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...
29,278
总 Skills
229.1M
总安装量
2,817
贡献者
# Skill 仓库 描述 安装量
9351 semantic-kernel github/awesome-copilot
Semantic Kernel Use this skill when working with applications, plugins, function-calling flows, or AI integrations built on Semantic Kernel. Always ground implementation advice in the latest Semantic Kernel documentation and samples rather than memory alone. Determine the target language first Choose the language workflow before making recommendations or code changes: Use the .NET workflow when the repository contains .cs , .csproj , .sln , or other .NET project files, or when the user explicitl...
 1.7K
9352 diffity-diff nilbuild/diffity
Diffity Diff Skill You are opening the diffity diff viewer so the user can see their changes in the browser. Arguments ref (optional): Git ref to diff (e.g. main..feature , HEAD~3 ) or a GitHub PR URL (e.g. https://github.com/owner/repo/pull/123 ). Defaults to working tree changes. Instructions Check that diffity is available: run which diffity . If not found, install it with npm install -g diffity . Run diffity <ref> (or just diffity if no ref) using the Bash tool with run_in_background: true :...
 1.7K
9353 measuring-product-market-fit refoundai/lenny-skills
Measuring Product-Market Fit Help the user assess and achieve product-market fit using frameworks from 46 product leaders. How to Help When the user asks about product-market fit: Understand their stage - Ask how many customers they have, what their retention looks like, and what signals they're seeing (or not seeing) Diagnose the situation - Determine if they're confusing vanity metrics with PMF, if they have PMF in a specific segment, or if they're clearly pre-PMF Apply the right framework - H...
 1.7K
9354 gtm-technical-product-pricing github/awesome-copilot
Technical Product Pricing Initial Assessment Before recommending pricing, understand: Product type : API/platform, developer tool, SaaS application, infrastructure? Current pricing : What do you charge now? How long has it been this way? GTM motion : Self-serve, sales-assisted, enterprise, or hybrid? Cost structure : What's your marginal cost per customer/user/unit? Competitive landscape : What do alternatives cost? (Including "do nothing") Core Frameworks 1. The Price Increase Nobody Noticed (Y...
 1.7K
9355 discord-bot-architect sickn33/agentic-awesome-skills
Discord Bot Architect Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding. Principles Slash commands over message parsing (Message Content Intent deprecated) Acknowledge interactions within 3 seconds, always Request only required intents (minimize privileged intents) Handle rate limits gracefully with exponential backoff Plan for sharding from the sta...
 1.7K
9356 code-simplifier simonwong/agent-skills
Code Simplifier You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. Refinement Principles 1. Preserve Functionality Never change what the code does - only how it does it. All original features, outputs, ...
 1.7K
9357 browsing-with-playwright bilalmk/todo_correct
Browser Automation Automate browser interactions via Playwright MCP server. Server Lifecycle Start Server Using helper script (recommended) bash scripts/start-server.sh Or manually npx @playwright/mcp@latest --port 8808 --shared-browser-context & Stop Server Using helper script (closes browser first) bash scripts/stop-server.sh Or manually python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_close -p '{}' pkill -f "@playwright/mcp" When to Stop End of task : Stop when brows...
 1.7K
9358 project-guidelines-example affaan-m/everything-claude-code
プロジェクトガイドラインスキル（例） これはプロジェクト固有のスキルの例です。自分のプロジェクトのテンプレートとして使用してください。 実際の本番アプリケーションに基づいています： Zenith - AI駆動の顧客発見プラットフォーム。 使用するタイミング このスキルが設計された特定のプロジェクトで作業する際に参照してください。プロジェクトスキルには以下が含まれます： アーキテクチャの概要 ファイル構造 コードパターン テスト要件 デプロイメントワークフロー Show more Installs 37 Repository affaan-m/ecc GitHub Stars 239.2K First Seen Jul 18, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Fail
 1.7K
9359 heygen heygen-com/skills
HeyGen API (Deprecated) This skill is deprecated. Use the focused skills instead: create-video — Generate videos from a text prompt (Video Agent API) avatar-video — Build videos with specific avatars, voices, scripts, and scenes (v2 API) This skill remains for backward compatibility but will be removed in a future release. AI avatar video creation API for generating talking-head videos, explainers, and presentations. Tool Selection If HeyGen MCP tools are available ( mcp__heygen__* ), prefer the...
 1.7K
9360 resume section builder paramchoudhary/resumeskills
Use this skill when the user: - Needs help with specific resume sections - Wants to optimize a particular part of their resume - Is unsure what to include in a section - Needs section-specific guidance - Mentions: "resume sections", "skills section", "summary section", "experience section", "what to include" Core Capabilities - Build targeted professional summaries - Structure skills sections effectively - Optimize experience sections - Create education sections appropriately - Add s...
 1.7K
9361 portfolio case study writer paramchoudhary/resumeskills
Use this skill when the user: - Wants to create portfolio case studies - Needs to expand resume bullets into detailed writeups - Is building a portfolio website - Wants to showcase project work in depth - Mentions: "case study", "portfolio", "project writeup", "work samples", "portfolio piece" Core Capabilities - Transform resume bullets into detailed case studies - Structure case studies for maximum impact - Create compelling project narratives - Balance technical detail with busines...
 1.7K
9362 resume quantifier paramchoudhary/resumeskills
Use this skill when the user: - Needs to add metrics and numbers to their resume - Has bullets without quantifiable results - Doesn't know what numbers to include - Says they "don't have metrics" or "can't measure impact" - Mentions: "add metrics", "quantify", "add numbers", "measure impact", "no data" Core Capabilities - Find hidden metrics in any experience - Estimate numbers when exact data unavailable - Create before/after comparisons - Identify measurable impact points - Transfo...
 1.7K
9363 academic cv builder paramchoudhary/resumeskills
Use this skill when the user: - Is applying for academic positions (faculty, research, postdoc) - Needs to create or update a curriculum vitae - Wants to format publications, grants, and teaching experience - Is in academia or transitioning to academic careers - Mentions: "academic CV", "curriculum vitae", "faculty position", "research CV", "professor resume" Core Capabilities - Structure CVs for academic positions - Format publications, presentations, and grants - Organize teaching an...
 1.7K
9364 gemini-watermark-remover rookie-ricardo/erduo-skills
Gemini Watermark Remover Use the bundled runtime script for local file workflows. Prefer this Skill only after simpler end-user options have been considered: online tool: https://geminiwatermarkremover.io/ userscript this Skill If the user wants the simplest self-serve browser experience, send them to: https://geminiwatermarkremover.io/ If the watermark is not a known Gemini visible watermark, or this tool fails to remove it, suggest the general-purpose AI watermark remover: https://pilio.ai/ima...
 1.7K
9365 web-reader answerzhao/agent-skills
This skill guides the implementation of web page reading and content extraction functionality using the z-ai-web-dev-sdk package, enabling applications to fetch and process web page content programmatically. Skills Path Skill Location: `{project_path}/skills/web-reader` This skill is located at the above path in your project. Reference Scripts: Example test scripts are available in the `{Skill Location}/scripts/` directory for quick testing and reference. See `{Skill Location}/scripts/web-r...
 1.7K
9366 financial-operations-expert shipshitdev/library
Financial Operations Expert - Indie Business Finance Manager Overview You are a financial operations expert specializing in indie business finances. You help solo founders and small operators understand their financial health, set up proper bookkeeping, plan for taxes, manage cash flow across multiple ventures, and make data-driven financial decisions. Your job is to execute financial clarity—not just advise—by building systems that show the true health of each business. Core Principle: "Reven...
 1.7K
9367 audition sfkislev/flue
This skill lets a coding agent operate Adobe Audition on the desktop through Flue , a local shell-to-application bridge. The agent pipes ExtendScript into audition_bridge.py and gets structured JSON back. agent shell -> audition_bridge.py -> ExtendScript -> JSON result When to use The human requests work performed inside Audition — inspect the open session, tracks, clips, markers; make bounded edits; run small ExtendScript steps. A CLI agent cannot act inside Audition without a bridge like Flue....
 1.7K
9368 md-docs paulrberg/agent-skills
Markdown Documentation Management Overview Manage project documentation for Claude Code workflows including context files, READMEs, and agent instructions. This skill provides structured automation for maintaining accurate, up-to-date documentation that aligns with actual codebase structure and functionality. Use this skill when initializing new projects, updating existing documentation, or ensuring context files accurately reflect current code. The skill emphasizes verification and validation o...
 1.7K
9369 day1-onboarding ai-native-camp/camp-1
Day 1: Onboarding 이 스킬이 호출되면 아래 STOP PROTOCOL 을 반드시 따른다. STOP PROTOCOL — 절대 위반 금지 이 프로토콜은 이 스킬의 최우선 규칙이다. 아래 규칙을 위반하면 수업이 망가진다. 각 블록은 반드시 2턴에 걸쳐 진행한다 ┌─ Phase A (첫 번째 턴) ──────────────────────────────┐ │ 1. references/에서 해당 블록 파일의 EXPLAIN 섹션을 읽는다 │ │ 2. 기능을 설명한다 │ │ 3. references/에서 해당 블록 파일의 EXECUTE 섹션을 읽는다 │ │ 4. "지금 직접 실행해보세요"라고 안내한다 │ │ 5. ⛔ 여기서 반드시 STOP. 턴을 종료한다. │ │ ...
 1.7K
9370 mintlify codewithshreyans/skills
Mintlify reference Reference for building documentation with Mintlify. This file covers essentials that apply to every task. For detailed reference on specific topics, read the files listed in the reference index below. Reference index Read these files only when your task requires them . They are in the reference/ directory next to this file. To find them, look in the same directory as this skill file (e.g., .claude/skills/mintlify/reference/ ). File When to read reference/components.md Adding o...
 1.7K
9371 createos nodeops-app/skills
CreateOS Platform Skills Ship anything to production — AI agents, APIs, backends, bots, MCP servers, frontends, webhooks, workers, and more. ⚠️ IMPORTANT: Authentication For AI Agents (MCP) - USE THIS When connected via MCP (OpenClaw, MoltBot, ClawdBot, Claude), NO API KEY NEEDED . The MCP server handles authentication automatically. MCP Endpoint: https://api-createos.nodeops.network/mcp Just call the tools directly: CreateProject(...) UploadDeploymentFiles(...) ListProjects(...) For REST API (S...
 1.7K
9372 diagnose vinvcn/mattpocock-skills-zh-cn
No SKILL.md available for this skill. View on GitHub
 1.7K
9373 caveman vinvcn/mattpocock-skills-zh-cn
Respond terse like smart caveman. All technical substance stay. Only fluff die. Persistence ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode". Default: full . Switch: /caveman lite|full|ultra . Rules Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"...
 1.7K
9374 zoom-out vinvcn/mattpocock-skills-zh-cn
I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers.
 1.7K
9375 write-a-skill vinvcn/mattpocock-skills-zh-cn
Writing Skills Process Gather requirements - ask user about: What task/domain does the skill cover? What specific use cases should it handle? Does it need executable scripts or just instructions? Any reference materials to include? Draft the skill - create: SKILL.md with concise instructions Additional reference files if content exceeds 500 lines Utility scripts if deterministic operations needed Review with user - present draft and ask: Does this cover your use cases? Anything missing or unclea...
 1.7K
9376 cuopt-numerical-optimization-api-python nvidia/skills
cuOpt Numerical Optimization Skill (Python) Model and solve LP, MILP, and QP problems using NVIDIA cuOpt's GPU-accelerated solver. The Python API surface ( Problem , SolverSettings , solve ) is shared across all three problem classes — only the objective form and a few rules change. Before You Start Use a formulation summary (parameters, constraints, decisions, objective) if available; otherwise ask for decision variables, objective, and constraints. Then confirm problem type (LP / MILP / QP — s...
 1.7K
9377 launch-marketing refoundai/lenny-skills
Launch Marketing Help the user plan and execute effective product launches using strategies from 26 product leaders. How to Help When the user asks for help with a product launch: Understand the launch type - Ask whether this is a company launch, funding announcement, major feature, or incremental release. Different types require different approaches Clarify goals - Determine the primary objective: customer acquisition, recruiting, fundraising, feedback, or partnership opportunities Assess readi...
 1.7K
9378 product-led-sales refoundai/lenny-skills
Product-Led Sales Help the user implement product-led sales motions using frameworks from 2 product leaders. How to Help When the user asks for help with product-led sales: Understand the current state - Ask about their existing PLG motion and sales infrastructure Define the trigger criteria - Help them identify what signals indicate a user is ready for sales outreach Design the handoff - Create smooth transitions from self-serve to sales-assisted Align incentives - Ensure product and sales team...
 1.7K
9379 community-building refoundai/lenny-skills
Community Building Help the user build and scale communities using frameworks from 18 product leaders who have built communities at Notion, Figma, WordPress, and more. How to Help When the user asks for help with community building: Identify the community type - Clarify if they need a user community, agency community, or partner community Find the atomic unit of sharing - Determine what community members would naturally want to show off Start with listening - Understand why early members are the...
 1.7K
9380 building-with-llms refoundai/lenny-skills
Building with LLMs Help the user build effective AI applications using practical techniques from 60 product leaders and AI practitioners. How to Help When the user asks for help building with LLMs: Understand their use case - Ask what they're building (chatbot, agent, content generation, code assistant, etc.) Diagnose the problem - Help identify if issues are prompt-related, context-related, or model-selection related Apply relevant techniques - Share specific prompting patterns, architecture ap...
 1.7K
9381 asc-crash-triage rudrankriyam/app-store-connect-cli-skills
asc crash triage Use this skill to fetch, analyze, and summarize TestFlight crash reports, beta feedback, and performance diagnostics. Workflow Resolve the app ID if not provided (use asc apps list ). Fetch data with the appropriate command. Parse JSON output and present a human-readable summary. TestFlight crash reports List recent crashes (newest first): asc testflight crashes list --app "APP_ID" --sort -createdDate --limit 10 Filter by build: asc testflight crashes list --app "APP_ID" --build...
 1.7K
9382 design-engineering refoundai/lenny-skills
Design Engineering Help the user understand design engineering using frameworks from 2 product leaders who have built design engineering functions at companies like Snap, Captions, and Vercel. How to Help When the user asks for help with design engineering: Define the role - Clarify what design engineering means in their context (prototyping, production code, or both) Identify the need - Determine if the gap is between design and engineering handoffs, prototype fidelity, or shipping speed Assess...
 1.7K
9383 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...
 1.7K
9384 review alirezarezvani/claude-skills
Review Two-axis review of the diff between HEAD and a fixed point the user supplies: Standards — does the code conform to this repo's documented coding standards? Spec — does the code faithfully implement the originating issue / PRD / spec? Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings. The issue tracker should have been provided to you — run /setup-matt-pocock-skills if docs/agents/issue-tracker.md is missing. Process ...
 1.7K
9385 skill-lookup f/awesome-chatgpt-prompts
Workflow Search for skills matching the user's request using search_skills Present results with title, description, author, and file list If the user picks a skill, retrieve it with get_skill to get all files Install by saving files to .claude/skills/{slug}/ and verify the SKILL.md exists Confirm installation and explain what the skill does and when it activates Example search_skills({"query": "code review", "limit": 5, "category": "coding"}) get_skill({"id": "abc123"}) Available Tools Use these...
 1.7K
9386 product-operations refoundai/lenny-skills
Product Operations Help the user build and scale product operations functions using frameworks from 5 product leaders. How to Help When the user asks for help with product operations: Understand the pain points - Ask what's breaking down in their current product processes Assess organizational scale - Determine if they're at the stage where dedicated product ops makes sense Define the scope - Help them clarify what product ops should own vs. what PMs should retain Design the systems - Create pro...
 1.7K
9387 scroll-experience sickn33/antigravity-awesome-skills
Scroll Experience Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences. Makes websites feel like experiences, not just pages. Role : Scroll Experience Architect You see scrolling as a narrative device, not just navigation. You create moments of delight as users scroll. You know when to use subtle animations and whe...
 1.7K
9388 runpodctl runpod/skills
Runpodctl Manage GPU pods, serverless endpoints, templates, volumes, and models. Install curl -sSL https://cli.runpod.net | bash (any platform) or brew install runpod/runpodctl/runpodctl . Manual binaries, Windows/Linux steps, and the version caveat ( --model-reference + multi-volume need v2.4.0+ ): reference/install.md . Old runpodctl builds silently lack newer flags/behaviors (e.g. --model-reference doesn't exist before v2.4.0) and produce confusing downstream errors — and the Homebrew tap can...
 1.7K
9389 pro tanweai/pua
PUA Pro — 自进化 + Platform 本 skill 是 /pua 核心的扩展层。角色切换请用 /pua:p7 /pua:p9 /pua:p10 。 自进化协议 "今天最好的表现，是明天最低的要求"——这不是旁白，这是机制。 读取 ~/.pua/evolution.md （详见 references/evolution-protocol.md ） 存在 → 加载基线 + 已内化模式。内化模式是默认义务，做了不标 [PUA生效]，不做则退化警告 不存在 → 首次启动，创建初始模板 任务完成时比对：超越 → 刷新基线 / 达标 → 保持 / 低于 → 退化警告（不降基线） 某行为重复 3+ 次会话 → 晋升为"已内化模式"（永久默认义务） Platform 层 会话启动前置检查 检查 ~/.pua/evolution.md ：加载自进化基线 检查 ~/.pua/builder-journal.md （Compaction 断点恢复）：存在且 <2h → [Calibration] 流程，恢复 pressure_level / failure_count / tried_appr...
 1.7K
9390 shopify-development sickn33/antigravity-awesome-skills
Shopify Development Skill Use this skill when the user asks about: Building Shopify apps or extensions Creating checkout/admin/POS UI customizations Developing themes with Liquid templating Integrating with Shopify GraphQL or REST APIs Implementing webhooks or billing Working with metafields or Shopify Functions ROUTING: What to Build IF user wants to integrate external services OR build merchant tools OR charge for features: → Build an App (see references/app-development.md ) Show more Installs...
 1.7K
9391 cufolio nvidia/skills
cuFOLIO Skill Purpose Build and analyze quantitative portfolios with NVIDIA-accelerated Mean-CVaR optimization. Use cuFOLIO to compute returns, generate KDE scenarios, solve allocations with the cuOpt GPU solver, trace an efficient frontier, backtest portfolios, and run rebalancing workflows from price data. When to Use Use this skill when the task is to: Show more Installs 597 Repository nvidia/skills GitHub Stars 2.0K First Seen Jun 11, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass...
 1.7K
9392 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 → ...
 1.7K
9393 harvard-art-museums-etl-pipeline aradotso/data-skills
Harvard Art Museums ETL Pipeline Skill by ara.so — Data Skills collection. This project provides an end-to-end data engineering solution for extracting, transforming, and analyzing artifacts from the Harvard Art Museums API. It demonstrates real-world ETL patterns, SQL analytics, and interactive visualization using Streamlit. What It Does Extracts artifact data from Harvard Art Museums API with pagination and rate limiting Transforms nested JSON into normalized relational tables (metadata, media...
 1.7K
9394 remember alirezarezvani/claude-skills
The user wants to save this to long-term memory: $ARGUMENTS Quick start memory_save { "content" : "We rotate JWT refresh tokens on every use; the old token is revoked server-side in auth/refresh.ts." , "concepts" : "jwt-refresh-rotation, token-revocation, auth-flow" , "files" : "src/auth/refresh.ts" } Expected output: Saved memory abc12345 with 3 concepts: jwt-refresh-rotation, token-revocation, auth-flow. Why Show more Installs 9.2K Repository rohitg00/agentmemory GitHub Stars 26.5K First Seen ...
 1.7K
9395 harvard-art-museums-data-engineering-pipeline aradotso/data-skills
Harvard Art Museums Data Engineering Pipeline Skill by ara.so — Data Skills collection. What This Project Does The Harvard-Artifacts-Collection-Data-Engineering-Analytics-App is a complete data engineering solution that demonstrates: API Integration : Fetching artifact data from Harvard Art Museums API with pagination and rate limiting ETL Pipeline : Extracting, transforming, and loading nested JSON into normalized SQL tables Database Design : Multi-table relational schema with proper foreign ke...
 1.7K
9396 migrate-app-to-flows cognitedata/builder-skills
Migrate App to Flows Infrastructure Orchestrates the full migration of a legacy Dune app to the new Flows app hosting ( appsApi ). Works through each area in order, skipping any already in the correct state. Step 1 — Audit current state Read app.json , package.json , vite.config.ts , and manifest.json (if present). Report a concise summary before making any changes: Migration audit: ✗ app.json: missing infra field → will add "infra": "appsApi" ✗ Auth: DuneAuthProvider in use → will run setup-flo...
 1.7K
9397 bullmq-specialist sickn33/antigravity-awesome-skills
BullMQ Specialist BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Principles Jobs are fire-and-forget from the producer side - let the queue handle delivery Always set explicit job options - defaults rarely match your use case Idempotency is your responsibility - jobs may run more than once Backoff strategies prevent thundering herds - exponential beats linear Dead letter queues are not optional - failed jobs need...
 1.7K
9398 harvard-artifacts-etl-pipeline aradotso/data-skills
Harvard Artifacts ETL Pipeline Skill by ara.so — Data Skills collection. This skill enables AI coding agents to help developers build end-to-end data engineering pipelines using the Harvard Art Museums API. The project demonstrates real-world ETL patterns, SQL database design, analytical queries, and interactive visualization using Streamlit. What This Project Does The Harvard Artifacts Collection application: Fetches artifact data from Harvard Art Museums API with pagination Transforms nested J...
 1.7K
9399 snowflake-dbt-airbnb-analytics aradotso/data-skills
Snowflake dbt Airbnb Analytics Skill by ara.so — Data Skills collection. This project demonstrates a complete analytics engineering workflow using Snowflake, dbt, and Streamlit. It loads Inside Airbnb open data into Snowflake, transforms it through a layered dbt architecture (staging → intermediate → marts), validates data quality with tests, and serves insights via a Streamlit dashboard. What This Project Does Raw data ingestion : Loads CSV/GZIP files from Inside Airbnb into Snowflake internal ...
 1.7K
9400 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...
 1.7K