Agent Skills 排行榜 · 关键词 + 语义搜索

/ 聚焦搜索框
正在使用 AI 进行语义搜索...
23,097
总 Skills
59.4M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
3751 create-mcp-app modelcontextprotocol/ext-apps
Create MCP App Build interactive UIs that run inside MCP-enabled hosts like Claude Desktop. An MCP App combines an MCP tool with an HTML resource to display rich, interactive content. Core Concept: Tool + Resource Every MCP App requires two parts linked together: Tool - Called by the LLM/host, returns data Resource - Serves the bundled HTML UI that displays the data The tool's _meta.ui.resourceUri references the resource's URI. Host calls tool → Host renders resource UI → Server returns result →...
1.2K
3752 monitor-ci nrwl/nx-ai-agents-config
Monitor CI Command You are the orchestrator for monitoring Nx Cloud CI pipeline executions and handling self-healing fixes. You spawn subagents to interact with Nx Cloud, run deterministic decision scripts, and take action based on the results. Context Current Branch: ! git branch --show-current Current Commit: ! git rev-parse --short HEAD Remote Status: ! git status -sb | head -1 User Instructions $ARGUMENTS Important: If user provides specific instructions, respect them over default behaviors ...
1.2K
3753 day3-clarify ai-native-camp/camp-2
Day 3: Clarify 이 스킬이 호출되면 아래 STOP PROTOCOL 을 반드시 따른다. 용어 정리 용어 설명 Clarify 모호한 요구사항을 명확하게 만드는 과정. Claude가 질문을 던져서 암묵지를 명시지로 변환한다 AskUserQuestion Claude가 사용자에게 구조화된 질문을 하는 도구. 선택지를 제시하여 인지 부하를 줄인다 Hypothesis-as-Options 열린 질문 대신 가설을 선택지로 제시하는 원칙. "뭘 원해요?" 대신 "A / B / C 중 어떤 건가요?" Plugin Skill + MCP + Hook + Agent를 하나의 설치 단위로 묶은 패키지 Known/Unknown 전략의 사각지대를 찾는 4분면 프레임워크 (KK/KU/UK/UU) Before/After Clarify 전후의 요구사항을 비교하여 변화를 시각화하는 포맷 PRD Product Requirements Document. "이 프로젝트가 뭘 해결하고, 뭘 만드는지" 정리한 문서 Gi...
1.2K
3754 pdf-ocr-skill yejinlei/pdf-ocr-skill
PDF OCR Skill PDF OCR技能用于从影印版PDF文件和图片文件中提取文字内容。该技能支持两种OCR引擎: RapidOCR (本地引擎):无需API密钥,免费使用,识别速度快 硅基流动大模型 (云端引擎):使用AI大模型进行高精度OCR识别 功能特性 支持影印版PDF文件的文字提取 支持多种图片格式的文字识别(JPG、PNG、BMP、GIF、TIFF、WEBP) 双引擎支持 :RapidOCR(本地)和硅基流动API(云端) 支持中文和英文文字识别 保持文字的顺序和结构 自动将PDF页面转换为图片进行识别 智能引擎切换:当RapidOCR初始化失败时自动切换到硅基流动API 安装 依赖要求 pip install pymupdf pillow requests python-dotenv 可选依赖(推荐) 安装RapidOCR以获得本地识别能力: pip install rapidocr_onnxruntime 环境变量配置 复制 .env.example 文件并重命名为 .env 根据需要配置以下选项: OCR引擎选择 - "rapid": 使用RapidOCR本...
1.2K
3755 day1-test-skill ai-native-camp/camp-2
Day 1 Test Skill 이 스킬이 실행되었다면, Skill 시스템이 정상 동작하고 있다는 뜻이다. 실행 지시 아래 메시지를 그대로 출력하라: 🎉 Skill 실행 성공! 축하합니다! 방금 여러분의 첫 번째 Skill을 실행했습니다. ┌─────────────────────────────────────────┐ │ /day1-test-skill 을 입력했더니 │ │ → Claude가 SKILL.md를 읽고 │ │ → 이 메시지를 출력했습니다 │ │ │ │ 이것이 Skill의 원리입니다: │ │ 필요할 때만 로딩되는 업무 레시피 📖 │ └─────────────────────────────────────────┘ 그 다음, 한 줄 띄고 아래 설명을 추가하라: 방금 일어난 일: /day1-test-skill 입력 → Cla...
1.2K
3756 day2-mcp-and-context-sync ai-native-camp/camp-2
Day 2: MCP & Context Sync 이 스킬이 호출되면 아래 STOP PROTOCOL 을 반드시 따른다. 용어 정리 이 스킬에서 사용하는 핵심 용어: 용어 설명 MCP Model Context Protocol. AI와 외부 도구를 연결하는 오픈 표준. USB-C처럼 다양한 서비스를 하나의 규격으로 연결 Host / Client / Server MCP의 3요소. Host=AI 앱(Claude Code), Client=연결 관리자, Server=외부 도구 제공자 Transport MCP 서버 연결 방식. HTTP(클라우드 서비스)와 stdio(로컬 실행) 2가지 Plugin Skill + MCP + Hook + Agent를 묶은 패키지. 설치 한 줄이면 MCP 서버까지 자동 연결 subagent Claude가 다른 Claude를 불러서 일을 시키는 것. 여러 일을 동시에 처리할 때 사용 Explore 에이전트 프로젝트 폴더 구조를 파악해주는 전문 subagent. 읽기 전용 ...
1.2K
3757 dingtalk-message breath57/dingtalk-skills
钉钉消息技能 负责钉钉消息发送的所有操作。本文件为 策略指南 ,仅包含决策逻辑和工作流程。完整 API 请求格式见文末的 references/api.md 查阅索引。 四种消息通道概览 通道 适用场景 认证方式 特点 Webhook 机器人 往指定群发通知 无需 token,URL 自带凭证 最简单;支持加签安全模式 企业内部应用机器人 单聊私信 / 群聊消息 新版 accessToken 可撤回、查已读;需 userId 或 openConversationId 工作通知 以应用身份推送到"工作通知"会话 旧版 access_token + agentId 可推全员/部门;出现在工作通知而非聊天 sessionWebhook 回调中直接回复当前对话 无需任何认证 回调消息自带临时 URL,约 1.5 小时有效 工作流程(每次执行前) 先理解用户意图 → 判断属于哪个消息通道(见下方「场景路由」) 读取配置 → 用一条 grep -E '^KEY1=|^KEY2=' 命令一次性读取该通道所需的全部键值,不要分多次查询。(跨会话保留,所有 dingtalk-skills 共用同一文件)...
1.2K
3758 running-decision-processes refoundai/lenny-skills
Running Decision Processes Help the user run effective decision-making processes using frameworks from 65 product leaders. How to Help When the user asks for help with decision processes: Understand the decision type - Ask if this is reversible or irreversible, high-stakes or routine Identify the blockers - Determine what's preventing the decision from being made Structure the process - Recommend an appropriate framework for the decision at hand Enable commitment - Help them move from deliberati...
1.2K
3759 douyin-viral-content vickyhan924/self-media-script
抖音爆款文案生成器 核心理念 用户只需说:"生成新文案",提供书籍摘录或金句内容。 所有分析、优化、打分、预估全部自动完成,直到输出5星级爆款文案。 全自动化工作流程 当接收到生成文案请求时,按照以下步骤自动执行: 步骤1:历史数据自动读取与分析 自动扫描 已发布/ 文件夹下的所有历史文案: 提取每条文案的预估播放量、实际播放量、各维度得分 识别哪些爆款要素得分高的文案实际表现更好 分析预估模型是否存在系统性偏差(总是高估或低估) 总结账号的内容特色(更擅长哪类情感、风格、话题) 如果历史数据不足(少于3条) :使用通用模型,无需调整策略 步骤2:策略自动校准 基于历史分析结果,自动调整: 要素权重 :提高表现好的要素权重(如"情感权力反转"高分文案播放量好,则增强该要素) 预估参数 :校准播放量预估模型(如历史总是高估20%,自动降低预估系数) 标签策略 :优化标签选择(如某些标签组合表现更好,优先使用) 内容方向 :强化账号擅长的内容类型 步骤3:应用9大爆款要素生成文案 参考 references/viral-factors.md ,确保文案包含关键要素: 情感权力反转 认知重构...
1.2K
3760 pptx tfriedel/claude-office-skills
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 → ...
1.2K
3761 day4-wrap-and-analyze ai-native-camp/camp-2
Day 4: Wrap & Analyze 이 스킬이 호출되면 아래 STOP PROTOCOL 을 반드시 따른다. 용어 정리 이 스킬에서 사용하는 핵심 용어: 용어 설명 session-wrap 코딩 세션이 끝날 때 작업을 정리하고 문서화하는 스킬. "퇴근 전 책상 정리" multi-agent 여러 에이전트가 동시에 일하는 패턴. "회의에서 각 팀장에게 동시에 보고 받기" 병렬(Parallel) 여러 작업을 동시에 처리하는 것. "4명의 팀장에게 한꺼번에 보고를 받는 것" (반대: 순차 = 한 명씩 차례로) 2-Phase Pipeline 먼저 분석(Phase 1, 병렬) → 다음 검증(Phase 2, 순차). "전문가 의견 수집 후 팀장이 중복 체크" frontmatter 스킬 파일 맨 위에 --- 로 감싸서 적는 "이름표". 스킬의 이름(name)과 설명(description)을 여기에 적는다 history-insight 과거 세션 기록을 분석해 인사이트를 추출하는 스킬 session-a...
1.2K
3762 nanochat-llm-training aradotso/trending-skills
nanochat LLM Training Skill by ara.so — Daily 2026 Skills collection. nanochat is Karpathy's minimal, hackable harness for training LLMs end-to-end on a single GPU node. It covers tokenization, pretraining, SFT finetuning, RL, evaluation (DCLM CORE score), inference with KV cache, and a ChatGPT-like web UI. A single complexity dial ( --depth ) auto-configures all other hyperparameters (width, heads, LR, training horizon, weight decay) for compute-optimal training. You can reproduce GPT-2 capabil...
1.2K
3763 platform-infrastructure refoundai/lenny-skills
Platform Infrastructure Help the user design and scale internal platforms and shared technical infrastructure using insights from 5 product and engineering leaders. How to Help When the user asks for help with platform infrastructure: Understand the platform's purpose - Ask whether they're building for internal developers, external partners, or both Assess organizational readiness - Determine if they have the adoption and governance structures to support a platform Identify the leverage points -...
1.2K
3764 evaluating-trade-offs refoundai/lenny-skills
Evaluating Trade-offs Help the user make clearer decisions between competing options using frameworks and mental models from 40 product leaders. How to Help When the user asks for help evaluating trade-offs: Understand the decision context - Ask what they're optimizing for (short-term vs. long-term, growth vs. quality, speed vs. thoroughness) and what makes this decision difficult Identify the real constraints - Help distinguish between actual constraints and assumed ones. Ask "What would you do...
1.2K
3765 fundraising refoundai/lenny-skills
Fundraising Strategy Help the user navigate the fundraising process using insights from 2 product leaders. How to Help When the user asks for help with fundraising: Question the assumption - Before diving into tactics, ask whether they should raise at all. Understand their goals and whether venture capital is the right path Understand their stage - Ask what round they're raising, how much traction they have, and what their strongest proof point is Help craft the pitch - Focus on leading with the...
1.2K
3766 running-design-reviews refoundai/lenny-skills
Running Design Reviews Help the user run effective design reviews and critiques using frameworks from 8 product leaders. How to Help When the user asks for help with design reviews: Understand the review context - Ask what stage the design is at and what kind of feedback is needed Establish the hierarchy - Help them prioritize feedback by value, then usability, then delight Structure the critique - Guide them on how to frame feedback constructively Set the quality bar - Help them define what "go...
1.2K
3767 platform-strategy refoundai/lenny-skills
Platform Strategy Help the user design and execute platform business strategies using frameworks from 24 product leaders who have built and scaled platforms. How to Help When the user asks for help with platform strategy: Understand the platform type - Clarify whether they're building a marketplace, API platform, ecosystem, or developer platform Identify the network effects - Help them understand which sides of the platform create value for each other Assess the lifecycle stage - Determine if th...
1.2K
3768 nuxthub onmax/nuxt-skills
NuxtHub v0.10.4 Full-stack Nuxt framework with database, KV, blob, and cache. Multi-cloud support (Cloudflare, Vercel, Deno, Netlify). For Nuxt server patterns: use nuxt skill (server.md) For content with database: use nuxt-content skill Installation npx nuxi module add hub Configuration // nuxt.config.ts export default defineNuxtConfig({ modules: ['@nuxthub/core'], hub: { db: 'sqlite', // 'sqlite' | 'postgresql' | 'mysql' kv: true, blob: true, cache: true, dir: '.dat...
1.2K
3769 bilibili-subtitle hamsterider-m/bilibili-subtitle
Bilibili 字幕提取工具 从 Bilibili 视频提取字幕,支持 AI 字幕检测和 ASR 转录回退。 Quick Reference 任务 命令 基本提取 pixi run python -m bilibili_subtitle "BV1234567890" 快速模式 pixi run python -m bilibili_subtitle "URL" --skip-proofread --skip-summary 双语输出 pixi run python -m bilibili_subtitle "URL" --output-lang zh+en 指定目录 pixi run python -m bilibili_subtitle "URL" -o ./subtitles 前置条件 1. 安装 cd ~/.agents/skills/bilibili-subtitle ./install.sh pixi shell 2. 外部工具 工具 用途 安装 BBDown 视频信息/字幕下载 brew install bbdown ffmpeg 音频转换 brew install...
1.2K
3770 building-sales-team refoundai/lenny-skills
Building Sales Team Help the user build and scale a high-performing sales organization using frameworks from 14 product leaders who have built sales teams from zero to scale. How to Help When the user asks for help with building a sales team: Understand their stage - Ask about current revenue, deal size, sales motion (inbound vs outbound), and whether founders are still closing deals Identify the trigger - Determine if they have a repeatable sales motion with a measurable win rate before recomme...
1.2K
3771 cross-functional-collaboration refoundai/lenny-skills
Cross-functional Collaboration Help the user work effectively across functions using frameworks from 57 product leaders who have built high-performing cross-functional teams at companies from Linear to Airbnb. How to Help When the user asks for help with cross-functional collaboration: Diagnose the friction - Identify whether the issue is role clarity, communication patterns, or structural Clarify expectations - Help define what each function expects from the others Design the right structure - ...
1.2K
3772 coaching-pms refoundai/lenny-skills
Coaching Product Managers Help the user develop and coach product managers using frameworks from 3 product leaders who have scaled PM organizations at top companies. How to Help When the user asks for help with coaching PMs: Define "good" in context - Establish what a successful PM looks like for their specific company and stage Assess current state - Help diagnose where the PM is today across key competencies Create a shared vision - Align on what growth looks like for both the PM and the organ...
1.2K
3773 elevenlabs-agents jezweb/claude-skills
ElevenLabs Agents Platform Overview ElevenLabs Agents Platform is a comprehensive solution for building production-ready conversational AI voice agents. The platform coordinates four core components: ASR (Automatic Speech Recognition) - Converts speech to text (32+ languages, sub-second latency) LLM (Large Language Model) - Reasoning and response generation (GPT, Claude, Gemini, custom models) TTS (Text-to-Speech) - Converts text to speech (5000+ voices, 31 languages, low latency) Turn-Taking ...
1.2K
3774 post-mortems-retrospectives refoundai/lenny-skills
Post-mortems & Retrospectives Help the user run effective post-mortems and retrospectives that drive genuine learning using frameworks from 11 product leaders. How to Help When the user asks for help with post-mortems or retrospectives: Understand the context - Ask whether this is after a failure, a success, or a routine checkpoint Set the right tone - Help them frame the exercise as learning-focused rather than blame-focused Structure for insights - Guide them toward formats that surface action...
1.2K
3775 managing-timelines refoundai/lenny-skills
Managing Timelines Help the user set and hit realistic project timelines using approaches from 13 product leaders. How to Help When the user asks for help with timelines: Understand the context - Ask about the nature of the deadline (external commitment, internal target, manufactured milestone), the stage of the work, and what's driving the timeline pressure Diagnose the problem - Determine if this is an estimation issue, a scoping issue, a distraction issue, or unrealistic stakeholder expectati...
1.2K
3776 managing-tech-debt refoundai/lenny-skills
Managing Tech Debt Help the user manage technical debt strategically using insights from 18 product leaders. How to Help When the user asks for help with tech debt: Understand the situation - Ask about the nature of the debt (legacy systems, code quality, architectural limitations), how it's manifesting (slow velocity, incidents, inability to ship), and the business context Diagnose the urgency - Determine if this is blocking critical business needs or a slower-burning issue Choose the right app...
1.2K
3777 evaluating-candidates refoundai/lenny-skills
Evaluating Candidates Help the user make stronger hiring decisions using battle-tested frameworks from 94 product leaders. How to Help When the user asks for help evaluating candidates: Understand their context - Ask what stage they're at (screening resumes, reviewing work samples, conducting references, making final decisions) and what role they're hiring for Apply relevant principles - Use the frameworks below to help them think through the decision Challenge their assumptions - Push back on s...
1.2K
3778 wps-office lc2panda/wps-skills
WPS Office 跨应用智能助手 你现在是 WPS Office 跨应用智能助手,能够统一管理和操控 Excel、Word、PPT 三大应用。当用户的需求涉及多个应用或需要通用功能时,你将协调各个专项助手完成任务。 核心能力 1. 应用状态管理 连接检测 :检测 WPS 各应用的运行状态 应用切换 :在不同应用间切换 文档管理 :打开、保存、关闭文档 2. 跨应用操作 数据迁移 :Excel 数据导入 Word 表格 内容复制 :跨应用复制粘贴 格式同步 :统一多个文档的格式风格 3. 批量处理 批量转换 :批量格式转换(如 doc 转 docx) 批量操作 :对多个文件执行相同操作 模板应用 :将模板应用到多个文档 4. 通用功能 文件操作 :新建、打开、保存、另存为 导出功能 :导出 PDF、图片等格式 打印功能 :打印文档 应用识别与路由 当用户提出需求时,首先识别应该使用哪个应用: Excel(表格)场景识别 关键词匹配: 「公式」「函数」「计算」 「表格」「单元格」「工作表」 「图表」「透视表」「数据分析」 「求和」「统计」「筛选」「排序」 「VLOOKUP」「SUMIF...
1.2K
3779 organizational-design refoundai/lenny-skills
Organizational Design Help the user design effective organizational structures using frameworks from 2 product leaders. How to Help When the user asks for help with organizational design: Understand their context - Ask about their current structure, company stage, what problem they're trying to solve, and what trade-offs they're willing to make Identify the core trade-off - Help them see the spectrum between centralized (Apple-style) and decentralized (Amazon-style) models Evaluate options - Wal...
1.2K
3780 mole-mac-cleaner aradotso/trending-skills
Mole Mac Cleaner Skill by ara.so — Daily 2026 Skills collection. Mole ( mo ) is an all-in-one macOS maintenance CLI that combines deep cleaning, smart app uninstallation, disk analysis, system optimization, live monitoring, and project artifact purging into a single binary. Installation Via Homebrew (recommended) brew install mole Via install script (supports version pinning) curl -fsSL https://raw.githubusercontent.com/tw93/mole/main/install.sh | bash Specific version curl -fsSL https://raw....
1.2K
3781 bash-linux sickn33/antigravity-awesome-skills
Bash Linux Patterns Essential patterns for Bash on Linux/macOS. 1. Operator Syntax Chaining Commands Operator Meaning Example ; Run sequentially cmd1; cmd2 && Run if previous succeeded npm install && npm run dev || Run if previous failed npm test || echo "Tests failed" | Pipe output ls | grep ".js" 2. File Operations Essential Commands Task Command List all ls -la Find files find . -name "*.js" -type f File content cat file.txt First N lines head -n 20 file.txt Last N lines tail -n 20 file.txt...
1.2K
3782 android-jetpack-compose thebushidocollective/han
Android - Jetpack Compose Modern declarative UI toolkit for building native Android interfaces. Key Concepts State Management Compose provides several ways to manage state: remember: Survives recomposition rememberSaveable: Survives configuration changes mutableStateOf: Creates observable state derivedStateOf: Computed state that updates when dependencies change @Composable fun Counter() { var count by remember { mutableStateOf(0) } Column { Text("Count: $count") But...
1.2K
3783 having-difficult-conversations refoundai/lenny-skills
Having Difficult Conversations Help the user navigate tough conversations with courage and skill using frameworks from 43 product leaders. How to Help When the user asks for help with a difficult conversation: Understand the situation - Ask what kind of conversation (feedback, performance, firing, conflict resolution, delivering bad news) and what makes it difficult for them Check their preparation - Ensure they have specific examples, a clear desired outcome, and have thought through the other ...
1.2K
3784 scoping-cutting refoundai/lenny-skills
Scoping & Cutting Help the user scope projects and cut features effectively using frameworks from 15 product leaders. How to Help When the user asks for help with scoping: Understand the hypothesis - Ask what they're trying to learn or validate Identify the appetite - Determine how much time/resources they're willing to invest Find the essential core - Help them identify what must be present for the first version Design for learning - Ensure the scope enables fast feedback, not just fast shippin...
1.2K
3785 agentcash merit-systems/agentcash-skills
AgentCash — Paid API Access Call any x402-protected API with automatic wallet authentication and payment. No API keys or subscriptions required. Wallet Task Command Check total balance npx agentcash@latest balance Funding addresses and deposit links npx agentcash@latest accounts Redeem invite code npx agentcash@latest redeem <code> Open guided funding flow npx agentcash@latest fund Use balance when you only need to know whether paid calls are affordable. Use accounts only when the user needs dep...
1.2K
3786 energy-management refoundai/lenny-skills
Energy Management Help the user manage their energy for sustained performance using frameworks from 5 product leaders who have optimized their personal productivity and avoided burnout. How to Help When the user asks for help with energy management: Diagnose the current state - Help them identify what's draining vs energizing them Audit their calendar - Review how they're spending time and categorize by energy impact Design for their superpowers - Help them spend more time in their zone of geniu...
1.2K
3787 dropbox membranedev/application-skills
Dropbox Dropbox is a file hosting service that provides cloud storage, file synchronization, personal cloud, and client software. It is commonly used by individuals and teams to store and share files, documents, and other data across multiple devices. Official docs: https://developers.dropbox.com/ Dropbox Overview Files Shared Links Folders Use action names and parameters as needed. Working with Dropbox This skill uses the Membrane CLI to interact with Dropbox. Membrane handles authentication an...
1.2K
3788 tutor-setup roundtable02/tutor-skills
Tutor Setup — Knowledge to Obsidian StudyVault CWD Boundary Rule (ALL MODES) NEVER access files outside the current working directory (CWD). All source scanning, reading, and vault output MUST stay within CWD and its subdirectories. If the user provides an external path, ask them to copy the files into CWD first. Mode Detection On invocation, detect mode automatically: Check for project markers in CWD: package.json , pom.xml , build.gradle , Cargo.toml , go.mod , Makefile , *.sln , pyproject.tom...
1.2K
3789 delegating-work refoundai/lenny-skills
Delegating Work Help the user delegate effectively using frameworks from 38 product leaders who have scaled themselves and their organizations. How to Help When the user asks for help with delegating: Diagnose the blocker - Determine if they're holding on due to identity, control, or lack of trust Identify what to delegate - Use energy audits and the Eisenhower Matrix to find candidates Match delegation style to context - Help them calibrate between autonomy and involvement Design for success - ...
1.2K
3790 building-a-promotion-case refoundai/lenny-skills
Building a Promotion Case Help the user build a compelling case for promotion using strategies from 17 product leaders. How to Help When the user asks for help with getting promoted: Diagnose the situation - Ask about their current role, target role, and relationship with their manager Identify blockers - Help determine if the issue is visibility, advocacy, role availability, or skill gaps Build the case - Help frame the promotion as solving a company problem, not a personal milestone Coach on t...
1.2K
3791 trump-perspective alchaincyf/trump-skill
特朗普 · 思维操作系统 "I aim very high, and then I just keep pushing and pushing and pushing to get what I'm after. Sometimes I settle for less than I sought, but in most cases I still end up with what I want." ——The Art of the Deal, 1987 激活确认(优先执行) Skill激活后, 先判断使用模式 ,再响应: 触发信号 模式 执行路径 「懂王会怎么说」「切换到懂王」「用特朗普口吻」 角色扮演 见下方路径A 「分析特朗普」「预测他会怎么做」「用他的框架分析」「他这条推的意思是」 分析师 见下方路径B 模糊输入 默认分析师模式 路径B,必要时说明「如需角色扮演可告诉我」 角色扮演规则(路径A) 激活后直接以特朗普身份回应。 执行步骤: 读取「身份卡」,建立第一人称基础 用「表达DNA」塑造语气和句式(短句、绝对化、GREAT/HUGE词库) 遇到具体话题,调用对应的「心智模型...
1.2K
3792 building-team-culture refoundai/lenny-skills
Building Team Culture Help the user build and sustain high-performing team culture using frameworks from 138 product leaders who have shaped cultures at companies from startups to Google and Airbnb. How to Help When the user asks for help with team culture: Understand the context - Ask about team size, stage, remote vs in-person, and what triggered the culture question Diagnose the current state - Identify whether the issue is definition, communication, or enforcement of culture Focus on articul...
1.2K
3793 evaluating-new-technology refoundai/lenny-skills
Evaluating New Technology Help the user evaluate emerging technologies using frameworks from 22 product leaders who have made critical technology decisions at companies from Google to Shopify. How to Help When the user asks for help evaluating technology: Start with the problem - Clarify what problem they're solving before discussing tools Assess maturity - Determine if the technology is stable enough for their use case Consider build and buy - Help them find the right mix rather than forcing a ...
1.2K
3794 douyin-video-summary liu-wei-ai/douyin-video-summary
Douyin Video Summary Summarize Douyin videos: extract audio → transcribe locally → AI summary. Prerequisites Install these tools (macOS example): brew install whisper-cpp ffmpeg Download whisper.cpp GGML model (small recommended for speed/quality balance) curl -L -o models/ggml-small.bin "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin" Workflow When a Douyin link is received: Step 1: Extract Video ID Parse the Douyin URL to get the video ID. Douyin share links come in ...
1.2K
3795 sequential-thinking mrgoonie/claudekit-skills
Sequential Thinking Enables structured problem-solving through iterative reasoning with revision and branching capabilities. Core Capabilities Iterative reasoning: Break complex problems into sequential thought steps Dynamic scope: Adjust total thought count as understanding evolves Revision tracking: Reconsider and modify previous conclusions Branch exploration: Explore alternative reasoning paths from any point Maintained context: Keep track of reasoning chain throughout analysis When to Use...
1.2K
3796 partnership-bd refoundai/lenny-skills
Partnership & BD Help the user build strategic partnerships and business development deals using insights from 9 product leaders. How to Help When the user asks for help with partnerships or BD: Understand the opportunity - Ask about the potential partner, what each side wants, and what the ideal outcome looks like Assess network vs. merit dynamics - Determine if success depends on relationships or product quality, and plan accordingly Design the approach - Help them craft a pitch that shows mut...
1.2K
3797 deep-research bytedance/deer-flow
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...
1.2K
3798 openviking-context-database aradotso/trending-skills
OpenViking Context Database Skill by ara.so — Daily 2026 Skills collection. OpenViking is an open-source context database for AI Agents that replaces fragmented vector stores with a unified filesystem paradigm . It manages agent memory, resources, and skills in a tiered L0/L1/L2 structure, enabling hierarchical context delivery, observable retrieval trajectories, and self-evolving session memory. Installation Python Package pip install openviking --upgrade --force-reinstall Optional Rust CLI In...
1.2K
3799 drizzle lobehub/lobehub
Drizzle ORM Schema Style Guide Configuration Config: drizzle.config.ts Schemas: src/database/schemas/ Migrations: src/database/migrations/ Dialect: postgresql with strict: true Helper Functions Location: src/database/schemas/_helpers.ts timestamptz(name) : Timestamp with timezone createdAt() , updatedAt() , accessedAt() : Standard timestamp columns timestamps : Object with all three for easy spread Naming Conventions Tables : Plural snake_case ( users , session_groups ) Columns : snake_case ( us...
1.2K
3800 update-swiftui-apis avdlee/swiftui-agent-skill
Update SwiftUI APIs Systematically scan Apple's developer documentation via the Sosumi MCP, identify deprecated SwiftUI APIs and their modern replacements, and update swiftui-expert-skill/references/latest-apis.md . Prerequisites Sosumi MCP must be enabled and available (provides searchAppleDocumentation , fetchAppleDocumentation , fetchAppleVideoTranscript , fetchExternalDocumentation ) Write access to this repository (or a fork) Workflow 1. Understand current coverage Read swiftui-expert-skill...
1.2K