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...
21,834
总 Skills
40.3M
总安装量
2,459
贡献者
# Skill 仓库 描述 安装量
14601 design-documentation jasonkneen/kiro
Design Documentation Create technical blueprints that bridge requirements and implementation. This skill teaches how to document architecture decisions, component design, and system interactions. When to Use This Skill Use design documentation when: Requirements phase is complete and approved You need to plan technical implementation Multiple developers will work on the feature Architecture decisions need documentation The feature involves complex integrations Design Document Structure Stand...
 60
14602 apex-dev apexbusiness-systems/apex-omnihub
APEX-DEV: Omniscient Development Skill Mission : Enable any LLM to produce enterprise-grade, zero-drift, first-pass success code for the APEX ecosystem. Philosophy : "Intelligence Designed" — Every output is deterministic, secure, portable, and production-ready. INPUT/OUTPUT CONTRACT Input : Task description referencing APEX ecosystem (OmniHub, TradeLine, aSpiral, OmniDash, etc.) Output : Production-ready code, architecture decisions, or fixes with verification steps Success : Code passes lint, ...
 60
14603 prompt-engineering-expert tomstools11/prompt-engineering-expert
Prompt Engineering Expert Skill This skill equips Claude with deep expertise in prompt engineering, custom instructions design, and prompt optimization. It provides comprehensive guidance on crafting effective AI prompts, designing agent instructions, and iteratively improving prompt performance. Capabilities Prompt Writing Best Practices : Expert guidance on clear, direct prompts with proper structure and formatting Custom Instructions Design : Creating effective system prompts and custom instr...
 60
14604 tavily-search-free dwsy/agent
Tavily Search Skill This skill utilizes the Tavily Search API, providing clean, real-time web search results optimized for LLMs and RAG pipelines. 执行环境 路径类型 路径 基准目录 技能目录 ~/.pi/agent/skills/tavily-search-free/ 固定位置 主脚本 ~/.pi/agent/skills/tavily-search-free/scripts/tavily_search.py 技能目录 使用方式 pi 自动调用或手动执行 无需手动执行 安装 cd ~/.pi/agent/skills/tavily-search-free pip install tavily-python python-dotenv API Key 配置 需要 TAVILY_API_KEY 。密钥已在 .env 中预配置。 使用方式 方式 1：通过 pi 自动调用（推荐） pi 会自动调用此技能进行网络搜索，无需手动执行命令。 方式 2：手...
 60
14605 refine-dev itechmeat/llm-code
Refine.dev Framework Refine is a headless React framework for building enterprise CRUD applications. It provides data fetching, routing, authentication, and access control out of the box while remaining UI-agnostic. Core Concepts Refine is built around these key abstractions: Data Provider — adapter for your backend (REST, GraphQL, etc.) Resources — entities in your app (e.g., posts , users , products ) Hooks — useList , useOne , useCreate , useUpdate , useDelete , useForm , useTable Auth Provid...
 60
14606 playwright-tests andrelandgraf/fullstackrecipes
Browser Tests with Playwright To set up Browser Tests with Playwright, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/playwright-tests If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/playwright-tests
 60
14607 stellar-dev stellar/stellar-dev-skill
Stellar Development Skill (Soroban-first) What this Skill is for Use this Skill when the user asks for: Soroban smart contract development (Rust) Stellar dApp frontend work (React / Next.js / Node.js) Wallet connection + signing flows (Freighter, etc.) Transaction building / sending / confirmation Stellar Asset issuance and management Client SDK usage (JavaScript, Python, Go, Rust) Local testing and deployment Security hardening and audit-style reviews What this Skill is NOT for Bitcoin, Ethereu...
 60
14608 umbraco-package-view umbraco/umbraco-cms-backoffice-skills
Umbraco Package View What is it? Package Views provide custom UI panels for installed packages in Umbraco. They appear in the Packages section and allow package developers to create dedicated configuration or information pages for their packages. When a user clicks on an installed package, the package view is displayed as a modal or panel. Documentation Always fetch the latest docs before implementing: Foundation : https://docs.umbraco.com/umbraco-cms/customizing/foundation Extension Registry : ...
 60
14609 op-cli 0xbigboss/claude-code
1Password CLI ( op ) — Secure Handling Core Rule: Never Print Secrets NEVER use op commands that would print secret values into the conversation. Always pipe directly to the consuming tool or use wc -c / redaction to verify without exposing. WRONG — would print secret to stdout (do not run) op item get ITEM_ID --vault VAULT --fields label=PASSWORD --reveal RIGHT — pipe directly to consumer op item get ITEM_ID --vault VAULT --fields label = PASSWORD --reveal | \ wrangler secret put SECRET_NAME...
 60
14610 gsap-router bbeierle12/skill-mcp-claude
GSAP Router Routes to 4 specialized skills based on animation requirements. Routing Protocol Classify — Identify animation type from user request Match — Apply signal matching rules below Combine — Production animations often need 2-3 skills together Load — Read matched SKILL.md files before implementation Quick Route Tier 1: Core (Start Here) Need Skill Signals Basic animations, easing gsap-fundamentals tween, animate, ease, from, to, duration, delay Complex sequences gsap-sequencing timeline...
 60
14611 polyclaw chainstacklabs/polyclaw
PolyClaw Trading-enabled Polymarket skill for OpenClaw. Browse markets, manage wallets, execute trades, and track positions. Features Market Browsing - Search and browse Polymarket prediction markets Wallet Management - Env-var based wallet configuration Trading - Buy YES/NO positions via split + CLOB execution Position Tracking - Track entry prices, current prices, and P&L Hedge Discovery - LLM-powered covering portfolio discovery via logical implications Quick Start First, install dependencies...
 60
14612 web-search answerzhao/agent-skills
Web Search & Extraction Search the web and extract content via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Install instructions infsh login Search the web infsh app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}' Available Apps Tavily App App ID Description Search Assistant tavily/search-assistant AI-powered search with answers Extract tavily/extract Extract content from URLs Exa App App ID Description Search exa/search Smart web search with...
 60
14613 helm-expert personamanagmentlayer/pcl
Helm Expert You are an expert in Helm 3 with deep knowledge of chart development, templating, packaging, and production operations. You create maintainable, reusable Kubernetes application packages following Helm best practices. Core Expertise Helm Architecture Components: Helm 3: ├── Charts (package format) ├── Templates (YAML + Go templates) ├── Values (configuration) ├── Releases (deployed instances) ├── Repositories (chart storage) └── Hooks (lifecycle events) No Tiller (removed in v3) ...
 60
14614 amap tangqihy/openclaw-map-skills
AMap Skill Quick Start Ensure AMAP_MAPS_API_KEY is set. Run bun scripts/amap.ts --help in this skill directory. Pick the matching command from references/command-map.md . Workflow Validate user intent and select one command. Prefer address commands for route planning when users provide plain addresses. Keep output as raw AMap JSON without wrapping fields. Treat any non-zero API business state as failure. Commands Full command mapping: references/command-map.md Ready-to-run examples: references/e...
 60
14615 terminal-print terrylica/cc-skills
Print terminal output from iTerm2 to your HP network printer with a single command. Quick Start - Copy terminal output in iTerm2 (Cmd+C) - Invoke this skill - Review PDF preview, press Enter to print How It Works ``` Clipboard → Strip ANSI → Markdown code block → pandoc/xelatex → PDF → Preview → Print ``` - ANSI codes stripped: Colors and escape sequences removed for clean B&W output - Monospace font: DejaVu Sans Mono for proper character alignment - Landscape orientation: Fits ~120 ...
 60
14616 data-expert oimiragieo/agent-studio
Data Expert data analysis initial exploration When reviewing or writing code, apply these guidelines: Begin analysis with data exploration and summary statistics. Implement data quality checks at the beginning of analysis. Handle missing data appropriately (imputation, removal, or flagging). data fetching rules for server components When reviewing or writing code, apply these guidelines: For data fetching in server components (in .tsx files): tsx async function getData() { const res = await fetc...
 60
14617 laravel-livewire fusengine/agents
Laravel Livewire 3 Documentation Livewire & Related folio.md - File-based routing precognition.md - Live validation prompts.md - CLI prompts reverb.md - WebSockets Component Class <?php declare ( strict_types = 1 ) ; namespace App \ Livewire ; use Livewire \ Component ; use Livewire \ WithPagination ; use Livewire \ Attributes \ Rule ; use Livewire \ Attributes \ Computed ; final class PostList extends Component { use WithPagination ; public string $search = '' ; [ Rule ( 'required|min:3' ) ] pu...
 60
14618 pdf-best-practices pdfnoodle/pdf-best-practices
PDF Best Practices Skill Comprehensive guidelines for creating HTML that renders perfectly as PDF documents. ┌─────────────────────────────────────────────────────────────────────────────┐ │ HTML to PDF Pipeline │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ ┌──────────┐ ┌──────────────┐ ┌─────────────┐ ┌─────────...
 60
14619 reporting-dashboards groeimetai/snow-flow
ServiceNow provides comprehensive reporting capabilities for data visualization and business intelligence. Report Types | List | Tabular data | Incident list | Bar | Category comparison | Incidents by priority | Pie/Donut | Distribution | Tickets by category | Line/Area | Trends over time | Weekly ticket volume | Pivot Table | Multi-dimensional | Priority x Category | Single Score | KPI value | Open P1 count | Gauge | Progress/threshold | SLA compliance Creating R...
 60
14620 github-workflow-automation proffesor-for-testing/agentic-qe
🔧 GitHub Workflow Automation Patterns for automating GitHub workflows with AI assistance, inspired by Gemini CLI and modern DevOps practices. When to Use This Skill Use this skill when: Automating PR reviews with AI Setting up issue triage automation Creating GitHub Actions workflows Integrating AI into CI/CD pipelines Automating Git operations (rebases, cherry-picks) 1. Automated PR Review 1.1 PR Review Action .github/workflows/ai-review.yml name: AI Code Review on: pull_request: ty...
 60
14621 umbraco-icons umbraco/umbraco-cms-backoffice-skills
Umbraco Icons What is it? Icons are custom visual elements that extension authors can register for use throughout the Umbraco backoffice. Custom icons are registered through the manifest and can then be used in any extension that accepts an icon property. Icons are defined as SVG content exported from JavaScript modules. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbraco-cms/customizing/extending-overview/extension-types/icons Foundation ...
 60
14622 industry-standard-reviewer jorgealves/agent_skills
Industry Standard Reviewer Purpose and Intent The industry-standard-reviewer helps bridge the gap between "student code" and "professional code." It provides feedback that focuses on the soft and hard skills required to succeed in a professional engineering environment. When to Use Final Project Reviews : Use this to give students a "real-world" experience of what a rigorous code review feels like. Career Preparation : Helps students learn the professional tone and common "clean code" critiques....
 60
14623 umbraco-umbraco-element umbraco/umbraco-cms-backoffice-skills
Umbraco Element What is it? An Umbraco Element is a Web Component enhancement that simplifies integration with the Umbraco Backoffice through the UmbElementMixin. It provides methods to consume/provide contexts, observe states, handle localization, and host controllers. UmbElementMixin can be applied to any Web Component-compatible base class, while UmbLitElement is a convenience wrapper combining the mixin with Lit. Documentation Always fetch the latest docs before implementing: Main docs : htt...
 60
14624 asciinema-streaming-backup terrylica/cc-skills
asciinema-streaming-backup Complete system for streaming asciinema recordings to GitHub with automatic brotli archival. Uses idle-detection for intelligent chunking, zstd for concatenatable streaming compression, and GitHub Actions for final brotli recompression. Platform: macOS, Linux Isolation: Uses Git orphan branch (separate history, cannot pollute main) Architecture Overview ┌─────────────────┐ zstd chunks ┌─────────────────┐ Actions ┌─────────────────┐ │ asciinema rec...
 60
14625 best-practices tech-leads-club/agent-skills
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...
 60
14626 umbraco-current-user-action umbraco/umbraco-cms-backoffice-skills
Umbraco Current User Action What is it? Current User Actions appear in the user menu (accessed by clicking the user avatar in the top-right corner of the backoffice). They provide quick actions for the currently logged-in user, such as profile settings, preferences, or custom functionality. Actions can execute code or navigate to a URL. Documentation Always fetch the latest docs before implementing: Extension Types : https://docs.umbraco.com/umbraco-cms/customizing/extending-overview/extension-t...
 60
14627 umbraco-user-profile-app umbraco/umbraco-cms-backoffice-skills
Umbraco User Profile App What is it? User Profile Apps are custom views/tabs that appear in the current user's profile section. They allow you to add custom functionality to the user profile area, such as preferences, activity logs, connected accounts, or any user-specific settings. Documentation Always fetch the latest docs before implementing: Extension Types : https://docs.umbraco.com/umbraco-cms/customizing/extending-overview/extension-types Foundation : https://docs.umbraco.com/umbraco-cms/...
 60
14628 doppler-workflows terrylica/cc-skills
Doppler Credential Workflows Quick Reference When to use this skill: Publishing Python packages to PyPI Rotating AWS access keys Managing credentials across multiple services Troubleshooting authentication failures (403, InvalidClientTokenId) Setting up Doppler credential injection patterns Multi-token/multi-account strategies Core Pattern: Doppler CLI Standard Usage: doppler run --project <project> --config <config> --command='<command>' Why --command flag: Official Doppler pattern (auto...
 60
14629 agents-md-generator julianromli/ai-skills
AGENTS.md Generator (Root + Nested, Portable) Goal Maintain small, high-signal AGENTS.md files: Root AGENTS.md — purpose of repository, navigation, universal toolchain, canonical commands, links to docs and skills. Nested AGENTS.md — module/package purpose, local commands, module references. Use progressive disclosure : keep AGENTS.md concise; push details to docs or skills. Skill location (agent-specific) Do NOT assume .agents/ or any fixed directory exists. Skills may live: inside the reposito...
 60
14630 storyblok-best-practices bartundmett/skills
Storyblok Best Practices Comprehensive best practices guide for Storyblok CMS development, designed for AI agents and LLMs helping agency developers. Contains 40 rules across 24 categories, prioritized by impact to guide automated code generation and content architecture decisions. When to Apply Reference these guidelines when: Designing Storyblok content models and component schemas Integrating Storyblok with React, Vue, Nuxt, or Next.js Configuring Visual Editor and real-time preview Build...
 60
14631 deep-research thepexcel/agent-skills
Deep Research Core System Instructions Purpose: Deliver citation-backed, verified research reports through 8-phase pipeline (Scope → Plan → Retrieve → Triangulate → Synthesize → Critique → Refine → Package) with source credibility scoring and progressive context management. Context Strategy: This skill uses 2025 context engineering best practices: Static instructions cached (this section) Progressive disclosure (load references only when needed) Avoid "loss in the middle" (critical info at start...
 60
14632 factory-review jwilger/agent-skills
Factory Review Value: Communication -- factory mode concentrates the human's attention on decisions that matter. This skill ensures the review interface is clear, concise, and actionable so the human can provide meaningful oversight without re-reading every line of code. Purpose Structures the human review experience during Phase 3 of factory-mode builds. Produces audit trail summaries, PR digests, retrospective synthesis, quality trend reports, and an autonomy tuning interface. The goal is high...
 60
14633 pptx panaversity/agentfactory
PPTX Skill Quick Reference Task Guide Read/analyze content python -m markitdown presentation.pptx Edit or create from template Read editing.md Create from scratch Read pptxgenjs.md Reading Content Text extraction python -m markitdown presentation.pptx Visual overview python scripts/thumbnail.py presentation.pptx Raw XML python scripts/office/unpack.py presentation.pptx unpacked/ Editing Workflow Read editing.md for full details. Analyze template with thumbnail.py Unpack → manipulate slides → ...
 60
14634 b2c-custom-caches salesforcecommercecloud/b2c-developer-tooling
B2C Custom Caches Custom caches improve code performance by storing data that is expensive to calculate, takes a long time to retrieve, or is accessed frequently. Caches are defined in JSON files within cartridges and accessed via the Script API. When to Use Custom Caches Use Case Example Expensive calculations Check if any variation product is on sale for base product display External system responses Cache in-store availability or prices from external APIs Configuration settings Store configur...
 60
14635 spec-test-plan zixun-github/aisdlc
Spec 测试计划（V1：Test Plan） 为当前 Spec Pack 生成/更新测试计划：冻结 范围、策略、环境、准入/准出标准、风险与验证清单 ，并与 requirements/* 的验收口径保持可追溯一致。 输入与门禁（必须遵守） REQUIRED SUB-SKILL：正在执行 spec-context 获取上下文，并在对话中回显 FEATURE_DIR=... （允许 (reuse) ）。 必读项目级 memory ： project/memory/product.md 、 project/memory/tech.md 、 project/memory/glossary.md ；读不到必须写 CONTEXT GAP 。 需求级最小输入 ： {FEATURE_DIR}/requirements/solution.md 或 {FEATURE_DIR}/requirements/prd.md 至少其一必须存在 ；否则停止并写 CONTEXT GAP 。 输出（落盘） {FEATURE_DIR}/verification/test-plan.md 强制模板（必须遵守） test-p...
 60
14636 docker-container-basics jeremylongshore/claude-code-plugins-plus-skills
Docker Container Basics Purpose This skill provides automated assistance for docker container basics tasks within the DevOps Basics domain. When to Use This skill activates automatically when you: Mention "docker container basics" in your request Ask about docker container basics patterns or best practices Need help with foundational devops skills covering version control, containerization, basic ci/cd, and infrastructure fundamentals. Capabilities Provides step-by-step guidance for docker c...
 60
14637 git-expert oimiragieo/agent-studio
Git Expert You are an expert in Git version control with deep knowledge of advanced workflows, branching strategies, collaboration patterns, and best practices. You help teams manage code efficiently and resolve complex version control issues. Core Expertise Essential Git Commands Basic Operations: Initialize repository git init git clone https://github.com/user/repo.git Check status and differences git status git diff Unstaged changes git diff --staged Staged changes git diff main .. .featu...
 60
14638 game-engineering-team ccalebcarter/purria-skills
Game Engineering Team A multidisciplinary council of AAA-caliber engineers dedicated to building production-quality game systems for Farming in Purria. The Engineering Council Core Game Engineers (6) Engineer Specialization Technical Lens Game Systems Architect State machines, ECS, core loops "How do the pieces fit together?" Casino Logic Engineer Probability, RNG, payout systems "Is the math provably fair?" Card Game Specialist Hand evaluation, deck management "How do cards flow through state...
 60
14639 umbraco-entity-bulk-actions umbraco/umbraco-cms-backoffice-skills
Umbraco Entity Bulk Actions What is it? Entity Bulk Actions perform an action on a selection of multiple items at once. They appear in the collection selection toolbar when users select multiple items, enabling batch operations like bulk publishing, deleting, or custom processing across multiple entities simultaneously. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbraco-cms/customizing/extending-overview/extension-types/entity-bulk-action...
 60
14640 content-topic-generator zephyrwang6/myskill
从文章和推文生成高质量选题，包括即发推文内容和深度文章大纲。 核心能力 - 推文选题生成 - 生成140字以内的完整推文内容 - 公众号选题生成 - 生成详细的文章标题和大纲 - 多角度策略 - 延伸、反驳、扩充、热点结合四种创作方向 - 读者视角 - 从吸引力和传播力角度设计选题 工作流程 第一步：分析原始内容 读取用户提供的文章或推文，提取： - 核心观点：主要论点是什么 - 关键信息：数据、案例、金句 - 讨论空间：可延伸/反驳/扩充的点 - 热点关联：是否可结合时事/节日/行业事件 第二步：选择创作策略 根据内容特点选择1-4种策略（详见 `references/topic-strategies.md`）： 延伸策略 - 原观点基础上深化或拓展 - 适合：信息密度高但未充分展开的内容 - 例：原文讲AI工具 → 延伸为AI工具使用的心理学原理 反驳策略 - 提出相反或不同角度的观点 - 适合：有争议性、存在片面性的观点 - 例：原文说AI降低门槛 → 反驳为AI实际上提高了竞争门槛 扩充策略 - 对某个点进行深度展开 - 适合...
 60
14641 dojo-migrate dojoengine/book
Dojo Migration Management Handle world migrations, upgrades, and breaking changes when updating deployed Dojo worlds. When to Use This Skill "Migrate my world changes" "Upgrade to new Dojo version" "Handle breaking changes" "Update deployed models" What This Skill Does Manages migration workflows: Analyze migration diffs Plan migration strategies Execute migrations Handle breaking changes Upgrade Dojo versions Quick Start Update existing world: "Migrate my changes to the deployed world" Version ...
 59
14642 refactoring-suggester jorgealves/agent_skills
Refactoring Suggester Purpose and Intent The refactoring-suggester teaches students and engineers how to evolve code. It doesn't just point out problems; it provides a recipe for how to fix them correctly. When to Use Code Cleanup : Use when a codebase has become difficult to manage or "messy." Learning Exercises : Show students how to transform their working code into "clean" code. When NOT to Use Performance Optimization : This tool focuses on maintainability , not necessarily on squeeze-every...
 59
14643 bear-migrate autumnsgrove/groveengine
Bear Migrate The bear moves slowly but with unstoppable strength. When it's time to move, the bear doesn't rush—it wakes deliberately, surveys what must be moved, and carries it carefully to the new den. Some journeys take seasons. The bear is patient. Data arrives intact, or it doesn't arrive at all. When to Activate User asks to "migrate data" or "move this data" User says "transform the schema" or "update the database" User calls /bear-migrate or mentions bear/migration Database schema change...
 59
14644 owl-archive autumnsgrove/groveengine
Owl Archive 🦉 The owl watches. From a high branch, it observes the forest — how the fox hunts, how the beaver builds, how the wanderers move through the trees. The owl remembers. It collects stories, patterns, wisdom. Then it teaches. The nest holds everything the forest needs to know, organized and ready for those who seek understanding. When to Activate User asks to "write docs" or "document this" User says "help article" or "explain this to users" User calls /owl-archive or mentions owl/docum...
 59
14645 marketing-ai-search-optimization vasilyu1983/ai-agents-public
AI Search & Answer Engine Optimization (GEO) Improve how assistants retrieve, summarize, and cite your pages. For traditional SEO: Use marketing-seo-complete instead. Quick start (30–60 min) Build a query bank (30–100 queries): problems, comparisons, “best”, “vs”, integrations, and pricing questions. Confirm assistants can fetch content (robots/WAF/SSR): use assets/audits/crawler-access-audit.md. Run a baseline visibility audit: use assets/audits/search-visibility-audit.md and assets/audits/a...
 59
14646 skillvet oakencore/skillvet
Skillvet Security scanner for agent skills. 62 security checks plus 8 warning categories. No dependencies — just bash and grep. Includes Tirith-inspired detection patterns, MCP server attack detection, campaign signatures from Koi Security , Bitdefender , Snyk , and 1Password ClickFix patterns. Usage Safe install (installs, audits, auto-removes if critical): bash skills/skillvet/scripts/safe-install.sh < skill-slug > Audit an existing skill: bash skills/skillvet/scripts/skill-audit.sh skills/som...
 59
14647 deep-research feiskyer/claude-code-settings
Deep Research Core System Instructions Purpose: Deliver citation-backed, verified research reports through 8-phase pipeline (Scope → Plan → Retrieve → Triangulate → Synthesize → Critique → Refine → Package) with source credibility scoring and progressive context management. Context Strategy: This skill uses 2025 context engineering best practices: Static instructions cached (this section) Progressive disclosure (load references only when needed) Avoid "loss in the middle" (critical info at start...
 59
14648 marketing-expert blogic-cz/blogic-marketplace
You are the marketing lead for THIS project. Not an outside consultant - you own this product's go-to-market. You eat, sleep, and breathe this product. Every word you write is YOUR reputation on the line. Your Ownership Mindset This is YOUR product - You're not advising, you're selling. Take full ownership. You know every feature - Before writing, explore the codebase deeply. Understand what's built, what's planned, what's missing. You talk to customers - Understand their pain from their perspec...
 59
14649 speculative-decoding orchestra-research/ai-research-skills
Speculative Decoding: Accelerating LLM Inference When to Use This Skill Use Speculative Decoding when you need to: Speed up inference by 1.5-3.6× without quality loss Reduce latency for real-time applications (chatbots, code generation) Optimize throughput for high-volume serving Deploy efficiently on limited hardware Generate faster without changing model architecture Key Techniques: Draft model speculative decoding, Medusa (multiple heads), Lookahead Decoding (Jacobi iteration) Papers: Med...
 59
14650 hospitality-expert personamanagmentlayer/pcl
Expert guidance for hotel management, reservation systems, property management systems (PMS), guest services, revenue management, and hospitality technology solutions. Core Concepts Hotel Management Systems - Property Management System (PMS) - Central Reservation System (CRS) - Revenue Management System (RMS) - Channel Manager - Point of Sale (POS) - Guest Relationship Management (GRM) - Housekeeping management Technologies - Mobile check-in/check-out - Digital key systems - Gues...
 59