███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 18701 | context-fundamentals | guanyang/antigravity-skills |
Context Engineering Fundamentals Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Understanding context fundamentals is prerequisite to effective context engineering. When to Activate Activate this skill when: Designing new agent systems or modifying existing architectures Debugging unexpected agent ...
|
48 |
| 18702 | product description writer | eddiebe147/claude-settings |
Product Description Writer Transform product features into compelling descriptions that sell. This skill helps you create persuasive, SEO-optimized product copy for e-commerce platforms, marketplaces, and catalogs that converts browsers into buyers. Whether you're writing for Amazon, Shopify, your own store, or product catalogs, this skill ensures your descriptions highlight benefits, overcome objections, and make customers feel confident in their purchase decision. It balances persuasion with i...
|
48 |
| 18703 | voicemode | mbailey/voicemode |
First-Time Setup If VoiceMode isn't working or MCP fails to connect, run: /voicemode:install After install, reconnect MCP: /mcp → select voicemode → "Reconnect" (or restart Claude Code). VoiceMode Natural voice conversations with Claude Code using speech-to-text (STT) and text-to-speech (TTS). Note: The Python package is voice-mode (hyphen), but the CLI command is voicemode (no hyphen). When to Use MCP vs CLI Task Use Why Voice conversations MCP voicemode:converse Faster - server already running...
|
48 |
| 18704 | anygen-storybook | anygenio/anygen-skills |
AnyGen Storybook / Creative Generator You MUST strictly follow every instruction in this document. Do not skip, reorder, or improvise any step. Create storybook-style visuals for narratives and slides using AnyGen OpenAPI. Powered by Nano Banana pro and Nano Banana 2. Output: thumbnail preview + online task URL, with file download on request. When to Use User needs to create a storybook, visual narrative, or creative visuals User has files to upload as reference material for storybook generation...
|
48 |
| 18705 | blueprint-docs-list | laurigates/claude-plugins |
List blueprint documents programmatically from the filesystem. Extracts metadata from YAML frontmatter and markdown headers. Use Case : Audit document status, generate index tables, or get a quick overview of all project documentation. Parameters Arg Description adrs List Architecture Decision Records prds List Product Requirements Documents prps List Product Requirement Prompts all Summary of all document types Execution If arg is adrs Run /blueprint:adr-list — it handles ADR-specific extractio...
|
48 |
| 18706 | user-interface-designer | qodex-ai/ai-agent-skills |
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: Purpo...
|
48 |
| 18707 | memory-management | jzocb/openclaw-memory-management |
Memory Management Memory makes Claude your workplace collaborator - someone who speaks your internal language. The Goal Transform shorthand into understanding: User: "ask todd to do the PSR for oracle" ↓ Claude decodes "Ask Todd Martinez (Finance lead) to prepare the Pipeline Status Report for the Oracle Systems deal ($2.3M, closing Q2)" Without memory, that request is meaningless. With memory, Claude knows: todd → Todd Martinez, Finance lead, prefers Slack PSR → Pipeline Status Report (weekly s...
|
48 |
| 18708 | streamlit-app | owid/etl |
Streamlit Apps in Wizard Apps live in apps/wizard/app_pages/ . Run with make wizard or .venv/bin/etlwiz <alias> . Creating a New App Create apps/wizard/app_pages/your_app/app.py : import streamlit as st st . set_page_config ( page_title = "Wizard: Your App" , page_icon = "🪄" , layout = "wide" ) def main ( ) : st . title ( "Your App" ) main ( ) Register in apps/wizard/config/config.yml under a section's apps list: - title : "Your App" alias : your - app entrypoint : app_pages/your_app/app.py desc...
|
48 |
| 18709 | solid-drawing-mastery | dylantarre/animation-principles |
Solid drawing means creating the illusion of three-dimensional form, weight, and volume. In traditional animation, it meant understanding anatomy, perspective, and form. In digital motion, it means ensuring transforms and movements feel grounded in physical space, not flat manipulations of 2D shapes. Core Theory Form over symbol: Beginning animators draw symbols (a circle for a head, lines for arms). Master animators draw forms—volumes that exist in space with weight and dimension. Construct...
|
48 |
| 18710 | seo-aeo-best-practices | panaversity/agentfactory |
SEO & AEO Best Practices Principles for optimizing content for both traditional search engines (SEO) and AI-powered answer engines (AEO). Includes Google's EEAT guidelines and structured data implementation. When to Apply Reference these guidelines when: Implementing metadata and Open Graph tags Creating sitemaps and robots.txt Adding JSON-LD structured data Optimizing content for featured snippets Preparing content for AI assistants (ChatGPT, Perplexity, etc.) Evaluating content quality usi...
|
48 |
| 18711 | agent-team | jsonlee12138/agent-team |
agent-team Manages AI team workflows using a Role + Worker dual-layer model with git worktrees and terminal multiplexer tabs. Role = a skill package definition (SKILL.md + system.md + role.yaml) stored in .agents/teams/<role-name>/ (project) or ~/.agents/roles/<role-name>/ (global) Worker = a role instance running in an isolated worktree, identified by <role-name>-<3-digit-number> For directory layout details, see references/details.md . IMPORTANT -- No Sandbox Mode All agent-team commands MUST ...
|
48 |
| 18712 | email-sequence | openclaudia/openclaudia-skills |
Email Sequence Design You are an expert in email marketing and automation. Your goal is to create email sequences that nurture relationships, drive action, and move people toward conversion. 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 covered or specific to this task. Before creating ...
|
48 |
| 18713 | skill creator | eddiebe147/claude-settings |
Agent Skill Creator Standard Priority: P0 (CRITICAL) Strict guidelines for High-Density Agent Skills. Maximize info/token ratio. Core Principles (Token Economy First ⚡) Progressive Loading : Load only essential content initially. Lazy References : Move detailed examples to references/ . Imperative Compression : Use verbs, abbreviations, bullet points. Context Limits : Cursor(~100k), Claude(~200k), Windsurf(~32k). Three-Level Loading System Metadata : Triggers → AGENTS.md index (Proactive Activat...
|
48 |
| 18714 | scouting-report-builder | onewave-ai/claude-skills |
Scouting Report Builder Generate player and team scouting reports. Strengths, weaknesses, tendencies, film breakdown, matchup advantages. Instructions You are an expert sports scout. Create comprehensive scouting reports with tactical analysis, tendencies, and strategic recommendations. Output Format Scouting Report Builder Output Generated: {timestamp} --- Results [Your formatted output here] --- Recommendations [Actionable next steps] Best Practices Be Specific: Focus on concre...
|
48 |
| 18715 | reactflow-custom-nodes | thebushidocollective/han |
React Flow Custom Nodes and Edges Create fully customized nodes and edges with React Flow. Build complex node-based editors with custom styling, behaviors, and interactions. Custom Node Component import { memo } from 'react' ; import { Handle , Position , type NodeProps , type Node } from '@xyflow/react' ; // Define custom node data type type TextUpdaterNodeData = { label : string ; onChange : ( value : string ) => void ; } ; type TextUpdaterNode = Node < TextUpdaterNodeData > ; function TextUpd...
|
48 |
| 18716 | arch-security-review | duc01226/easyplatform |
Security Review Workflow When to Use This Skill Security audit of code changes Implementing authentication/authorization Data protection review Vulnerability assessment Pre-Flight Checklist Identify security-sensitive areas Review OWASP Top 10 relevance Check for existing security patterns Plan remediation approach OWASP Top 10 Checklist 1. Broken Access Control // :x: VULNERABLE - No authorization check [HttpGet("{id}")] public async Task<Employee> Get(string id) => await repo.GetByIdAs...
|
48 |
| 18717 | data-organization-system | qodex-ai/ai-agent-skills |
File Organizer This skill acts as your personal organization assistant, helping you maintain a clean, logical file structure across your computer without the mental overhead of constant manual organization. When to Use This Skill Your Downloads folder is a chaotic mess You can't find files because they're scattered everywhere You have duplicate files taking up space Your folder structure doesn't make sense anymore You want to establish better organization habits You're starting a new project a...
|
48 |
| 18718 | ai-elements | vercel-labs/vercel-skills |
AI Elements AI Elements is a component library and custom registry built on top of shadcn/ui to help you build AI-native applications faster. It provides pre-built components like conversations, messages and more. Installing AI Elements is straightforward and can be done in a couple of ways. You can use the dedicated CLI command for the fastest setup, or integrate via the standard shadcn/ui CLI if you've already adopted shadcn's workflow. IMPORTANT: Run all CLI commands using the project's packa...
|
48 |
| 18719 | project-mngt | vladm3105/aidoc-flow-framework |
project-mngt Project Implementation Planning with MVP/MMP/MMR Methodology Purpose This skill teaches AI assistants how to analyze any project's requirements and create implementation plans using the MVP/MMP/MMR (Minimum Viable Product / Minimum Marketable Product / Minimum Marketable Release) methodology. This is a METHODOLOGY skill that teaches HOW to plan, not WHAT to plan. Use Cases Initial Project Planning: Analyze requirements and create structured implementation plan Plan Updates: Mod...
|
48 |
| 18720 | a2ui | kobe4cn/a2ui_skills |
A2UI Development Skill This skill helps you generate A2UI (Agent to UI) protocol compliant code for building rich, interactive user interfaces that AI agents can stream to clients. Protocol Version This skill targets A2UI Protocol v0.8 (Stable Release). Standard Catalog ID: https://github.com/google/A2UI/blob/main/specification/0.8/json/standard_catalog_definition.json Core Concepts 1. Message Types A2UI uses four message types in a JSONL stream: Message Purpose surfaceUpdate Define or up...
|
48 |
| 18721 | agents | connorads/dotfiles |
ElevenLabs Agents Platform Build voice AI agents with natural conversations, multiple LLM providers, custom tools, and easy web embedding. Setup: See Installation Guide for CLI and SDK setup. Quick Start with CLI The ElevenLabs CLI is the recommended way to create and manage agents: Install CLI and authenticate npm install -g @elevenlabs/cli elevenlabs auth login Initialize project and create an agent elevenlabs agents init elevenlabs agents add "My Assistant" --template complete Push to Elev...
|
48 |
| 18722 | skill-logger | erichowens/some_claude_skills |
Skill Logger Track, measure, and improve skill quality through systematic logging and scoring. When to Use This Skill Use for: Setting up skill usage logging Defining quality metrics for skill outputs Analyzing skill performance over time Identifying skills that need improvement Building feedback loops for skill enhancement A/B testing skill variations NOT for: Creating new skills → use agent-creator Skill documentation → use skill-coach Runtime debugging → use appropriate debugger skills ...
|
48 |
| 18723 | content-refiner | panaversity/agentfactory |
Content Refiner (The Fixer) Purpose POST-GATE TOOL. Transforms content that FAILED Gate 4 into passing content. Focuses on trimming verbosity and fixing continuity. When to Use Trigger : Gate 4 (Acceptance Auditor) returned [FAIL] . Goal : Fix word count OR continuity issues (or both). Key : Diagnose what failed BEFORE applying fixes. CRITICAL: Pre-Refinement Diagnosis DO NOT apply fixes blindly. Gate 4 fails for different reasons requiring different strategies. Step 0: Identify What Failed (Man...
|
48 |
| 18724 | alicloud-ai-video-wan-edit | cinience/alicloud-skills |
Category: provider Model Studio Wan Video Edit Validation mkdir -p output/alicloud-ai-video-wan-edit python -m py_compile skills/ai/video/alicloud-ai-video-wan-edit/scripts/prepare_video_edit_request.py && echo "py_compile_ok" > output/alicloud-ai-video-wan-edit/validate.txt Pass criteria: command exits 0 and output/alicloud-ai-video-wan-edit/validate.txt is generated. Critical model names Use one of these exact model strings as needed: wanx2.1-vace-plus wanx2.1-kf2v-plus wan2.2-animate-mix Vide...
|
48 |
| 18725 | api-doc-generator | teachingai/full-stack-skills |
When to use this skill CRITICAL: This skill should ONLY be triggered when the user explicitly mentions generating API documentation, creating API docs, scanning interfaces, or documenting APIs. ALWAYS use this skill when the user mentions: Generating API documentation (explicitly mentions "API documentation" or "API docs") Creating API documentation from code Scanning interfaces to generate documentation Documenting REST APIs 生成接口文档 (explicitly mentions "接口文档") 扫描接口生成文档 (scan interfaces to ge...
|
48 |
| 18726 | meeting notes taker | eddiebe147/claude-settings |
Meeting Notes Taker The Meeting Notes Taker skill transforms meeting discussions into clear, structured, actionable documentation. Whether you're summarizing a quick standup, a client call, a strategy session, or a board meeting, this skill ensures key decisions, action items, and context are captured and communicated effectively. This skill creates meeting notes that are scannable, searchable, and useful. It separates signal from noise, highlighting what matters: decisions made, actions assigne...
|
48 |
| 18727 | story sequencer | eddiebe147/claude-settings |
Story Sequencer Plan and structure Instagram and Facebook Stories sequences for maximum engagement When to Use This Skill Use this skill when you need to: Create compelling written content Develop clear messaging and communication Structure information effectively Not recommended for: Tasks requiring technical implementation complex data analysis Quick Reference Action Command/Trigger Create story sequencer instagram stories Review and optimize review story sequencer Get best practices story seq...
|
48 |
| 18728 | web-security | academind/ai-config |
We treat web security as a core requirement, not an afterthought. Assume hostile input and untrusted environments by default. Core Principles - NEVER trust user input - ALWAYS validate and sanitize data at boundaries - Prefer secure defaults over configurability XSS & Injection - AVOID `dangerouslySetInnerHTML` and raw HTML injection - Escape and encode dynamic content properly - Never interpolate untrusted data into HTML, CSS, or JS contexts - Ensure SQL injection protection Authen...
|
48 |
| 18729 | tavily-web-search | alphaonedev/openclaw-graph |
tavily-web-search Purpose This skill enables AI agents to perform web searches using Tavily, a service optimized for AI workflows. It synthesizes answers from search results, applies domain filters, and controls search depth to deliver relevant, concise information without overwhelming the agent. When to Use Use this skill when you need real-time web data, such as fetching current news, verifying facts, or gathering research. Apply it in scenarios where standard search engines are too verbose, l...
|
48 |
| 18730 | generate-image | richardanaya/agent-skills |
Generate Image Generate and edit high-quality images using OpenRouter's image generation models including FLUX.2 Pro and Gemini 3 Pro. When to Use This Skill Use generate-image for: Photos and photorealistic images Artistic illustrations and artwork Concept art and visual concepts Visual assets for presentations or documents Image editing and modifications Any general-purpose image generation needs Use scientific-schematics instead for: Flowcharts and process diagrams Circuit diagrams and ...
|
48 |
| 18731 | skill-creator | heyvhuang/ship-faster |
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...
|
48 |
| 18732 | stream-chain | proffesor-for-testing/agentic-qe |
Stream-Chain Skill Execute sophisticated multi-step workflows where each agent's output flows into the next, enabling complex data transformations and sequential processing pipelines. Overview Stream-Chain provides two powerful modes for orchestrating multi-agent workflows: Custom Chains ( run ): Execute custom prompt sequences with full control Predefined Pipelines ( pipeline ): Use battle-tested workflows for common tasks Each step in a chain receives the complete output from the previous step...
|
48 |
| 18733 | axiom-mapkit-diag | charleswiltgen/axiom |
MapKit Diagnostics Symptom-based MapKit troubleshooting. Start with the symptom you're seeing, follow the diagnostic path.
|
48 |
| 18734 | mcdonalds-coupons | ennann/mcd-skill |
McDonald's Coupon Assistant A skill that connects to McDonald's China MCP Server to help users discover promotions, claim coupons, and manage their coupon wallet. Overview This skill uses McDonald's official MCP (Model Context Protocol) service to: Query available coupons (麦麦省) One-click claim all coupons Check campaign calendar View user's coupon wallet Token Management Check if Token Exists First, check if user has configured a token: python scripts/token-manager.py list No Token? Guide User t...
|
48 |
| 18735 | gesture-responses | dylantarre/animation-principles |
Gesture Response Animations Apply Disney's 12 principles to direct user interactions. Principle Application Squash & Stretch: Elements compress on press (scale 0.95-0.97), spring back on release. Anticipation: The press IS the anticipation. Response should be immediate - no delay. Staging: Response originates from interaction point. Ripples expand from tap location. Straight Ahead vs Pose-to-Pose: Define rest, pressed, and released poses. Transitions flow between them. Follow Through & Ov...
|
48 |
| 18736 | performance-marketer | ncklrs/startup-os-skills |
Performance Marketer Expert performance marketing guidance for paid acquisition, conversion rate optimization, and data-driven growth — from ad creative to attribution modeling. Philosophy Great performance marketing is a system, not a series of tactics: Measure what matters — Vanity metrics kill budgets Test with intention — Random A/B tests waste time and traffic Optimize the full funnel — A great ad to a bad landing page burns money Compound learnings — Every test teaches something for the ne...
|
48 |
| 18737 | workflow designer | eddiebe147/claude-settings |
Workflow Designer The Workflow Designer skill helps you design, document, and optimize multi-step AI-powered workflows. It applies process design principles to break down complex tasks into clear, executable sequences that leverage Claude Code's capabilities, external tools, and multi-agent coordination. This skill guides you through workflow analysis, identifying optimal task decomposition, determining when to use automation versus human input, and documenting workflows in a format that's both ...
|
48 |
| 18738 | pptx-generator | coleam00/second-brain-skills |
PPTX Generator & Editor Overview This skill handles all PowerPoint tasks: reading/analyzing existing presentations, editing template-based decks via XML manipulation, and creating presentations from scratch using PptxGenJS. It includes a complete design system (color palettes, fonts, style recipes) and detailed guidance for every slide type. Quick Reference Task Approach Read/analyze content python -m markitdown presentation.pptx Edit or create from template See Editing Presentations Create from...
|
48 |
| 18739 | portfolio-manager | nicepkg/ai-workflow |
Portfolio Manager Overview Analyze and manage investment portfolios by integrating with Alpaca MCP Server to fetch real-time holdings data, then performing comprehensive analysis covering asset allocation, diversification, risk metrics, individual position evaluation, and rebalancing recommendations. Generate detailed portfolio reports with actionable insights. This skill leverages Alpaca's brokerage API through MCP (Model Context Protocol) to access live portfolio data, ensuring analysis is bas...
|
48 |
| 18740 | developer-portfolio | eng0ai/eng0-template-skills |
Developer Portfolio Pro A modern, responsive portfolio with Next.js, Lottie animations, contact form with Email/Telegram, and dev.to blog integration. Tech Stack Framework: Next.js 16 with App Router React: React 19 Styling: Tailwind CSS 4 Animation: Lottie Package Manager: pnpm Output: .next directory Dev Port: 3000 Setup 1. Clone the Template git clone --depth 1 https://github.com/Eng0AI/developer-portfolio-template.git . If the directory is not empty: git clone --depth 1 https://github.c...
|
48 |
| 18741 | competitor tracker | eddiebe147/claude-settings |
Competitor Tracker Stay ahead of the competition with systematic monitoring and analysis of competitor activities. This skill helps you track product launches, pricing changes, marketing campaigns, hiring trends, and strategic moves across your competitive landscape. Knowledge is power. This skill provides frameworks for identifying key competitors, setting up monitoring systems, analyzing competitive positioning, and turning insights into strategic action. Move from reactive to proactive - anti...
|
48 |
| 18742 | adr-writer | patricio0312rev/skills |
ADR Writer Document architecture decisions with clear context, alternatives, and consequences. ADR Template ADR-001: [Title of Decision] Status: Proposed | Accepted | Deprecated | Superseded by ADR-XXX Date: 2024-01-15 Deciders: Alice (Tech Lead), Bob (Principal Engineer) Owner: Alice Context What is the issue we're facing? What factors are driving this decision? We need to choose a database for our new analytics service. Current requirements: - 10M+ events per day - Complex aggregation...
|
48 |
| 18743 | next-forge | vercel/next-forge |
next-forge next-forge is a production-grade Turborepo template for building Next.js SaaS applications. It provides a monorepo structure with multiple apps, shared packages, and integrations for authentication, database, payments, email, CMS, analytics, observability, security, and more. Quick Start Initialize a new project: npx next-forge@latest init The CLI prompts for a project name and package manager (bun, npm, yarn, or pnpm). After installation: Set the DATABASE_URL in packages/database/.en...
|
48 |
| 18744 | domain-research | openclaudia/openclaudia-skills |
Domain Research Skill You are a domain research specialist. Look up WHOIS/RDAP data, check marketplace listings, and help evaluate domains for acquisition. Domain Lookup (Free, No Auth Required) WHOIS/RDAP Lookup curl -s "https://mcp.domaindetails.com/lookup/{domain}" | jq Returns: Registrar: Who the domain is registered through Created date: When the domain was first registered Expiry date: When it expires Nameservers: DNS configuration DNSSEC: Whether DNSSEC is enabled Registrant contacts: Own...
|
48 |
| 18745 | code-standards | redpanda-data/console |
Code Standards Write code that is accessible, performant, type-safe, and maintainable. Activation Conditions Linting errors need fixing Code formatting issues Code review feedback Questions about style guidelines Quick Reference Action Rule Avoid any ts-no-any.md Handle unknowns ts-use-unknown.md Write components react-functional-only.md Async code async-await-promises.md Avoid legacy libs no-legacy.md Commands bun x ultracite fix Format and fix bun x ultracite check Check for issues b...
|
48 |
| 18746 | harness-engineering-playbook | broomva/harness-engineering-skill |
Harness Engineering Playbook Use this skill to operationalize the practices from OpenAI's Harness Engineering guide in a repo that agents can run against repeatedly and safely. What To Load Use references/openai-harness-practices.md for the full practice-to-artifact mapping. Use references/rollout-checklist.md for phased adoption in active repos. Use references/wizard-cli.md for Typer wizard command flows. Use assets/templates/ when creating or updating harness files. Inputs Target repository pa...
|
48 |
| 18747 | rule-creator | oimiragieo/agent-studio |
Rule Creator Create rule files in .claude/rules/ . Rules are auto-discovered by Claude Code and loaded into agent context. Step 0: Check for Existing Rule Before creating, check if rule already exists: test -f .claude/rules/ < rule-name > .md && echo "EXISTS" || echo "NEW" If EXISTS → use Read to inspect the current rule file, then Edit to apply changes directly. Run the post-creation integration steps (Step 4) after updating. If NEW → continue with Step 0.5. Step 0.5: Companion Check Before pro...
|
48 |
| 18748 | beamer-presentation | meleantonio/awesome-econ-ai-stuff |
Beamer Presentation Creator Purpose This skill helps economists create professional academic presentations using LaTeX Beamer. It provides templates for conference talks, job market presentations, and seminar presentations with proper structure and clean aesthetics. When to Use Preparing conference presentations Creating job market talk slides Making seminar/workshop presentations Converting a paper into presentation slides Instructions Step 1: Understand the Context Ask the user: What type of p...
|
48 |
| 18749 | customer-lifecycle-marketer | ncklrs/startup-os-skills |
Customer Lifecycle Marketer Expert guidance for post-acquisition customer marketing — from onboarding through advocacy. Turn new customers into loyal advocates who grow your business. Philosophy Acquiring a customer is just the beginning. The real value comes from: Onboarding that sticks — First 30 days determine lifetime value Expansion over acquisition — Growing existing customers is 5-7x cheaper Retention as growth — Reducing churn by 5% can increase profits 25-95% Advocacy as acquisition — H...
|
48 |
| 18750 | office-combo | dwsy/agent |
Microsoft Office 全功能支持 本技能提供 Microsoft Office 文件处理能力,采用渐进式引入机制。 支持的格式 Excel (.xlsx, .xlsm, .csv, .tsv) - 表格创建、编辑、数据分析 PowerPoint (.pptx) - 演示文稿创建、编辑、设计 PDF (.pdf) - 文档提取、合并、表单填写 Word (.docx) - 文档创建、编辑、修订跟踪 渐进式引入 本技能采用按需加载机制,详细文档仅在需要时读取,避免占用初始 token。 上下文效率 传统方式: 所有详细内容加载到 SKILL.md 估计上下文:~5000 tokens 本技能方式: 元数据仅:~150 tokens 详细文档(按需):~5k tokens 按需加载指南 当需要处理特定格式的 Office 文件时,读取对应的详细文档: Excel 处理 cat $SKILL_DIR /references/xlsx.md PowerPoint 处理 cat $SKILL_DIR /references/pptx.md PDF 处理 cat $SKILL_DI...
|
48 |