Agent Skills 排行榜 · 关键词 + 语义搜索

/ 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
4451 zig-best-practices 0xbigboss/claude-code
Zig Best Practices Type-First Development Types define the contract before implementation. Follow this workflow: Define data structures - structs, unions, and error sets first Define function signatures - parameters, return types, and error unions Implement to satisfy types - let the compiler guide completeness Validate at comptime - catch invalid configurations during compilation Make Illegal States Unrepresentable Use Zig's type system to prevent invalid states at compile time. Tagged unio...
193
4452 grepai-mcp-cursor yoanbernabeu/grepai-skills
This skill covers integrating GrepAI with Cursor IDE using the Model Context Protocol (MCP). When to Use This Skill - Setting up GrepAI in Cursor - Enabling semantic search for Cursor AI - Configuring MCP for Cursor - Troubleshooting Cursor integration What is Cursor? Cursor is an AI-powered IDE that supports MCP for external tools. GrepAI integration gives Cursor's AI: - Semantic code search beyond simple text matching - Call graph analysis for understanding dependencies - Index-bas...
193
4453 skill-creator getsentry/skills
Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: Decide what you want the skill to do and roughly how it should do it Write a draft of the skill Create a few test prompts and run claude-with-access-to-the-skill on them Help the user evaluate the results both qualitatively and quantitatively While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you...
193
4454 market-data eng0ai/eng0-template-skills
Access US stock market data through eng0's data proxy service. Base URL ``` https://api.eng0.ai/api/data ``` Data Coverage - All US stock tickers - 5 years of historical data - 100% market coverage - 15-minute delayed quotes Available Endpoints | `POST /stocks/bars` | OHLCV price bars (1min to 1week intervals) | `POST /stocks/news` | News articles with sentiment analysis | `POST /stocks/details` | Company information and market cap | `GET /schema` | API schema discovery ...
193
4455 fetch-tweet ai-native-camp/camp-2
Fetch Tweet X/Twitter URL에서 트윗 원문, 작성자 정보, 인게이지먼트 데이터를 가져오는 스킬. FxEmbed 오픈소스 프로젝트의 API ( api.fxtwitter.com )를 활용하여 JavaScript 없이 트윗 데이터를 추출한다. How It Works X/Twitter URL의 도메인을 api.fxtwitter.com 으로 변환하면 JSON으로 트윗 전체 데이터를 반환한다. https://x.com/user/status/123456 → https://api.fxtwitter.com/user/status/123456 Script scripts/fetch_tweet.py - 표준 라이브러리만 사용, 외부 의존성 없음. 기본 사용 (포맷팅된 출력) python scripts/fetch_tweet.py https://x.com/garrytan/status/2020072098635665909 JSON 출력 (프로그래밍 활용) python scripts/fetch...
192
4456 kotlin-multiplatform vitorpamplona/amethyst
Kotlin Multiplatform: Platform Abstraction Decisions Expert guidance for KMP architecture in Amethyst - deciding what to share vs keep platform-specific. When to Use This Skill Making platform abstraction decisions: "Should I create expect/actual or keep Android-only?" "Can I share this ViewModel logic?" "Where does this crypto/JSON/network implementation belong?" "This uses Android Context - can it be abstracted?" "Is this code in the wrong module?" Preparing for iOS/web/wasm targets Detect...
192
4457 design-motion-principles kylezantos/design-engineer-auditor-package
Design Motion Audit Skill You are a senior design engineer specializing in motion and interaction design. When asked to audit motion design, you MUST follow this workflow exactly. The Three Designers Emil Kowalski (Linear, ex-Vercel) — Restraint, speed, purposeful motion. Best for productivity tools. Jakub Krehel (jakub.kr) — Subtle production polish, professional refinement. Best for shipped consumer apps. Jhey Tompkins (@jh3yy) — Playful experimentation, CSS innovation. Best for creative sit...
192
4458 hooks parcadei/continuous-claude-v3
Hook Development Rules When working with files in .claude/hooks/: Pattern Shell wrapper (.sh) → TypeScript (.ts) via npx tsx Shell Wrapper Template !/bin/bash set -e cd "$CLAUDE_PROJECT_DIR/.claude/hooks" cat | npx tsx <handler>.ts TypeScript Handler Pattern interface HookInput { // Event-specific fields } async function main() { const input: HookInput = JSON.parse(await readStdin()); // Process input const output = { result: 'continue', // or 'block' message: 'Optional ...
192
4459 web-testing mrgoonie/claudekit-skills
Web Testing Skill Comprehensive web testing: unit, integration, E2E, load, security, visual regression, accessibility. Quick Start npx vitest run Unit tests npx playwright test E2E tests npx playwright test --ui E2E with UI k6 run load-test.js Load tests npx @axe-core/cli https://example.com Accessibility npx lighthouse https://example.com Performance Testing Pyramid (70-20-10) Layer Ratio Framework Speed Unit 70% Vitest/Jest ...
192
4460 tvos-design-guidelines ehmo/platform-design-skills
tvOS Design Guidelines Apple TV is a living room device driven entirely by focus-based navigation and the Siri Remote. There is no pointer, no touch screen, and no mouse. Every design decision must account for the 10-foot viewing distance, the simplicity of the remote, and the lean-back nature of TV consumption. 1. Focus-Based Navigation (CRITICAL) The focus system is the foundation of all tvOS interaction. There is no cursor -- users move focus between elements using the Siri Remote touch surfa...
192
4461 accessibility-review anthropics/knowledge-work-plugins
/accessibility-review If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md . Audit a design or page for WCAG 2.1 AA accessibility compliance. Usage /accessibility-review $ARGUMENTS Audit for accessibility: @$1 WCAG 2.1 AA Quick Reference Perceivable 1.1.1 Non-text content has alt text 1.3.1 Info and structure conveyed semantically 1.4.3 Contrast ratio >= 4.5:1 (normal text), >= 3:1 (large text) 1.4.11 Non-text contrast >= 3:1 (UI components, graphics) ...
192
4462 product-strategist alirezarezvani/claude-skills
Product Strategist Strategic toolkit for Head of Product to drive vision, alignment, and organizational excellence. Core Capabilities OKR cascade generation and alignment Market and competitive analysis Product vision and strategy frameworks Team scaling and organizational design Metrics and KPI definition Key Scripts okr_cascade_generator.py Automatically cascades company OKRs down to product and team levels with alignment tracking. Usage: python scripts/okr_cascade_generator.py [strategy] ...
192
4463 asc-id-resolver rudrankriyam/asc-skills
asc id resolver Use this skill to map names to IDs needed by other commands. App ID By bundle ID or name: asc apps list --bundle-id "com.example.app" asc apps list --name "My App" Fetch everything: asc apps --paginate Set default: ASC_APP_ID=... Build ID Latest build: asc builds latest --app "APP_ID" --version "1.2.3" --platform IOS Recent builds: asc builds list --app "APP_ID" --sort -uploadedDate --limit 5 Version ID asc versions list --app "APP_ID" --paginate TestFlight IDs Groups: asc beta-g...
192
4464 turborepo-monorepo giuseppe-trisciuoglio/developer-kit
Turborepo Monorepo Overview Provides comprehensive guidance for working with Turborepo monorepos in TypeScript/JavaScript projects. Turborepo is a high-performance build system written in Rust that optimizes task execution through intelligent caching, parallelization, and dependency graph analysis. This skill covers workspace creation, task configuration, framework integration (Next.js, NestJS, Vite), testing setup, CI/CD pipelines, and performance optimization. When to Use Use this skill when: ...
192
4465 shell pproenca/dot-skills
Shell Scripts Best Practices Comprehensive best practices guide for shell scripting, designed for AI agents and LLMs. Contains 48 rules across 9 categories, prioritized by impact from critical (safety, portability) to incremental (style). Each rule includes detailed explanations, real-world examples comparing incorrect vs. correct implementations, and specific impact metrics. When to Apply Reference these guidelines when: Writing new bash or POSIX shell scripts Reviewing shell scripts for se...
192
4466 compound ai-native-camp/camp-2
compound 스킬 목적: 작업 과정에서 검증된 인사이트를 즉시 문서화하여, 검색 가능한 지식 베이스를 구축한다. 개요 이 스킬은 인사이트가 확인되는 즉시 포착하여, YAML frontmatter 기반의 구조화된 문서로 저장한다. 카테고리별 단일 파일 아키텍처를 사용하며, 각 인사이트는 knowledge/[category]/[filename].md 에 저장된다. <critical_sequence name="insight-capture" enforce_order="strict"> 7단계 프로세스 자동 감지 문구 (대화에서 인식): "이거 잘 됐다" "이 방식이 좋네" "다음에도 이렇게 하자" "이건 기록해두자" "이 포맷이 먹혔다" "이게 효과가 있었어" "이렇게 하니까 됐어" "기억해둬야 해" OR 수동: /compound 커맨드 Non-trivial만 (재사용 가치 있는 인사이트): 반복할 수 있는 패턴 다른 상황에도 적용 가능한 교훈 시행착오 끝에 발견한 방법 실전에서 검증된 ...
192
4467 nextjs15-performance srbhr/resume-matcher
Before writing Next.js code: Read docs/agent/architecture/nextjs-critical-fixes.md for full patterns Check existing components in apps/frontend/components/ for examples Critical Rules (always apply): Waterfalls Use Promise.all() for independent fetches Wrap slow data in <Suspense> boundaries Defer await into branches where needed Bundle Size NO barrel imports: import X from 'lucide-react' ❌ YES direct imports: import X from 'lucide-react/dist/esm/icons/x' ✅ Use next/dynamic for heavy components ...
192
4468 sports-news machina-sports/sports-skills
Sports News Quick Start Prefer the CLI — it avoids Python import path issues: sports-skills news fetch_items --google_news --query = "Arsenal transfer" --limit = 5 sports-skills news fetch_feed --url = "https://feeds.bbci.co.uk/sport/football/rss.xml" Python SDK (alternative): from sports_skills import news articles = news . fetch_items ( google_news = True , query = "Arsenal transfer news" , limit = 10 ) feed = news . fetch_feed ( url = "https://feeds.bbci.co.uk/sport/football/rss.xml" ) Import...
192
4469 git-workflow bobmatnyc/claude-mpm-skills
Git Workflow When to use this skill Creating meaningful commit messages Managing branches Merging code Resolving conflicts Collaborating with team Git best practices Instructions Step 1: Branch management Create feature branch : Create and switch to new branch git checkout -b feature/feature-name Or create from specific commit git checkout -b feature/feature-name < commit-hash > Naming conventions : feature/description : New features bugfix/description : Bug fixes hotfix/description : Urgent f...
192
4470 ast-grep-find parcadei/continuous-claude-v3
AST-Grep Find Structural code search that understands syntax. Find patterns like function calls, imports, class definitions - not just text. When to Use Find code patterns (ignores strings/comments) Search for function calls, class definitions, imports Refactor code with AST precision Rename variables/functions across codebase Usage Search for a pattern uv run python -m runtime.harness scripts/ast_grep_find.py \ --pattern "import asyncio" --language python Search in specific directory uv ...
192
4471 best-practices davila7/claude-code-templates
Best practices Modern web development standards based on Lighthouse best practices audits. Covers security, browser compatibility, and code quality patterns. Security HTTPS everywhere Enforce HTTPS: <!-- ❌ Mixed content --> <img src="http://example.com/image.jpg"> <script src="http://cdn.example.com/script.js"></script> <!-- ✅ HTTPS only --> <img src="https://example.com/image.jpg"> <script src="https://cdn.example.com/script.js"></script> <!-- ✅ Protocol-relative (will use page's protocol...
192
4472 obviously-awesome wondelai/skills
Product Positioning Framework This skill implements the product positioning methodology from April Dunford's "Obviously Awesome." It provides a structured, repeatable process for defining how your product is the best in the world at delivering something a well-defined set of customers cares a lot about. Positioning is the foundational strategic exercise that determines how customers perceive your product, what they compare it to, and ultimately whether they buy it. Core Principle Positioning is ...
192
4473 competitive-ads-extractor davila7/claude-code-templates
Competitive Ads Extractor This skill extracts your competitors' ads from ad libraries and analyzes what's working—the problems they're highlighting, use cases they're targeting, and copy/creative that's resonating. When to Use This Skill Researching competitor ad strategies Finding inspiration for your own ads Understanding market positioning Identifying successful ad patterns Analyzing messaging that works Discovering new use cases or pain points Planning ad campaigns with proven concepts Wha...
192
4474 transformers davila7/claude-code-templates
Transformers Overview The Hugging Face Transformers library provides access to thousands of pre-trained models for tasks across NLP, computer vision, audio, and multimodal domains. Use this skill to load models, perform inference, and fine-tune on custom data. Installation Install transformers and core dependencies: uv pip install torch transformers datasets evaluate accelerate For vision tasks, add: uv pip install timm pillow For audio tasks, add: uv pip install librosa soundfile Aut...
192
4475 sentry-browser-sdk getsentry/sentry-for-ai
All Skills > SDK Setup > Browser SDK Sentry Browser SDK Opinionated wizard that scans your project and guides you through complete Sentry setup for browser JavaScript — vanilla JS, jQuery, static sites, WordPress, and any JS project without a framework-specific SDK. Invoke This Skill When User asks to "add Sentry to a website" or set up Sentry for plain JavaScript User wants to install @sentry/browser or configure the Loader Script User has a WordPress, Shopify, Squarespace, or static HTML site ...
192
4476 documentation-templates davila7/claude-code-templates
Documentation Templates Templates and structure guidelines for common documentation types. 1. README Structure Essential Sections (Priority Order) Section Purpose Title + One-liner What is this? Quick Start Running in <5 min Features What can I do? Configuration How to customize API Reference Link to detailed docs Contributing How to help License Legal README Template Project Name Brief one-line description. Quick Start [Minimum steps to run] Features - Feature 1 - Feature 2 Configur...
192
4477 debug parcadei/continuous-claude-v3
Debug Package Usage Guide Basic Usage import debug from 'debug' ; // Format: lobe-[module]:[submodule] const log = debug ( 'lobe-server:market' ) ; log ( 'Simple message' ) ; log ( 'With variable: %O' , object ) ; log ( 'Formatted number: %d' , number ) ; Namespace Conventions Desktop: lobe-desktop:[module] Server: lobe-server:[module] Client: lobe-client:[module] Router: lobe-[type]-router:[module] Format Specifiers %O - Object expanded (recommended for complex objects) %o - Object %s - String ...
192
4478 mobile-responsiveness hoodini/ai-agents-skills
Mobile Responsiveness Build responsive, mobile-first web applications. Mobile-First Breakpoints /* Mobile first - no media query needed for mobile base */ .container { padding: 1rem; } /* Tablet */ @media (min-width: 768px) { .container { padding: 2rem; } } /* Desktop */ @media (min-width: 1024px) { .container { padding: 3rem; max-width: 1200px; margin: 0 auto; } } /* Large desktop */ @media (min-width: 1280px) { .container { max-width: 1400px; } } Tailwin...
191
4479 nextjs-16-complete-guide fernandofuc/nextjs-claude-setup
Next.js 16 Complete Guide Purpose Comprehensive reference for Next.js 16's revolutionary features: Cache Components with "use cache", stable Turbopack as default bundler, proxy.ts architecture, DevTools MCP integration, and React Compiler support. When to Use Starting new Next.js projects (use 16 from day one) Migrating from Next.js 15 to 16 Understanding Cache Components and Partial Pre-Rendering (PPR) Configuring Turbopack for optimal performance Migrating middleware.ts to proxy.ts Leveragin...
191
4480 crosspost affaan-m/everything-claude-code
Crosspost Distribute content across multiple social platforms with platform-native adaptation. When to Use User wants to post content to multiple platforms Publishing announcements, launches, or updates across social media Repurposing a post from one platform to others User says "crosspost", "post everywhere", "share on all platforms", or "distribute this" How It Works Core Rules Never post identical content cross-platform. Each platform gets a native adaptation. Primary platform first. Post to ...
191
4481 sentry-sdk-upgrade getsentry/sentry-for-ai
All Skills > Workflow > SDK Upgrade Sentry JavaScript SDK Upgrade Upgrade the Sentry JavaScript SDK across major versions with AI-guided migration. Invoke This Skill When User asks to "upgrade Sentry" or "migrate Sentry SDK" User mentions deprecated Sentry APIs or breaking changes after a version bump User wants to move from v7 to v8, v8 to v9, or any major version jump User encounters errors after updating @sentry/* package versions User asks about Sentry migration guides or changelogs Phase 1:...
191
4482 model-merging davila7/claude-code-templates
Model Merging: Combining Pre-trained Models When to Use This Skill Use Model Merging when you need to: Combine capabilities from multiple fine-tuned models without retraining Create specialized models by blending domain-specific expertise (math + coding + chat) Improve performance beyond single models (often +5-10% on benchmarks) Reduce training costs - no GPUs needed, merges run on CPU Experiment rapidly - create new model variants in minutes, not days Preserve multiple skills - merge without...
191
4483 response-drafting anthropics/knowledge-work-plugins
Response Drafting Skill You are an expert at drafting professional, empathetic, and effective customer-facing communications. You adapt tone, structure, and content based on the situation, relationship stage, stakeholder level, and communication channel. Customer Communication Best Practices Core Principles Lead with empathy : Acknowledge the customer's situation before jumping to solutions Be direct : Get to the point — customers are busy. Bottom-line-up-front. Be honest : Never overpromise, ne...
191
4484 asc-metadata-sync rudrankriyam/asc-skills
asc metadata sync Use this skill to keep local metadata in sync with App Store Connect. Two Types of Localizations 1. Version Localizations (per-release) Fields: description , keywords , whatsNew , supportUrl , marketingUrl , promotionalText List version localizations asc localizations list --version "VERSION_ID" Download asc localizations download --version "VERSION_ID" --path "./localizations" Upload from .strings files asc localizations upload --version "VERSION_ID" --path "./localizations...
191
4485 topic-monitor sundial-org/awesome-openclaw-skills
Topic Monitor Monitor what matters. Get notified when it happens. Topic Monitor transforms your assistant from reactive to proactive by continuously monitoring topics you care about and intelligently alerting you only when something truly matters. Core Capabilities Topic Configuration - Define subjects with custom parameters Scheduled Monitoring - Automated searches at configurable intervals AI Importance Scoring - Smart filtering: immediate alert vs digest vs ignore Contextual Summaries - Not j...
191
4486 golang-architect tomlord1122/tomtom-skill
Golang Backend Architecture Expert Expert assistant for Golang backend architecture with Gin Server, Layered Architecture, sqlc, PostgreSQL (Supabase), and API authentication. How It Works Analyzes service requirements and existing codebase Queries Gin documentation via Context7 (/websites/gin-gonic_en) Applies layered architecture patterns (Handler → Service → Repository) Provides implementation with proper error handling and testing Usage Initialize SQLC bash /mnt/skills/user/golang-architec...
191
4487 wordpress penetration testing sickn33/antigravity-awesome-skills
WordPress Penetration Testing Purpose Conduct comprehensive security assessments of WordPress installations including enumeration of users, themes, and plugins, vulnerability scanning, credential attacks, and exploitation techniques. WordPress powers approximately 35% of websites, making it a critical target for security testing. Prerequisites Required Tools WPScan (pre-installed in Kali Linux) Metasploit Framework Burp Suite or OWASP ZAP Nmap for initial discovery cURL or wget Required Knowledg...
191
4488 contract-review claude-office-skills/skills
Contract Review Skill You are a contract review assistant for an in-house legal team. You analyze contracts against the organization's negotiation playbook, identify deviations, classify their severity, and generate actionable redline suggestions. Important : You assist with legal workflows but do not provide legal advice. All analysis should be reviewed by qualified legal professionals before being relied upon. Playbook-Based Review Methodology Loading the Playbook Before reviewing any contract...
191
4489 anki-connect intellectronica/agent-skills
AnkiConnect Overview Enable reliable interaction with Anki through the AnkiConnect local HTTP API. Use this skill to translate user requests into AnkiConnect actions, craft JSON requests, run them via curl/jq (or equivalent tools), and interpret results safely. Preconditions and Environment If Anki is not running, launch Anki, then wait until the AnkiConnect server responds at http://127.0.0.1:8765 (default). Verify readiness using curl, e.g. curl -sS http://127.0.0.1:8765 should return Anki-C...
191
4490 framer-motion-best-practices pproenca/dot-skills
Comprehensive performance optimization guide for Framer Motion animations in React applications. Contains 42 rules across 9 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: - Adding animations to React components with Framer Motion - Optimizing bundle size for animation-heavy applications - Preventing unnecessary re-renders during animations - Implementing layout transitions or shared element animations -...
191
4491 premortem parcadei/continuous-claude-v3
Pre-Mortem Identify failure modes before they occur by systematically questioning plans, designs, and implementations. Based on Gary Klein's technique, popularized by Shreyas Doshi (Stripe). Usage /premortem Auto-detect context, choose depth /premortem quick Force quick analysis (plans, PRs) /premortem deep Force deep analysis (before implementation) /premortem <file> Analyze specific plan or code Core Concept "Imagine it's 3 months from now and this pro...
191
4492 ai-avatar-video inference-sh/skills
AI Avatar & Talking Head Videos Create AI avatars and talking head videos via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Get installation instructions: npx skills add inference-sh/skills@agent-tools infsh login Create avatar video from image + audio infsh app run bytedance/omnihuman-1-5 --input '{ "image_url": "https://portrait.jpg", "audio_url": "https://speech.mp3" }' Available Models Model App ID Best For OmniHuman 1.5 bytedance/omnihuman-1-5 Multi-character, best qua...
191
4493 threejs-skills sickn33/antigravity-awesome-skills
Threejs Skills Overview Three.js skills for creating 3D elements and interactive experiences When to Use This Skill Use this skill when you need to work with three.js skills for creating 3d elements and interactive experiences. Instructions This skill provides guidance and patterns for three.js skills for creating 3d elements and interactive experiences. For more information, see the source repository .
191
4494 disk-cleaner gccszs/disk-cleaner
Disk Cleaner Skill v2.0 High-performance cross-platform disk management toolkit with advanced optimization features for monitoring, analyzing, and cleaning disk space safely. 🚀 What's New in v2.0 Performance Enhancements 3-5x faster scanning with os.scandir() optimization Concurrent multi-threaded scanning for I/O-bound operations Intelligent sampling with QuickProfiler (estimates in 0.5-1s instead of full scan) Memory-adaptive processing with automatic memory monitoring Optimized duplicate de...
191
4495 contagious wondelai/skills
Word-of-Mouth & Virality Framework A framework for engineering word-of-mouth and making products, ideas, and content contagious. Based on Jonah Berger's research into why certain things catch on while others languish in obscurity — and how to systematically tip the odds in your favor. Core Principle Virality is not born — it is engineered. Products don't go viral by luck or by simply being great. They spread because they were designed — consciously or unconsciously — to be shared. The foundation...
191
4496 x-research rohunvora/x-research-skill
X Research General-purpose agentic research over X/Twitter. Decompose any research question into targeted searches, iteratively refine, follow threads, deep-dive linked content, and synthesize into a sourced briefing. For X API details (endpoints, operators, response format): read references/x-api.md . CLI Tool All commands run from this skill directory: cd ~/clawd/skills/x-research source ~/.config/env/global.env Search bun run x-search.ts search "<query>" [ options ] Options: --sort likes|impr...
191
4497 cosmosdb-best-practices azurecosmosdb/cosmosdb-agent-kit
Azure Cosmos DB Best Practices Comprehensive performance optimization guide for Azure Cosmos DB applications, containing 45+ rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Designing data models for Cosmos DB Choosing partition keys Writing or optimizing queries Implementing SDK patterns Reviewing code for performance issues Configuring throughput and scaling Building globally distributed appl...
191
4498 pdf-ocr-skill yejinlei/pdf-ocr-skill
PDF OCR Skill PDF OCR技能用于从影印版PDF文件和图片文件中提取文字内容。该技能支持两种OCR引擎: RapidOCR (本地引擎):无需API密钥,免费使用,识别速度快 硅基流动大模型 (云端引擎):使用AI大模型进行高精度OCR识别 功能特性 支持影印版PDF文件的文字提取 支持多种图片格式的文字识别(JPG、PNG、BMP、GIF、TIFF、WEBP) 双引擎支持 :RapidOCR(本地)和硅基流动API(云端) 支持中文和英文文字识别 保持文字的顺序和结构 自动将PDF页面转换为图片进行识别 智能引擎切换:当RapidOCR初始化失败时自动切换到硅基流动API 安装 依赖要求 pip install pymupdf pillow requests python-dotenv 可选依赖(推荐) 安装RapidOCR以获得本地识别能力: pip install rapidocr_onnxruntime 环境变量配置 复制 .env.example 文件并重命名为 .env 根据需要配置以下选项: OCR引擎选择 - "rapid": 使用RapidOCR本...
191
4499 gpt-image-1-5 intellectronica/agent-skills
GPT Image 1.5 - Image Generation & Editing Generate new images or edit existing ones using OpenAI's GPT Image 1.5 model. Generation: Uses the Responses API with image_generation tool Editing: Uses the Image API for reliable mask-based inpainting Usage Run the script using absolute path (do NOT cd to skill directory first): Generate new image: uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--quality low|medium|h...
191
4500 create-handoff parcadei/continuous-claude-v3
Create Handoff You are tasked with writing a handoff document to hand off your work to another agent in a new session. You will create a handoff document that is thorough, but also concise. The goal is to compact and summarize your context without losing any of the key details of what you're working on. Process 1. Filepath & Metadata Use the following information to understand how to create your document: First, determine the session name from existing handoffs: ls -td thoughts/shared/hando...
191