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...
25,082
总 Skills
109.6M
总安装量
2,605
贡献者
# Skill 仓库 描述 安装量
18301 tailwind-config sgcarstrends/sgcarstrends
Tailwind CSS Configuration Skill This skill helps you configure and customize Tailwind CSS across the monorepo. When to Use This Skill Adding custom colors to the design system Configuring typography scales Customizing spacing and sizing Setting up design tokens Configuring Tailwind plugins Debugging Tailwind configuration issues Creating reusable theme presets Tailwind Configuration Structure ├── packages/ui/ │ ├── tailwind.config.ts UI package Tailwind config │ └── src/styles/glob...
 57
18302 api-response-optimization secondsky/claude-skills
API Response Optimization Overview Fast API responses improve overall application performance and user experience. Optimization focuses on payload size, caching, and query efficiency. When to Use Slow API response times High server CPU/memory usage Large response payloads Performance degradation Scaling bottlenecks Instructions 1. Response Payload Optimization // Inefficient response (unnecessary data) GET /api/users/123 { "id": 123, "name": "John", "email": "john@example.com", "passwo...
 57
18303 add-vault-abi-methods tradingstrategy-ai/web3-ethereum-defi
Add vault ABI methods This is a skill description to add smart contract Inputs Vault protocol name Smart contract address and a blockchain as a blockchain explorer link What methods to cover Vault classes Vault protocol classes can be found in eth_defi/erc_4626/vault_protocol folder. Each vault protocol has its own class. There are 40+ protocols. Some protocol share classes and extend other protocols. Smart contracts Each vault class wraps a JSON-RPC calls to an Ethereum smart contract. The...
 57
18304 uv-package-manager autumnsgrove/groveengine
UV Package Manager Comprehensive guide to using uv, an extremely fast Python package installer and resolver written in Rust, for modern Python project management and dependency workflows. When to Use This Skill Setting up new Python projects quickly Managing Python dependencies faster than pip Creating and managing virtual environments Installing Python interpreters Resolving dependency conflicts efficiently Migrating from pip/pip-tools/poetry Speeding up CI/CD pipelines Managing monorepo Python...
 57
18305 sglang orchestra-research/ai-research-skills
SGLang High-performance serving framework for LLMs and VLMs with RadixAttention for automatic prefix caching. When to use SGLang Use SGLang when: Need structured outputs (JSON, regex, grammar) Building agents with repeated prefixes (system prompts, tools) Agentic workflows with function calling Multi-turn conversations with shared context Need faster JSON decoding (3× vs standard) Use vLLM instead when: Simple text generation without structure Don't need prefix caching Want mature, widely-...
 57
18306 naming-format tartinerlabs/skills
You are a naming conventions expert. Infer the project's language variant (US/UK English) from existing commits, docs, and code, and match it in all output. Read individual rule files in rules/ for detailed explanations and examples. Rules Overview Rule Impact File Case consistency HIGH rules/case-consistency.md File suffixes HIGH rules/file-suffixes.md Export naming HIGH rules/export-naming.md Index files HIGH rules/index-files.md Framework conventions MEDIUM rules/framework-conventions.md Work...
 57
18307 qdrant vm0-ai/vm0-skills
Qdrant Vector Database Integration Overview Qdrant is an AI-native vector database for semantic search and similarity retrieval. This skill provides patterns for integrating Qdrant with Java applications, focusing on Spring Boot integration and LangChain4j framework support. Enable efficient vector search capabilities for RAG systems, recommendation engines, and semantic search applications. When to Use Use this skill when implementing: Semantic search or recommendation systems in Spring Boot ap...
 57
18308 memos-memory-guide memtensor/memos
MemOS Local Memory — Agent Guide This skill describes how to use the MemOS memory tools so you can reliably search and use the user's long-term conversation history, share knowledge across agents, and discover public skills. How memory is provided each turn Automatic recall (hook): At the start of each turn, the system runs a memory search using the user's current message and injects relevant past memories into your context. You do not need to call any tool for that. When that is not enough: If ...
 57
18309 create-blog-post jim60105/blog
Create Blog Post on 聆.tw This skill guides the full workflow of creating a new tech blog post on 聆.tw (琳聽智者漫談), from repo setup to PR submission. [!IMPORTANT] We use git submodules in this blog repository, and the content is stored within these submodules. Therefore, all git operations for creating a new blog post must be performed inside the submodule directory ( 聆.tw/content/ ). ALWAYS CHECK PWD AND GIT STATUS TO MAKE SURE YOU'RE IN THE CORRECT DIRECTORY AND STATE BEFORE RUNNING ANY GIT COMMAN...
 57
18310 laravel-blade fusengine/agents
Laravel Blade Agent Workflow (MANDATORY) Before ANY implementation, use TeamCreate to spawn 3 agents: fuse-ai-pilot:explore-codebase - Check existing views, components structure fuse-ai-pilot:research-expert - Verify latest Blade docs via Context7 mcp__context7__query-docs - Query specific patterns (components, slots) After implementation, run fuse-ai-pilot:sniper for validation. Overview Blade is Laravel's templating engine. It provides a clean syntax for PHP in views while compiling to pure PH...
 57
18311 theme-factory shipshitdev/library
Theme Factory Skill This skill provides a curated collection of professional font and color themes themes, each with carefully selected color palettes and font pairings. Once a theme is chosen, it can be applied to any artifact. Purpose To apply consistent, professional styling to presentation slide decks, use this skill. Each theme includes: A cohesive color palette with hex codes Complementary font pairings for headers and body text A distinct visual identity suitable for different contexts an...
 57
18312 deepspeed orchestra-research/ai-research-skills
Deepspeed Skill Comprehensive assistance with deepspeed development, generated from official documentation. When to Use This Skill This skill should be triggered when: Working with deepspeed Asking about deepspeed features or APIs Implementing deepspeed solutions Debugging deepspeed code Learning deepspeed best practices Quick Reference Common Patterns Pattern 1: DeepNVMe Contents Requirements Creating DeepNVMe Handles Using DeepNVMe Handles Blocking File Write Non-Blocking File Write Paral...
 57
18313 umbraco-playwright-testhelpers umbraco/umbraco-cms-backoffice-skills
Umbraco Playwright Testhelpers What is it? @umbraco/playwright-testhelpers is the official Umbraco package that provides Playwright fixtures, API helpers, and UI helpers for writing E2E tests against an Umbraco backoffice instance. Repository : https://github.com/umbraco/Umbraco.Playwright.Testhelpers Installation npm install @umbraco/playwright-testhelpers --save-dev
 57
18314 moe-training orchestra-research/ai-research-skills
MoE Training: Mixture of Experts When to Use This Skill Use MoE Training when you need to: Train larger models with limited compute (5× cost reduction vs dense models) Scale model capacity without proportional compute increase Achieve better performance per compute budget than dense models Specialize experts for different domains/tasks/languages Reduce inference latency with sparse activation (only 13B/47B params active in Mixtral) Implement SOTA models like Mixtral 8x7B, DeepSeek-V3, Switch T...
 57
18315 annualreports danielmiessler/personal_ai_infrastructure
Before executing, check for user customizations at: `~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/AnnualReports/` If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults. AnnualReports - Security Report Aggregation Aggregates and analyzes annual security reports from 570+ sources across the cybersecurity industry. Source: [awesome-annual-security-rep...
 57
18316 gtm-pricing scientiacapital/skills
<quick_start> ICP scoring: 80+ = Ideal | 60-79 = Good | 40-59 = Marginal | <40 = Pass Positioning statement: For [target] who [need], [product] is a [category] that [benefit]. Unlike [alternative], our product [differentiator]. Value-based pricing: Price at 10-20% of quantified value delivered Opportunity score: /100 across Market Fit, Technical Fit, GTM Fit, Personal Fit, Economics </quick_start> <success_criteria> GTM strategy is successful when: ICP documented with scoring criteria (fi...
 57
18317 web-motion-design dylantarre/animation-principles
Web Motion Design Apply Disney's 12 animation principles to CSS, JavaScript, and frontend frameworks. Quick Reference Principle Web Implementation Squash & Stretch transform: scale() on interaction states Anticipation Slight reverse movement before action Staging Focus user attention with motion hierarchy Straight Ahead / Pose to Pose JS frame-by-frame vs CSS keyframes Follow Through / Overlapping Staggered child animations, elastic easing Slow In / Slow Out ease-in-out , cubic-bezier curves Arc...
 57
18318 panther-strike autumnsgrove/groveengine
Panther Strike 🐆 The panther doesn't ask permission. It watches. It waits. Then — swiftness . Lock onto a single issue. Melt into the shadows. Weave through the branches. Strike with deadly silence. Leave nothing but a clean commit in your wake and the fading echo of a hunt well-had. When to Activate User provides an issue number to fix User says "strike", "drop on", "attack", or "kill" an issue User explicitly calls /panther-strike 123 User wants focused, rapid resolution of ONE issue The Hunt ...
 57
18319 godot-quest-system thedivergentai/gd-agentic-skills
Quest System Resource-based data, signal-driven updates, and AutoLoad coordination define scalable quest architectures. Available Scripts quest_manager.gd Expert AutoLoad quest tracker with objective progression and reward distribution. quest_graph_manager.gd Runtime manager for graph-based quests. Tracks objectives and node progression. NEVER Do in Quest Systems NEVER store quest data in nodes — Quest progress in player.gd variables? Loss on scene reload. Use Resource-based Quests OR AutoLoad s...
 57
18320 rbac-permissions-builder patricio0312rev/skills
RBAC/Permissions Builder Implement flexible role-based access control systems. Permission Matrix // Define permissions export enum Permission { USER_READ = "user:read", USER_WRITE = "user:write", USER_DELETE = "user:delete", POST_READ = "post:read", POST_WRITE = "post:write", ADMIN_ACCESS = "admin:access", } // Define roles export const ROLE_PERMISSIONS = { user: [Permission.USER_READ, Permission.POST_READ, Permission.POST_WRITE], moderator: [...userPermissions, Permission.POS...
 57
18321 windows-git-bash-testing josiahsiegel/claude-plugin-marketplace
Windows and Git Bash Testing Compatibility Guide Overview This guide provides essential knowledge for running Vitest, Playwright, and MSW tests on Windows, particularly in Git Bash/MINGW environments. It addresses common path conversion issues, shell detection, and cross-platform test execution patterns. Shell Detection in Test Environments Detecting Git Bash/MINGW When running tests in Git Bash or MINGW environments, use these detection methods: Method 1: Environment Variable (Most Reliable...
 57
18322 brainstorming-research-ideas orchestra-research/ai-research-skills
Research Idea Brainstorming Structured frameworks for discovering the next research idea. This skill provides ten complementary ideation lenses that help researchers move from vague curiosity to concrete, defensible research proposals. Each framework targets a different cognitive mode—use them individually or combine them for comprehensive exploration. When to Use This Skill Starting a new research direction and need structured exploration Feeling stuck on a current project and want fresh angles...
 57
18323 slack-gif-creator davepoon/buildwithclaude
Slack GIF Creator A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack. Slack Requirements Dimensions: Emoji GIFs: 128x128 (recommended) Message GIFs: 480x480 Parameters: FPS: 10-30 (lower is smaller file size) Colors: 48-128 (fewer = smaller file size) Duration: Keep under 3 seconds for emoji GIFs Core Workflow from core . gif_builder import GIFBuilder from PIL import Image , ImageDraw 1. Create builder builder = GIFBuilder ( width = 128 , height = 128 , f...
 57
18324 web-design-guidelines asyrafhussin/agent-skills
Web Interface Guidelines Review files for compliance with Web Interface Guidelines. How It Works Fetch the latest guidelines from the source URL below Read the specified files (or prompt user for files/pattern) Check against all rules in the fetched guidelines Output findings in the terse file:line format Guidelines Source Fetch fresh guidelines before each review: https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md Use WebFetch to retrieve the latest rules. Th...
 57
18325 sap-btp-best-practices secondsky/sap-skills
Production-ready SAP BTP implementation guidance based on official SAP documentation. Quick Links: - Official Guide: [https://github.com/SAP-docs/btp-best-practices-guide](https://github.com/SAP-docs/btp-best-practices-guide) - SAP Help Portal: [https://help.sap.com/docs/btp/btp-administrators-guide](https://help.sap.com/docs/btp/btp-administrators-guide) Table of Contents - [Platform Fundamentals](platform-fundamentals) - [Account Model Setup](account-model-setup) - [Security and Authen...
 57
18326 rangebar-eval-metrics terrylica/cc-skills
Machine-readable reference + computation scripts for state-of-the-art metrics evaluating range bar (price-based sampling) data. Quick Start ``` Compute metrics from predictions + actuals python scripts/compute_metrics.py --predictions preds.npy --actuals actuals.npy --timestamps ts.npy Generate full evaluation report python scripts/generate_report.py --results folds.jsonl --output report.md ``` Metric Tiers | Primary (5) | Research decisions | weekly_sharpe, hit_rate, cumulative_pnl,...
 57
18327 resume-optimization melodic-software/claude-code-plugins
Resume Optimization Comprehensive guidance for creating effective software engineering resumes that pass ATS systems and resonate with hiring managers. When to Use This Skill Reviewing or improving a software engineer's resume Crafting impactful achievement bullets from work experience Optimizing resume content for ATS keyword matching Tailoring a resume for a specific job description Understanding modern resume structure and formatting Core Principles The Resume's Purpose A resume is a marke...
 57
18328 github-actions-2025 josiahsiegel/claude-plugin-marketplace
GitHub Actions 2025 Features 1 vCPU Linux Runners (October 2025 - Public Preview) What: New lightweight runners optimized for automation tasks with lower cost. Specs: 1 vCPU 5 GB RAM 15-minute job limit Optimized for short-running tasks When to Use 1 vCPU Runners Ideal for: Issue triage automation Label management PR comment automation Status checks Lightweight scripts Git operations (checkout, tag, commit) Notification tasks NOT suitable for: Build operations Test suites Complex CI/CD pi...
 57
18329 memory-lifecycle basicmachines-co/basic-memory-skills
Memory Lifecycle Manage how entities move through status stages in Basic Memory. The core principle: archive, never delete. Completed work is valuable context — move it out of the active view, but keep it in the knowledge graph. When to Use User says something is "done", "finished", "completed", "submitted", "missed", or "cancelled" Moving entities between status folders (active → archive, pipeline → active, etc.) Reverting a mistaken completion Periodic cleanup of stale active items Core Princi...
 57
18330 chanjing-tts chanjing-ai/chan-skills
Chanjing TTS When to Use This Skill Use this skill when the user needs to generate audio from text. Chanjing TTS supports: both Chinese and English multiple system voices adjustment of speech speed sentence-level timestamp in result How to Use This Skill Multiple APIs need to be invoked. All share the domain: " https://open-api.chanjing.cc ". All requests communicate using json. You should use utf-8 to encode and decode text throughout this task. Obtain an access_token , which is required for al...
 57
18331 vueuse-motion-skilld harlan-zw/vue-ecosystem-skills
vueuse/motion @vueuse/motion Vue Composables putting your components in motion Version: 3.0.3 (Mar 2025) Deps: @vueuse/core@^13.0.0, @vueuse/shared@^13.0.0, defu@^6.1.4, framesync@^6.1.2, popmotion@^11.0.5, style-value-types@^5.1.2 Tags: beta: 2.0.0-beta.29 (May 2023), latest: 3.0.3 (Mar 2025) References: Docs — API reference, guides API Changes This section documents version-specific API changes — prioritize recent major/minor releases. BREAKING: ESM-only — @vueuse/motion v3.0.0 dropped CommonJ...
 57
18332 baseproject-update autumnsgrove/groveengine
BaseProject Update Skill When to Activate Activate this skill when: Updating an existing BaseProject installation to latest Syncing skills or AgentUsage docs with upstream User says "update baseproject", "sync baseproject", or invokes /baseproject-update Refreshing project templates after upstream changes Prerequisites Project already has BaseProject installed ( .claude/skills/ and/or AgentUsage/ exist) Git repository is clean (commit or stash changes first) Update Workflow Execute these steps i...
 57
18333 gguf-quantization orchestra-research/ai-research-skills
GGUF - Quantization Format for llama.cpp The GGUF (GPT-Generated Unified Format) is the standard file format for llama.cpp, enabling efficient inference on CPUs, Apple Silicon, and GPUs with flexible quantization options. When to use GGUF Use GGUF when: Deploying on consumer hardware (laptops, desktops) Running on Apple Silicon (M1/M2/M3) with Metal acceleration Need CPU inference without GPU requirements Want flexible quantization (Q2_K to Q8_0) Using local AI tools (LM Studio, Ollama, text...
 57
18334 llm-router jamesrochabrun/skills
LLM Router Overview Route AI requests to different LLM providers using SwiftOpenAI-CLI's agent mode. This skill automatically configures the CLI to use the requested provider (OpenAI, Grok, Groq, DeepSeek, or OpenRouter), ensures the tool is installed and up-to-date, and executes one-shot agentic tasks. Core Workflow When a user requests to use a specific LLM provider (e.g., "use grok to explain quantum computing"), follow this workflow: Step 1: Ensure SwiftOpenAI-CLI is Ready Check if Swif...
 57
18335 python-workspace terrylica/cc-skills
Seamless MQL5 indicator translation to Python with autonomous validation and self-correction. When to Use This Skill Use this skill when the user wants to: - Export market data or indicator values from MetaTrader 5 - Translate MQL5 indicators to Python implementations - Validate Python indicator accuracy against MQL5 reference - Understand MQL5-Python workflow capabilities and limitations - Troubleshoot common translation issues Activation Phrases: "MQL5", "MetaTrader", "indicator trans...
 57
18336 n8n-patterns mindmorass/reflex
n8n Workflow Patterns Build robust workflow automations with n8n - the open-source workflow automation tool. Overview n8n is a self-hostable workflow automation platform that connects apps and services. Key features: Visual workflow builder with 400+ integrations Self-hosted or cloud deployment Code nodes for custom logic (JavaScript/Python) Webhook triggers for real-time automation Sub-workflows for modular design Core Concepts Workflow Structure ┌─────────────┐ ┌─────────────┐ ┌─────...
 57
18337 nemo-guardrails orchestra-research/ai-research-skills
NeMo Guardrails - Programmable Safety for LLMs Quick start NeMo Guardrails adds programmable safety rails to LLM applications at runtime. Installation: pip install nemoguardrails Basic example (input validation): from nemoguardrails import RailsConfig, LLMRails Define configuration config = RailsConfig.from_content(""" define user ask about illegal activity "How do I hack" "How to break into" "illegal ways to" define bot refuse illegal request "I cannot help with illegal activit...
 57
18338 prior-auth-review-skill anthropics/healthcare
Prior Authorization Review Skill Overview This skill automates the payer review process for prior authorization (PA) requests. It processes clinical documentation, validates medical necessity against coverage policies, and generates authorization decisions with supporting rationale. Target Users: Health insurance payer organizations (Medicare Advantage, Commercial, Medicaid MCOs) Value Proposition: Reduce PA review time from 30-60 minutes to under 5 minutes. Enable auto-approval for 40-60% of...
 57
18339 bee-collect autumnsgrove/groveengine
Bee Collect 🐝 The bee buzzes from flower to flower through the meadow, gathering what the others have bloomed. Each idea, each task, each thought—collected, examined, and stored with care. The bee doesn't build the honeycomb (that's not its job). It collects the pollen, ensures it's properly catalogued, and deposits it in the hive where it can be found when needed. When the workers arrive, they know exactly which cell holds what they need. When to Activate User provides a batch of TODOs, tasks, ...
 57
18340 developer-growth-analysis davepoon/buildwithclaude
Developer Growth Analysis This skill provides personalized feedback on your recent coding work by analyzing your Claude Code chat interactions and identifying patterns that reveal strengths and areas for growth. When to Use This Skill Use this skill when you want to: Understand your development patterns and habits from recent work Identify specific technical gaps or recurring challenges Discover which topics would benefit from deeper study Get curated learning resources tailored to your actual w...
 57
18341 hig-components-status raintree-technology/apple-hig-skills
Apple HIG: Status Components Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Show progress for operations longer than a second or two. Determinate when duration/percentage is known. A filling progress bar gives users a clear sense of remaining work. Use for downloads, uploads, or any measurable process. Indeterminate when duration is unknown. A spinner communicates work is happening without p...
 57
18342 tmux hkuds/nanobot
tmux Session Control Control tmux sessions by sending keystrokes and reading output. Essential for managing Claude Code sessions. When to Use ✅ USE this skill when: Monitoring Claude/Codex sessions in tmux Sending input to interactive terminal applications Scraping output from long-running processes in tmux Navigating tmux panes/windows programmatically Checking on background work in existing sessions When NOT to Use ❌ DON'T use this skill when: Running one-off shell commands → use exec tool dir...
 57
18343 implement-plan-preflight terrylica/cc-skills
Execute the Preflight phase of the `/itp:go` workflow. Creates ADR and Design Spec artifacts with proper cross-linking and verification. When to Use This Skill - Invoked by `/itp:go` command during Preflight phase - User asks to create an ADR for a feature - User mentions "design spec" or "MADR format" - Manual preflight verification needed Preflight Workflow Overview ``` P.1: Create Feature Branch (if -b flag) │ ▼ P.2: Create ADR File (MADR 4.0) │ ▼ ...
 57
18344 acli-jira arjunmahishi/dotfiles
Purpose Use this skill when you need to interact with Jira: reading tickets, creating new work items, updating existing ones, searching with JQL, transitioning status, assigning, commenting, or browsing projects. acli jira provides full Jira Cloud management from the CLI. When to use what acli jira workitem view : View a specific ticket by key. Use to read ticket details, description, status, assignee, etc. acli jira workitem search : Find tickets using JQL queries. Use for any search, filtering...
 57
18345 tmux connorads/dotfiles
tmux Session Control Control tmux sessions by sending keystrokes and reading output. Essential for managing Claude Code sessions. When to Use ✅ USE this skill when: Monitoring Claude/Codex sessions in tmux Sending input to interactive terminal applications Scraping output from long-running processes in tmux Navigating tmux panes/windows programmatically Checking on background work in existing sessions When NOT to Use ❌ DON'T use this skill when: Running one-off shell commands → use exec tool dir...
 57
18346 evolve miles990/self-evolving-agent
/evolve — Goal-Driven Compounding Loop Measure what's wrong. Fix the worst thing. Measure again. Compound. Always-on autonomous loop over /rpi . Work selection order: Harvested .agents/rpi/next-work.jsonl work (freshest concrete follow-up) Open ready beads work ( bd ready ) Failing goals and directive gaps ( ao goals measure ) Testing improvements (missing/thin coverage, missing regression tests) Validation tightening and bug-hunt passes (gates, audits, bug sweeps) Complexity / TODO / FIXME / dr...
 57
18347 dust-temporal dust-tt/dust
Creating Temporal Workflows This skill guides you through creating Temporal workflows for durable background processing. Quick Reference Files Structure (per queue) temporal/your_queue/ ├── config.ts Queue name and version ├── helpers.ts Workflow ID generators ├── activities.ts Activity implementations (DB, API calls) ├── workflows.ts Workflow orchestration ├── worker.ts Worker setup └── client.ts Workflow launcher functions Key Concepts Wor...
 57
18348 storybook-args-controls thebushidocollective/han
Storybook - Args and Controls Configure interactive controls and args to make stories dynamic and explorable, allowing designers and developers to test component variations in real-time. Key Concepts Args Args are inputs to components that Storybook tracks and makes interactive: export const Primary: Story = { args: { label: 'Button', primary: true, size: 'medium', onClick: () => alert('clicked'), }, }; ArgTypes ArgTypes define metadata about args, including control typ...
 57
18349 find-skills openstatushq/openstatus
Find Skills This skill helps you discover and install skills from the open agent skills ecosystem. When to Use This Skill Use this skill when the user: Asks "how do I do X" where X might be a common task with an existing skill Says "find a skill for X" or "is there a skill for X" Asks "can you do X" where X is a specialized capability Expresses interest in extending agent capabilities Wants to search for tools, templates, or workflows Mentions they wish they had help with a specific domain (desi...
 57
18350 dingtalk_channel_connect agentscope-ai/copaw
钉钉 Channel 自动连接（可视浏览器） 此 skill 用于通过可视浏览器自动化完成钉钉应用创建与 CoPaw channel 绑定。 强制规则 必须使用可视浏览器模式启动： { "action" : "start" , "headed" : true } 遇到登录关卡必须暂停： 若页面出现登录界面（如 登录 、扫码登录、手机号/密码登录），立即停止自动操作。 明确提示用户先手动登录，再等待用户回复“登录好了/继续”。 未收到用户确认前，不得继续执行后续步骤。 任何应用配置变更都必须新建版本并发布后才生效： 配置完机器人相关信息后 一定要发布机器人 不论是新建应用还是修改应用信息（名称、描述、图标、机器人配置等），最终都 必须执行“创建新版本 + 发布” 。 若未完成发布，不得宣称配置已生效。 执行前显著确认（必须先做） 在开始自动化点击前，先向用户发起一次“配置确认”，明确告知可自定义项、图片规范、默认值。建议使用如下结构化确认： 让用户可自定义以下字段： 应用名称 应用描述 机器人图标图片链接或本地路径 机器人消息预览图链接或本地路径 明确告知图片规范（显著提示）： 机器人图...
 57