └── 用户故事 (US-XXX) │ └── 验收标准 (AC-XXX) │ ├── 单元测试 (UT-XXX) ← 验证内部逻辑 │ ├── 集成测试 (IT-XXX) ← 验证组件协作 │ └── E2E 测试 (E2E-XXX) ← 验证用户场景 关键原则： 测试...
 41
21976 nestjs-best-practices ejirocodes/agent-skills
NestJS Best Practices Comprehensive best practices guide for NestJS applications. Contains 40 rules across 10 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new NestJS modules, controllers, or services Implementing authentication and authorization Reviewing code for architecture and security issues Refactoring existing NestJS codebases Optimizing performance or database queries Building microservice...
 41
21977 qcsd-refinement-swarm proffesor-for-testing/agentic-qe
QCSD Refinement Swarm v1.0 Shift-left quality engineering swarm for Sprint Refinement sessions. Overview The Refinement Swarm takes user stories that passed Ideation and prepares them for Sprint commitment. Where the Ideation Swarm asks "Should we build this?" using HTSM quality criteria, the Refinement Swarm asks "How should we test this?" using SFDIPOT product factors, BDD scenarios, and INVEST validation. Key Differentiators from Ideation Swarm Dimension Ideation Swarm Refinement Swarm Framew...
 41
21978 3d-graphics samhvw8/dot-claude
Three.js Development Build high-performance 3D web applications using Three.js - a cross-browser WebGL/WebGPU library. When to Use This Skill Use when working with: 3D scenes, models, animations, or visualizations WebGL/WebGPU rendering and graphics programming Interactive 3D experiences (games, configurators, data viz) Camera controls, lighting, materials, or shaders Loading 3D assets (GLTF, FBX, OBJ) or textures Post-processing effects (bloom, depth of field, SSAO) Physics simulations, VR/XR e...
 41
21979 azure-mgmt-fabric-dotnet sickn33/antigravity-awesome-skills
Azure.ResourceManager.Fabric (.NET) Management plane SDK for provisioning and managing Microsoft Fabric capacity resources via Azure Resource Manager. Management Plane Only This SDK manages Fabric capacities (compute resources). For working with Fabric workspaces, lakehouses, warehouses, and data items, use the Microsoft Fabric REST API or data plane SDKs. Installation dotnet add package Azure.ResourceManager.Fabric dotnet add package Azure.Identity Current Version : 1.0.0 (GA - September 2025) ...
 41
21980 distributed-task-execution qodex-ai/ai-agent-skills
Dispatching Parallel Agents Overview When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel. Core principle: Dispatch one agent per independent problem domain. Let them work concurrently. When to Use digraph when_to_use { "Multiple failures?" [ shape = diamond ] ; "Are they independent?" [ shape = diamond ] ; "Single agent investigates all" [ ...
 41
21981 ssh penetration testing zebbern/claude-code-guide
SSH Penetration Testing Purpose Conduct comprehensive SSH security assessments including enumeration, credential attacks, vulnerability exploitation, tunneling techniques, and post-exploitation activities. This skill covers the complete methodology for testing SSH service security. Prerequisites Required Tools Nmap with SSH scripts Hydra or Medusa for brute-forcing ssh-audit for configuration analysis Metasploit Framework Python with Paramiko library Required Knowledge SSH protocol fundamentals ...
 41
21982 octocode-prompt-optimizer bgauryy/octocode-mcp
Prompt Optimizer Skill <when_to_use> Creating or improving prompts Agents skip steps or ignore instructions Instructions lack enforcement Output format is inconsistent Reviewing any instruction document or prompt Strengthening agent-operational text without changing business/domain logic </when_to_use> <global_forbidden priority="maximum"> CRITICAL - FORBIDDEN at ALL times: Changing good parts that already work Changing the existing logic/intent of prompts Making changes before understanding the...
 41
21983 cqrs-event-sourcing nickcrew/claude-ctx-plugin
CQRS and Event Sourcing Patterns Expert guidance for implementing Command Query Responsibility Segregation (CQRS) and Event Sourcing patterns to build scalable, auditable systems with complete historical tracking and optimized read/write models. When to Use This Skill Building systems requiring complete audit trails and compliance Implementing temporal queries ("show me the state at time T") Designing high-scale applications with complex domain logic Creating systems with significantly differe...
 41
21984 pachca-chats pachca/openapi
pachca-chats Quick start Ask user for Pachca token (bot: Automations → Integrations → API, or user: Automations → API). Run commands with npx @pachca/cli and --token flag: npx @pachca/cli <command> --token $PACHCA_TOKEN Or set PACHCA_TOKEN for multiple commands: export PACHCA_TOKEN=<token> npx @pachca/cli <command> Help: npx @pachca/cli --help | Scenarios: npx @pachca/cli guide After successful use, suggest installing CLI globally: npm install -g @pachca/cli && pachca auth login --token $PACHCA_...
 41
21985 dlt-skill untitled-data-company/data-skills
Choose pipeline type with the decision tree below; then follow the Core Workflow. Quick start: 1) Use the decision tree. 2) Follow the Core Workflow. 3) Use patterns and references as needed. Pipeline Type Decision Tree When a user requests a dlt pipeline, determine which type to create: ``` START: User wants to create a dlt pipeline │ ├─→ Is there a dlt verified source available for this platform? │ (Check: https://dlthub.com/docs/dlt-ecosystem/verified-sources) │ │ │ YES → Use VERIF...
 41
21986 image-generation sanky369/vibe-building-skills
Image Generation Skill Overview I help you create effective prompts for AI image generation tools like DALL-E, Midjourney, and Stable Diffusion. I understand the nuances of different platforms and can help you achieve specific visual styles. What I can do: Write detailed image generation prompts Optimize prompts for specific AI tools Suggest style keywords and modifiers Create negative prompts to avoid unwanted elements Adapt prompts for different aspect ratios Generate variations and alternativ...
 41
21987 rest-api-design erichowens/some_claude_skills
REST API Design Overview Design REST APIs that are intuitive, consistent, and follow industry best practices for resource-oriented architecture. When to Use Designing new RESTful APIs Creating endpoint structures Defining request/response formats Implementing API versioning Documenting API specifications Refactoring existing APIs Instructions 1. Resource Naming ✅ Good Resource Names (Nouns, Plural) GET /api/users GET /api/users/123 GET /api/users/123/orders POST /api/products DELETE...
 41
21988 effect-ts blogic-cz/blogic-marketplace
Effect-TS Expert Expert guidance for functional programming with the Effect library, covering error handling, dependency injection, composability, and testing patterns. Prerequisites Check Before starting any Effect-related work, verify the Effect-TS source code exists at ~/.effect . If missing, stop immediately and inform the user. Clone it before proceeding: git clone https://github.com/Effect-TS/effect.git ~/.effect Research Strategy Effect-TS has many ways to accomplish the same task. Proact...
 41
21989 adhd-task-management-skill breverdbidder/life-os
ADHD Task Management Skill Tracks tasks, detects abandonment patterns, and provides ADHD-specific interventions. When to Use This Skill Starting any task with Ariel Tracking task progress through completion Detecting context switches and abandonments Providing accountability interventions Logging task outcomes to Life OS Task State Flow INITIATED → SOLUTION_PROVIDED → IN_PROGRESS → ├─→ COMPLETED ✓ ├─→ ABANDONED ⚠️ ├─→ BLOCKED 🚫 └─→ DEFERRED 📅 Mental Task Tracking For EVERY task request, silently...
 41
21990 azure-monitor-query-java sickn33/antigravity-awesome-skills
Azure Monitor Query SDK for Java DEPRECATION NOTICE : This package is deprecated in favor of: azure-monitor-query-logs — For Log Analytics queries azure-monitor-query-metrics — For metrics queries See migration guides: Logs Migration | Metrics Migration Client library for querying Azure Monitor Logs and Metrics. Installation < dependency > < groupId > com.azure </ groupId > < artifactId > azure-monitor-query </ artifactId > < version > 1.5.9 </ version > </ dependency > Or use Azure SDK BOM: < d...
 41
21991 comfort-safety dylantarre/animation-principles
Comfort & Safety Animation Create animations that reassure, protect, and make users feel secure. Emotional Goal Comfort comes from predictable, gentle motion that never startles. Safety means animations that communicate protection, stability, and user control. Disney Principles for Comfort Squash & Stretch Minimal, soft (5-10%). Gentle give without instability. Like a cushion—absorbs impact, maintains structure. Anticipation Clear, reassuring preparation (150-200ms). Users always know wha...
 41
21992 using-git-worktrees zenobi-us/dotfiles
Using Git Worktrees Overview Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching. Core principle: Systematic directory selection + safety verification = reliable isolation. Announce at start: "I'm using the using-git-worktrees skill to set up an isolated workspace." Directory Selection Process Follow this priority order: 1. Check Existing Directories Check in priority order ls -d .worktrees 2 > /dev/null Pref...
 41
21993 address-parser dkyazzentwatwa/chatgpt-skills
Address Parser Parse unstructured addresses into structured fields. Features Component Extraction : Street, city, state, zip, country Format Standardization : Normalize address formats Validation : Verify address components Batch Processing : Parse multiple addresses International Support : Multiple country formats Geocoding Ready : Output for geocoding APIs CLI Usage python address_parser.py --input addresses.csv --column address --output parsed.csv Dependencies pandas>=2.0.0
 41
21994 pai danielmiessler/personal_ai_infrastructure
Intro to PAI The PAI system is designed to magnify human capabilities. It is a general problem-solving system that uses the PAI Algorithm. RESPONSE DEPTH SELECTION (Read First) Nothing escapes the Algorithm. The only variable is depth. The FormatReminder hook uses AI inference to classify depth. Its classification is authoritative — do not override it. Depth When Format FULL Any non-trivial work: problem-solving, implementation, design, analysis, thinking 7 phases with ISC Tasks ITERATION Contin...
 41
21995 jupyter-notebook-best-practices oimiragieo/agent-studio
Jupyter Notebook Best Practices Skill Structure notebooks with clear sections using markdown cells. Use meaningful cell execution order to ensure reproducibility. Include explanatory text in markdown cells to document analysis steps. Keep code cells focused and modular for easier understanding and debugging. Use magic commands like %matplotlib inline for inline plotting. Document data sources, assumptions, and methodologies clearly. Use version control (e.g., git) for tracking changes in noteboo...
 41
21996 azure-mgmt-applicationinsights-dotnet sickn33/antigravity-awesome-skills
Azure.ResourceManager.ApplicationInsights (.NET) Azure Resource Manager SDK for managing Application Insights resources for application performance monitoring. Installation dotnet add package Azure.ResourceManager.ApplicationInsights dotnet add package Azure.Identity Current Version : v1.0.0 (GA) API Version : 2022-06-15 Environment Variables AZURE_SUBSCRIPTION_ID = < your-subscription-id > AZURE_RESOURCE_GROUP = < your-resource-group > AZURE_APPINSIGHTS_NAME = < your-appinsights-component > Aut...
 41
21997 semgrep-rule-creator oimiragieo/agent-studio
Semgrep Rule Creator Create production-quality Semgrep rules with proper testing and validation. When to Use Ideal scenarios: Creating custom detection rules for specific bug patterns Building security vulnerability detectors for your codebase Writing taint-mode rules for data flow vulnerabilities Developing rules to enforce coding standards When NOT to Use Do NOT use this skill for: Running existing Semgrep rulesets General static analysis without custom rules (use static-analysis plugin)...
 41
21998 topic-generator zephyrwang6/myskill
根据内容特点选择： - 干货教程 - 有具体步骤可复现 - 产品体验 - 新产品/新功能测评 - 观点分享 - 趋势分析/行业洞察 - 新技术突破 - 重大更新/技术解读 输出格式 每个选题输出： ``` 选题 N：[标题] 事件描述 一句话说清楚发生了什么 核心角度 为什么值得写？独特切入点是什么？ 推荐标题（3个备选） 1. 标题A 2. 标题B 3. 标题C 写作方式：干货教程 / 产品体验 / 观点分享 / 新技术突破 预估热度：⭐⭐⭐⭐⭐（1-5星） 不写的风险：错过什么？（可选） ``` 选题公式参考 工具测评型 - 用了X天[工具]，我发现[意外收获] - [工具]的隐藏功能，90%的人不知道 方法论型 - 我用[方法]搞定了[问题]的完整流程 - [数字]个让[场景]效率翻倍的技巧 热点结合型 - [热点]爆火，但大家忽略了这一点 - 从[热点]看AI编程的未来 反共识型 - 别再[常见做法]了 - 为什么我不推荐[热门事物] 经验复盘型 - 做了[数字]个[事情]后，我总结的[数字]条教训 -...
 41
21999 update-provider-models vercel/ai
Update Provider Model IDs This skill covers adding new model IDs and removing obsolete ones across the AI SDK codebase. Each workflow uses search to discover all locations that need changes. You may be asked to add or remove a single model ID, or to process a list of multiple model ID changes from an issue. For each model ID, follow the appropriate workflow: If a new model ID is being added, follow the <adding-new-model> workflow. If an obsolete model ID is being removed, follow the <removing-ob...
 41
22000 ai-video-generation inference-sh/agent-skills
AI Video Generation Generate videos with 40+ AI models via inference.sh CLI. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login Generate a video with Veo belt app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}' Available Models Text-to-Video Model App ID Best For Veo 3.1 Fast google/veo-3-1-fast Fast, with optional audio Veo 3.1 google/veo-3-1 Best quality, frame interpolation Veo 3 google/veo-3 High quality with audio Veo 3 Fast goog...
 41