███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 10401 | news-extractor | nanmicoder/newscrawler |
News Extractor Skill 从主流新闻平台提取文章内容,输出 JSON 和 Markdown 格式。 独立可迁移 :本 Skill 包含所有必需代码,无外部依赖,可直接复制到其他项目使用。 支持平台 (12) 中文平台 平台 ID URL 示例 微信公众号 wechat https://mp.weixin.qq.com/s/xxxxx 今日头条 toutiao https://www.toutiao.com/article/123456/ 网易新闻 netease https://www.163.com/news/article/ABC123.html 搜狐新闻 sohu https://www.sohu.com/a/123456_789 腾讯新闻 tencent https://news.qq.com/rain/a/20251016A07W8J00 国际平台 平台 ID URL 示例 BBC News bbc https://www.bbc.com/news/articles/c797qlx93j0o CNN News cnn https://edition.cnn.c...
|
289 |
| 10402 | xcrawl | xcrawl-api/xcrawl-skills |
XCrawl Overview This skill is the default XCrawl entry point when the user asks for XCrawl directly without naming a specific API or sub-skill. It currently targets single-page extraction through XCrawl Scrape APIs. Default behavior is raw passthrough: return upstream API response bodies as-is. Routing Guidance If the user wants to extract one or more specific URLs, use this skill and default to XCrawl Scrape. If the user wants site URL discovery, prefer XCrawl Map APIs. If the user wants multi-...
|
289 |
| 10403 | lsp-code-analysis | lsp-client/lsp-skill |
LSP Code Analysis IMPORTANT: PREREQUISITE To use this skill, you MUST follow these steps: Check for updates: Run the update script to ensure you are using the latest version of the tool. Verify project support: Run lsp server start <project_path> to start the LSP server and confirm the project is supported. IF YOU DO NOT PERFORM THESE STEPS, YOU ARE NOT ALLOWED TO USE THIS SKILL. Abstract This document specifies the operational requirements and best practices for the lsp-code-analysis skill...
|
289 |
| 10404 | finance | travisjneuman/.claude |
No SKILL.md available for this skill. View on GitHub
|
289 |
| 10405 | seo-cannibalization-detector | sickn33/antigravity-awesome-skills |
Use this skill when Working on seo cannibalization detector tasks or workflows Needing guidance, best practices, or checklists for seo cannibalization detector Do not use this skill when The task is unrelated to seo cannibalization detector You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resour...
|
289 |
| 10406 | gitlab-ci-patterns | sickn33/antigravity-awesome-skills |
GitLab CI Patterns Comprehensive GitLab CI/CD pipeline patterns for automated testing, building, and deployment. Purpose Create efficient GitLab CI pipelines with proper stage organization, caching, and deployment strategies. When to Use Automate GitLab-based CI/CD Implement multi-stage pipelines Configure GitLab Runners Deploy to Kubernetes from GitLab Implement GitOps workflows Basic Pipeline Structure stages : - build - test - deploy variables : DOCKER_DRIVER : overlay2 DOCKER_TLS_CERTDIR : "...
|
289 |
| 10407 | anti-reversing-techniques | sickn33/antigravity-awesome-skills |
AUTHORIZED USE ONLY: This skill contains dual-use security techniques. Before proceeding with any bypass or analysis: Verify authorization: Confirm you have explicit written permission from the software owner, or are operating within a legitimate security context (CTF, authorized pentest, malware analysis, security research) Document scope: Ensure your activities fall within the defined scope of your authorization Legal compliance: Understand that unauthorized bypassing of software protection m...
|
289 |
| 10408 | symfony:api-platform-dto-resources | makfly/superpowers-symfony |
$ npx skills add https://github.com/makfly/superpowers-symfony --skill symfony:api-platform-dto-resources<div
|
289 |
| 10409 | symfony:api-platform-filters | makfly/superpowers-symfony |
$ npx skills add https://github.com/makfly/superpowers-symfony --skill symfony:api-platform-filters<div
|
289 |
| 10410 | dependency-tracking | aj-geddes/useful-ai-prompts |
Dependency Tracking Overview Dependency tracking ensures visibility of task relationships, identifies blocking issues early, and enables better resource planning and risk mitigation. When to Use Multi-team projects and programs Complex technical integrations Cross-organizational initiatives Identifying critical path items Resource allocation planning Preventing schedule delays Onboarding new team members Instructions 1. Dependency Mapping Dependency mapping and tracking class DependencyTrack...
|
289 |
| 10411 | yourvpndead-vpn-detection | aradotso/trending-skills |
YourVPNDead — Android VPN Detection & SOCKS5 Vulnerability Scanner Skill by ara.so — Daily 2026 Skills collection. Android app (Kotlin + Jetpack Compose) demonstrating that any app — without root or special permissions — can detect VPN usage, identify the VPN client, and retrieve the VPN server's exit IP through unauthenticated SOCKS5 proxies exposed on localhost by popular VPN clients (v2rayNG, NekoBox, Hiddify, etc.). Build & Install git clone https://github.com/loop-uh/yourvpndead.git cd your...
|
289 |
| 10412 | wix-cli-app-validation | wix/skills |
Wix App Validation Validates Wix CLI applications through a four-step sequential workflow: package installation, TypeScript compilation check, build, and preview. Non-Matching Intents Do NOT use this skill for: Creating new extensions → Use wix-cli-dashboard-page, wix-cli-embedded-script, etc. Deploying to production → This is for validation/testing only Unit testing → This skill validates build and preview, not unit tests Validation Workflow Execute these steps sequentially. Stop and repor...
|
288 |
| 10413 | wix-cli-backend-api | wix/skills |
Wix Backend API Builder Creates HTTP endpoints for Wix CLI applications — server-side routes that handle HTTP requests, process data, and return responses. HTTP endpoints are powered by Astro endpoints and are automatically discovered from the file system. Key facts: Files live in src/pages/api/ with .ts extension Cannot be added via npm run generate — create files directly Don't appear on the Extensions page in the app dashboard No extension registration needed (auto-discovered) Replace the leg...
|
288 |
| 10414 | wix-cli-site-plugin | wix/skills |
Wix Site Plugin Builder Creates site plugin extensions for Wix CLI applications. Site plugins are custom elements that integrate into predefined slots within Wix business solutions (like Wix Stores, Wix Bookings, Wix eCommerce), extending their functionality and user experience. Site owners can place site plugins into UI slots using the plugin explorer in Wix editors. Quick Start Checklist Follow these steps in order when creating a site plugin: Create plugin folder: src/extensions/site/plugins/...
|
288 |
| 10415 | frontend-design | dengineproblem/agents-monorepo |
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
|
288 |
| 10416 | openai-image-gen | 0xbigboss/claude-code |
OpenAI Image Gen Generate a handful of “random but structured” prompts and render them via the OpenAI Images API. Run Note: Image generation can take longer than common exec timeouts (for example 30 seconds). When invoking this skill via OpenClaw’s exec tool, set a higher timeout to avoid premature termination/retries (e.g., exec timeout=300). python3 { baseDir } /scripts/gen.py open ~/Projects/tmp/openai-image-gen-*/index.html if ~/Projects/tmp exists; else ./tmp/... Useful flags: GPT image m...
|
288 |
| 10417 | capacity-planning | aj-geddes/useful-ai-prompts |
Capacity Planning Overview Capacity planning ensures teams have sufficient resources to deliver work at sustainable pace, prevents burnout, and enables accurate commitment to stakeholders. When to Use Annual or quarterly planning cycles Allocating people to projects Adjusting team size Planning for holidays and absences Forecasting resource needs Balancing multiple projects Identifying bottlenecks Instructions 1. Capacity Assessment Team capacity calculation and planning class CapacityPlanne...
|
288 |
| 10418 | performance-regression-debugging | aj-geddes/useful-ai-prompts |
Performance Regression Debugging Overview Performance regressions occur when code changes degrade application performance. Detection and quick resolution are critical. When to Use After deployment performance degrades Metrics show negative trend User complaints about slowness A/B testing shows variance Regular performance monitoring Instructions 1. Detection & Measurement // Before: 500ms response time // After: 1000ms response time (2x slower = regression) // Capture baseline metrics const b...
|
288 |
| 10419 | documentation-site-setup | aj-geddes/useful-ai-prompts |
Documentation Site Setup Overview Set up professional documentation websites using popular static site generators like Docusaurus, MkDocs, VitePress, and GitBook. When to Use Documentation website setup API documentation portals Product documentation sites Technical documentation hubs Static site generation GitHub Pages deployment Multi-version documentation Docusaurus Setup Installation Create new Docusaurus site npx create-docusaurus@latest my-docs classic cd my-docs Install dependencies...
|
288 |
| 10420 | token-optimizer | asif2bd/openclaw-token-optimizer |
Token Optimizer Skill This skill provides the procedural knowledge to keep your OpenClaw instance lean and efficient. Quick Reference Problem Solution Background tasks bloating context Cron isolation ( sessionTarget: "isolated" ) Reading entire history every turn Local RAG with memory_search Context exceeds 100k tokens Reset & Summarize protocol Finding old conversations Session transcript indexing Workflow 1: Periodic Task Isolation To prevent background tasks from bloating your main conversati...
|
288 |
| 10421 | microservices-patterns | sickn33/antigravity-awesome-skills |
Microservices Patterns Master microservices architecture patterns including service boundaries, inter-service communication, data management, and resilience patterns for building distributed systems. When to Use This Skill Decomposing monoliths into microservices Designing service boundaries and contracts Implementing inter-service communication Managing distributed data and transactions Building resilient distributed systems Implementing service discovery and load balancing Designing event-driv...
|
288 |
| 10422 | security-scanning-security-dependencies | sickn33/antigravity-awesome-skills |
Dependency Vulnerability Scanning You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across multiple ecosystems to identify vulnerabilities, assess risks, and provide automated remediation strategies. Use this skill when Auditing dependencies for vulnerabilities or license risks Generating SBOMs for compliance or supply chain visibility Planning remediation for outdated or vulnerable packages Standard...
|
288 |
| 10423 | tdd-orchestrator | sickn33/antigravity-awesome-skills |
Use this skill when Working on tdd orchestrator tasks or workflows Needing guidance, best practices, or checklists for tdd orchestrator Do not use this skill when The task is unrelated to tdd orchestrator You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementation-playbook.md . You...
|
288 |
| 10424 | wix-cli-orchestrator | wix/skills |
Wix CLI Orchestrator Helps select the appropriate Wix CLI extension type based on use case and requirements. ⚠️ MANDATORY WORKFLOW CHECKLIST ⚠️ Before reporting completion to the user, ALL boxes MUST be checked: Step 1: Determined extension type(s) needed Asked clarifying questions if requirements were unclear Checked for implicit Data Collection need — unless user provided a collection ID directly (see Data Collection Inference ) Obtained app namespace if Data Collection extension is being crea...
|
287 |
| 10425 | wix-cli-data-collection | wix/skills |
Wix Data Collection Builder Creates CMS data collections for Wix CLI apps. The data collections extension allows your app to automatically create CMS collections when it's installed on a site. Collections store structured data that can be accessed from dashboard pages, site pages, backend code, and external applications. Important: This extension automatically enables the site's code editor, which is required for the Wix Data APIs to work. Without this extension, apps using Data APIs would need ...
|
287 |
| 10426 | vlm | answerzhao/agent-skills |
This skill guides the implementation of vision chat functionality using the z-ai-web-dev-sdk package, enabling AI models to understand and respond to images combined with text prompts. Skills Path Skill Location: `{project_path}/skills/VLM` this skill is located at above path in your project. Reference Scripts: Example test scripts are available in the `{Skill Location}/scripts/` directory for quick testing and reference. See `{Skill Location}/scripts/vlm.ts` for a working example. Overvi...
|
287 |
| 10427 | artifact-management | aj-geddes/useful-ai-prompts |
Artifact Management Overview Implement comprehensive artifact management strategies for storing, versioning, and distributing built binaries, Docker images, and packages across environments. When to Use Docker image registry management Package publication and versioning Build artifact storage and retrieval Container image optimization Artifact retention policies Multi-registry distribution Dependency caching Implementation Examples 1. Docker Registry Configuration Dockerfile with multi-stage ...
|
287 |
| 10428 | network-security-groups | aj-geddes/useful-ai-prompts |
Network Security Groups Overview Implement network security groups and firewall rules to enforce least privilege access, segment networks, and protect infrastructure from unauthorized access. When to Use Inbound traffic control Outbound traffic filtering Network segmentation Zero-trust networking DDoS mitigation Database access restriction VPN access control Multi-tier application security Implementation Examples 1. AWS Security Groups aws-security-groups.yaml Resources: VPC Security Group...
|
287 |
| 10429 | secrets-rotation | aj-geddes/useful-ai-prompts |
Secrets Rotation Overview Implement automated secrets rotation strategy for credentials, API keys, certificates, and encryption keys with zero-downtime deployment and comprehensive audit logging. When to Use API key management Database credentials TLS/SSL certificates Encryption key rotation Compliance requirements Security incident response Service account management Implementation Examples 1. Node.js Secrets Manager with Rotation // secrets-manager.js const AWS = require('aws-sdk'); const cr...
|
287 |
| 10430 | classification modeling | aj-geddes/useful-ai-prompts |
Classification Modeling Overview Classification modeling predicts categorical target values, assigning observations to discrete classes or categories based on input features. When to Use Predicting binary outcomes like customer churn, loan default, or email spam Classifying items into multiple categories such as product types or sentiment Building credit scoring models or risk assessment systems Identifying disease diagnosis or medical condition from patient data Predicting customer purchase lik...
|
287 |
| 10431 | mixin-pattern | patternsdev/skills |
Mixin Pattern A mixin is an object that we can use in order to add reusable functionality to another object or class, without using inheritance. We can't use mixins on their own: their sole purpose is to add functionality to objects or classes without inheritance. Let's say that for our application, we need to create multiple dogs. However, the basic dog that we create doesn't have any properties but a name property. When to Use Use this when you need to add reusable functionality to multiple cl...
|
287 |
| 10432 | command-pattern | patternsdev/skills |
Command Pattern With the Command Pattern , we can decouple objects that execute a certain task from the object that calls the method. Let's say we have an online food delivery platform. Users can place, track, and cancel orders. When to Use Use this when you need to decouple the object invoking an operation from the object performing it This is helpful when commands need a certain lifespan or should be queued and executed at specific times When NOT to Use For simple one-off operations that don't...
|
287 |
| 10433 | product-discovery | majiayu000/claude-arsenal |
Product Discovery Core Principles Continuous Discovery — Weekly user conversations, not episodic research Outcome-Driven — Start with outcomes to achieve, not solutions to build Assumption Testing — Validate risky assumptions before committing resources Co-Creation — Build with customers, not just for them Data-Driven — Use evidence over intuition and stakeholder opinions Problem-First — Deeply understand the problem space before ideating solutions Hard Rules (Must Follow) These rules are manda...
|
287 |
| 10434 | accessibility | davila7/claude-code-templates |
Accessibility (a11y) Comprehensive accessibility guidelines based on WCAG 2.2 and Lighthouse accessibility audits. Goal: make content usable by everyone, including people with disabilities. WCAG Principles: POUR Principle Description P erceivable Content can be perceived through different senses O perable Interface can be operated by all users U nderstandable Content and interface are understandable R obust Content works with assistive technologies Conformance levels Level Requirement Target A M...
|
287 |
| 10435 | langfuse | davila7/claude-code-templates |
Langfuse This skill helps you use Langfuse effectively across all common workflows: instrumenting applications, migrating prompts, debugging traces, and accessing data programmatically. Core Principles Follow these principles for ALL Langfuse work: Documentation First : NEVER implement based on memory. Always fetch current docs before writing code (Langfuse updates frequently) See the section below on how to access documentation. CLI for Data Access : Use langfuse-cli when querying/modifying Lan...
|
287 |
| 10436 | rdkit | davila7/claude-code-templates |
RDKit Cheminformatics Toolkit Overview RDKit is a comprehensive cheminformatics library providing Python APIs for molecular analysis and manipulation. This skill provides guidance for reading/writing molecular structures, calculating descriptors, fingerprinting, substructure searching, chemical reactions, 2D/3D coordinate generation, and molecular visualization. Use this skill for drug discovery, computational chemistry, and cheminformatics research tasks. Core Capabilities 1. Molecular I/O an...
|
287 |
| 10437 | cocoindex | davila7/claude-code-templates |
CocoIndex Overview CocoIndex is an ultra-performant real-time data transformation framework for AI with incremental processing. This skill enables building indexing flows that extract data from sources, apply transformations (chunking, embedding, LLM extraction), and export to targets (vector databases, graph databases, relational databases). Core capabilities: Write indexing flows - Define ETL pipelines using Python Create custom functions - Build reusable transformation logic Operate flows ...
|
287 |
| 10438 | wix-cli-extension-registration | wix/skills |
Wix App Registration After creating any extension file, you must update the main src/extensions.ts file to register the extension with the app. Why Registration Matters The Wix CLI discovers extensions through the src/extensions.ts file — it's the single entry point that tells the build system which extensions exist. Without registration: Dashboard pages won't appear in the sidebar Site widgets won't show in the Wix Editor Service plugins won't be called during checkout flows Event handlers won'...
|
286 |
| 10439 | contrast-checker | accesslint/claude-marketplace |
You are an expert color contrast analyzer specializing in WCAG 2.1 compliance. Your Role You analyze color contrast ratios in codebases and provide actionable recommendations for achieving WCAG AA compliance while preserving the original design aesthetic. When to Activate Use this skill when: User mentions color contrast, WCAG compliance, or accessibility issues Discussion involves colors in UI components, text readability, or visual design User asks about making colors more accessible Analyzing...
|
286 |
| 10440 | effect-ts | kastalien-research/thoughtbox-dot-claude |
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...
|
286 |
| 10441 | firecrawl | connorads/dotfiles |
Firecrawl CLI Web scraping, search, and browser automation CLI. Returns clean markdown optimized for LLM context windows. Run firecrawl --help or firecrawl <command> --help for full option details. Prerequisites Must be installed and authenticated. Check with firecrawl --status . 🔥 firecrawl cli v1.8.0 ● Authenticated via FIRECRAWL_API_KEY Concurrency: 0/100 jobs (parallel scrape limit) Credits: 500,000 remaining Concurrency : Max parallel jobs. Run parallel operations up to this limit. Credits ...
|
286 |
| 10442 | wireframe | markdown-viewer/skills |
UI Wireframe & Mockup Generator Quick Start: Choose platform (Web/iOS/Android) → Add UI components from stencil library → Arrange in screen layout → Add navigation flows → Wrap in ```drawio fence. ⚠️ IMPORTANT: Always use ```drawio code fence. NEVER use ```xml — it will NOT render as a diagram. Critical Rules 🔗 This is a drawio-derived skill. All structure, layout, and edge routing rules inherit from drawio SKILL.md . Read the base rules first. Wireframe-specific additions: Check stencils/README...
|
286 |
| 10443 | container-registry-management | aj-geddes/useful-ai-prompts |
Container Registry Management Overview Implement comprehensive container registry management including image scanning, vulnerability detection, retention policies, access control, and multi-region replication. When to Use Container image storage and distribution Security scanning and compliance Image retention and cleanup Registry access control Multi-region deployments Image signing and verification Cost optimization Implementation Examples 1. AWS ECR Setup and Management ecr-setup.yaml apiV...
|
286 |
| 10444 | deep-research-pro | parags/deep-research-pro |
Deep Research Pro 🔬 A powerful, self-contained deep research skill that produces thorough, cited reports from multiple web sources. No paid APIs required — uses DuckDuckGo search. How It Works When the user asks for research on any topic, follow this workflow: Step 1: Understand the Goal (30 seconds) Ask 1-2 quick clarifying questions: "What's your goal — learning, making a decision, or writing something?" "Any specific angle or depth you want?" If the user says "just research it" — skip ahead w...
|
286 |
| 10445 | paywall-upgrade-cro | davila7/claude-code-templates |
Paywall and Upgrade Screen CRO You are an expert in in-app paywalls and upgrade flows. Your goal is to convert free users to paid, or upgrade users to higher tiers, at moments when they've experienced enough value to justify the commitment. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already ...
|
286 |
| 10446 | tdd-workflow | davila7/claude-code-templates |
Test-Driven Development Workflow This skill ensures all code development follows TDD principles with comprehensive test coverage. When to Activate Writing new features or functionality Fixing bugs or issues Refactoring existing code Adding API endpoints Creating new components Core Principles 1. Tests BEFORE Code ALWAYS write tests first, then implement code to make tests pass. 2. Coverage Requirements Minimum 80% coverage (unit + integration + E2E) All edge cases covered Error scenarios tested ...
|
286 |
| 10447 | gwas-database | davila7/claude-code-templates |
GWAS Catalog Database Overview The GWAS Catalog is a comprehensive repository of published genome-wide association studies maintained by the National Human Genome Research Institute (NHGRI) and the European Bioinformatics Institute (EBI). The catalog contains curated SNP-trait associations from thousands of GWAS publications, including genetic variants, associated traits and diseases, p-values, effect sizes, and full summary statistics for many studies. When to Use This Skill This skill shoul...
|
286 |
| 10448 | moss-tts-nano-speech | aradotso/trending-skills |
MOSS-TTS-Nano Speech Generation Skill Skill by ara.so — Daily 2026 Skills collection. MOSS-TTS-Nano is an open-source multilingual tiny TTS model (0.1B parameters) from MOSI.AI and the OpenMOSS team. It uses an Audio Tokenizer + LLM autoregressive pipeline to generate 48 kHz stereo speech in real time, supports 20 languages, voice cloning, streaming inference, and runs on CPU without a GPU. Installation Conda (recommended) conda create -n moss-tts-nano python = 3.12 -y conda activate moss-tts-na...
|
286 |
| 10449 | alicloud-ai-audio-asr | cinience/alicloud-skills |
Category: provider Model Studio Qwen ASR (Non-Realtime) Validation mkdir -p output/alicloud-ai-audio-asr python -m py_compile skills/ai/audio/alicloud-ai-audio-asr/scripts/transcribe_audio.py && echo "py_compile_ok" > output/alicloud-ai-audio-asr/validate.txt Pass criteria: command exits 0 and output/alicloud-ai-audio-asr/validate.txt is generated. Output And Evidence Store transcripts and API responses under output/alicloud-ai-audio-asr/ . Keep one command log or sample response per run. Use Qw...
|
285 |
| 10450 | targeted-chatroom | dontbesilent2025/claude-skills |
targeted-chatroom:定向聊天室 你是定向聊天室的主持人。根据话题推荐或接受用户指定的专家,模拟多角色对话。 工作流程 第一步:检测模式 情况 A:用户指定了人物 格式: /定向聊天室 [人物1] [人物2] [人物3] 示例: /定向聊天室 查理·芒格 丹尼尔·卡尼曼 雷·达里奥 动作:直接跳到第三步 情况 B:用户未指定人物 格式: /定向聊天室 (或其他触发词) 动作:进入第二步 第二步:推荐人物(仅情况 B) 分析话题,推荐 3-5 位专家: 🎯 根据话题「{话题总结}」,推荐以下专家: 1. {人物1}:{核心观点一句话} 2. {人物2}:{核心观点一句话} 3. {人物3}:{核心观点一句话} 确认后启动聊天室。 停在这里,等用户回复「确认」「开始」或调整人选。不要继续执行。 第三步:生成对话(使用 Agent tool) 确认人物后,使用 Agent tool 并行调用多个专家。每个专家一个独立 Agent。 Prompt 模板结构 为每位专家生成如下结构的 prompt: 你是 {专家名字}。 话题:{用户的话题} 思考方式: 1. {该专家的核心思维方...
|
285 |