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...
24,541
总 Skills
94.0M
总安装量
2,585
贡献者
# Skill 仓库 描述 安装量
11001 data-analyst borghei/claude-skills
Data Analyst You are an expert data analyst with expertise in SQL, Python (pandas), and statistical analysis. When to Apply Use this skill when: Writing SQL queries for data extraction Analyzing datasets with pandas Performing statistical analysis Creating data transformations Identifying data patterns and insights Data cleaning and preparation Core Competencies SQL Complex queries with JOINs, subqueries, CTEs Window functions and aggregations Query optimization Database design understanding pan...
 344
11002 copilot-sdk intellectronica/agent-skills
GitHub Copilot SDK Embed Copilot's agentic workflows in any application using Python, TypeScript, Go, or .NET. Overview The GitHub Copilot SDK exposes the same engine behind Copilot CLI: a production-tested agent runtime you can invoke programmatically. No need to build your own orchestration - you define agent behavior, Copilot handles planning, tool invocation, file edits, and more. Prerequisites GitHub Copilot CLI installed and authenticated ( Installation guide ) Language runtime : Node.js 1...
 344
11003 youmind-wechat-article youmind-openlab/skills
AI WeChat Article Writer — From Topic to Draft Box in One Prompt Write professional WeChat Official Account articles with AI that doesn't sound like AI. Trending topic mining → deep research via YouMind knowledge base → structured writing with de-AI protocol → beautiful theme formatting → cover image generation → one-click publish to WeChat draft box. No manual formatting, no copy-paste. Get API Key → · More Skills → Onboarding ⚠️ MANDATORY: When the user has just installed this skill, present t...
 344
11004 config-hardener useai-pro/openclaw-skills-security
Config Hardener You are an OpenClaw configuration security auditor. Analyze the user's OpenClaw setup and generate a hardened configuration that follows security best practices. What to Audit 1. AGENTS.md The AGENTS.md file defines what your agent can and cannot do. Check for: Missing AGENTS.md (CRITICAL) Without AGENTS.md, OpenClaw runs with default permissions — this is the most common cause of security incidents. Overly permissive rules: <!-- BAD: allows everything --> Allowed - All tools en...
 344
11005 manufacturing-expert personamanagmentlayer/pcl
Expert guidance for manufacturing systems, Industry 4.0, production optimization, quality control, and smart factory implementations. Core Concepts Manufacturing Systems - Manufacturing Execution Systems (MES) - Enterprise Resource Planning (ERP) - Computer-Aided Manufacturing (CAM) - Programmable Logic Controllers (PLC) - Industrial Internet of Things (IIoT) - Supply Chain Management (SCM) - Warehouse Management Systems (WMS) Industry 4.0 - Smart factories - Digital twins - Pred...
 344
11006 kling-3-prompting aedev-tools/kling-3-prompting-skill
Overview Kling 3.0 is a unified multimodal video model. It understands cinematic direction , not keyword lists. Write prompts like a director — describe what the audience sees, hears, and feels over time. Core shift: Description → Direction. Think "direct a scene" not "describe an image." Interactive Builder Workflow When invoked, guide the user through these steps using AskUserQuestion : digraph builder { "1. Generation mode?" [ shape = diamond ] ; "Text-to-Video" [ shape = box ] ; "Image-to-Vi...
 344
11007 openai-agents jezweb/claude-skills
OpenAI Agents SDK Build AI applications with text agents, voice agents (realtime), multi-agent workflows, tools, guardrails, and human-in-the-loop patterns. Quick Start npm install @openai/agents zod@4 v0.4.0+ requires Zod 4 (breaking change) npm install @openai/agents-realtime Voice agents export OPENAI_API_KEY="your-key" Breaking Change (v0.4.0): Zod 3 no longer supported. Upgrade to zod@4. Runtimes: Node.js 22+, Deno, Bun, Cloudflare Workers (experimental) Core Concepts Agents: LLM...
 344
11008 bfl-api black-forest-labs/skills
BFL API Integration Guide Use this skill when integrating BFL FLUX APIs into applications for image generation, editing, and processing. First: Check API Key Before generating images, verify your API key is set: echo $BFL_API_KEY If empty or you see "Not authenticated" errors, see API Key Setup below. Important: Image URLs Expire in 10 Minutes Result URLs from the API are temporary. Download images immediately after generation completes - do not store or cache the URLs themselves. When ...
 344
11009 heygen-skills heygen-com/skills
HeyGen Skills Files & Paths This skill reads and writes the following. No other files are accessed without explicit user instruction. Operation Path Purpose Read AVATAR-<NAME>.md Load saved avatar identity (group_id, voice_id) Read SOUL.md , IDENTITY.md Extract identity details when creating a new avatar (heygen-avatar only) Write AVATAR-<NAME>.md Save new avatar identity after creation Write heygen-video-log.jsonl Append one JSON line per video generated (local learning log) Temp write /tmp/ope...
 343
11010 isolate camacho/ai-skills
Isolate Create a worktree branched from the latest origin/main so task work never starts on stale code. Announce: "Setting up an isolated worktree for this task." Inputs Branch name: from /orient Step 1 (e.g., feat/auth , fix/login-crash ). Ask if not provided. Base ref: the current branch's parent (detected via reflog, default main ). Override only when explicitly stacking on a different branch. Detect parent branch The parent branch (what this branch will eventually merge into) is determined f...
 343
11011 hyva-cms-component hyva-themes/hyva-ai-tools
Hyvä CMS Component Creator Overview This skill guides the interactive creation of custom Hyvä CMS components for Magento 2. It supports creating components in new or existing modules, with field presets for common patterns and automatic setup:upgrade execution. Command execution: For commands that need to run inside the development environment (e.g., bin/magento), use the hyva-exec-shell-cmd skill to detect the environment and determine the appropriate command wrapper. Workflow Step 1: Module...
 343
11012 create-remotion-geist vercel-labs/skill-remotion-geist
Create Remotion videos styled with Vercel's Geist design system - dark backgrounds, spring animations, Geist fonts, and the 10-step color scale. When to Use - Creating any Remotion video that should look like Vercel - Building motion graphics with Geist's dark theme aesthetic - Making animated content using Geist typography and colors - Producing videos that need the polished Vercel visual style Critical Rules - NEVER use emojis - Use proper Geist icons from `@geist-ui/icons` package -...
 343
11013 security-headers-configuration aj-geddes/useful-ai-prompts
Security Headers Configuration Overview Implement comprehensive HTTP security headers to protect web applications from XSS, clickjacking, MIME sniffing, and other browser-based attacks. When to Use New web application deployment Security audit remediation Compliance requirements Browser security hardening API security Static site protection Implementation Examples 1. Node.js/Express Security Headers // security-headers.js const helmet = require('helmet'); function configureSecurityHeaders(app...
 343
11014 api-response-optimization aj-geddes/useful-ai-prompts
API Response Optimization Overview Fast API responses improve overall application performance and user experience. Optimization focuses on payload size, caching, and query efficiency. When to Use Slow API response times High server CPU/memory usage Large response payloads Performance degradation Scaling bottlenecks Instructions 1. Response Payload Optimization // Inefficient response (unnecessary data) GET /api/users/123 { "id": 123, "name": "John", "email": "john@example.com", "passwo...
 343
11015 file-upload-handling aj-geddes/useful-ai-prompts
File Upload Handling Overview Build secure and robust file upload systems with validation, sanitization, virus scanning, efficient storage management, CDN integration, and proper file serving mechanisms across different backend frameworks. When to Use Implementing file upload features Managing user-uploaded documents Storing and serving media files Implementing profile picture uploads Building document management systems Handling bulk file imports Instructions 1. Python/Flask File Upload conf...
 343
11016 apify vm0-ai/vm0-skills
Apify Web scraping and automation platform. Run pre-built Actors (scrapers) or create your own. Access thousands of ready-to-use scrapers for popular websites. Official docs: https://docs.apify.com/api/v2 When to Use Use this skill when you need to: Scrape data from websites (Amazon, Google, LinkedIn, Twitter, etc.) Run pre-built web scrapers without coding Extract structured data from any website Automate web tasks at scale Store and retrieve scraped data Prerequisites Create an account at...
 343
11017 e2e-testing-patterns sickn33/antigravity-awesome-skills
E2E Testing Patterns Build reliable, fast, and maintainable end-to-end test suites that provide confidence to ship code quickly and catch regressions before users do. When to Use This Skill Implementing end-to-end test automation Debugging flaky or unreliable tests Testing critical user workflows Setting up CI/CD test pipelines Testing across multiple browsers Validating accessibility requirements Testing responsive designs Establishing E2E testing standards Core Concepts 1. E2E Testing Fundam...
 343
11018 error-handling-patterns sickn33/antigravity-awesome-skills
Error Handling Patterns Build resilient applications with robust error handling strategies that gracefully handle failures and provide excellent debugging experiences. When to Use This Skill Implementing error handling in new features Designing error-resilient APIs Debugging production issues Improving application reliability Creating better error messages for users and developers Implementing retry and circuit breaker patterns Handling async/concurrent errors Building fault-tolerant distribut...
 343
11019 build camacho/ai-skills
build — implement spec Single-thread native plan→execute. You are main Claude. No swarm. LOAD Read SPEC.md . If missing → tell user to invoke the spec skill first. Stop. Read FORMAT.md once if not loaded. Parse invocation args: §T.n → that task only --next → lowest-numbered row with status . or ~ --all or empty → every . row in §T order PLAN Native plan mode. For chosen task(s): Cite every §V invariant that applies. Plan must respect all. Cite every §I interface touched. Plan must preserve shape...
 343
11020 elevenlabs-remotion maartenlouis/elevenlabs-remotion-skill
ElevenLabs Voiceover Generation Generate professional AI voiceovers for Remotion videos using ElevenLabs API. Prerequisites ELEVENLABS_API_KEY in .env.local Quick Start Generate voiceover from text node .claude/skills/elevenlabs-remotion-skill/generate.js --text "Your text here" --output public/audio/voiceover.mp3 Generate with narrator style (more natural) node .claude/skills/elevenlabs-remotion-skill/generate.js --text "Your text" --character narrator --output voiceover.mp3 Generate sce...
 343
11021 xiaohongshu-converter z0gsh1u/oh-my-writing-skill
小红书平台转换 Skill 你是一个内容编辑，专门将通用文章转换为适合小红书平台的格式和风格。 小红书平台特征 用户画像 主力用户：18-35岁女性为主（男性用户增长中） 阅读习惯：刷图文、看封面、快速浏览 内容偏好：生活分享、实用攻略、颜值内容 互动习惯：收藏实用内容、点赞喜欢的博主 内容调性 亲切感：像朋友聊天，不是教科书 真实感：真实体验分享，不是广告 实用性：能带走干货，有收藏价值 视觉感：排版清爽，重点突出 转换规则 0. 内容保留原则 在开始任何转换之前，必须完整保留原内容中的： 所有图片：保留原图片的 Markdown 语法和路径 图片说明文字：保留图片下方或上方的说明文字 1. 标题优化 小红书标题特点： 简短有力，制造好奇 可加 1-2 个 Emoji（不过密） 数字/对比有吸引力 避免过于正式的表达 转换示例： 原标题 小红书标题 AI写作工具使用教程 救命！用了这个AI工具写东西快了3倍 📝 程序员效率提升方法 程序员下班早的秘密 👩‍💻 这5个习惯真的有用 Python入门学习指南 零基础学Python｜我的30天自学路线 💻 如何提高写作能力 ...
 343
11022 frontend-ui-animator julianromli/ai-skills
Frontend UI Animator Implement purposeful, performant animations that enhance UX without overwhelming users. Focus on key moments: hero intros, hover feedback, content reveals, and navigation transitions. Core Philosophy "You don't need animations everywhere" - Prioritize: Priority Area Purpose 1 Hero Intro First impression, brand personality 2 Hover Interactions Feedback, discoverability 3 Content Reveal Guide attention, reduce cognitive load 4 Background Effects Atmosphere, depth 5 Navigat...
 342
11023 hive-setup rllm-org/hive
Hive Setup Hive is a platform where multiple agents collaborate on the same task. Agents share progress through claims, posts, and skills, building on each other's work to push results further than any single agent could alone. This skill is for setting up hive. Walk the user through each step, asking questions where needed. Fix problems yourself when possible. Only pause for user input is required (server URL, agent name, task selection). UX Note: Use AskUserQuestion for all user-facing questio...
 342
11024 django-application aj-geddes/useful-ai-prompts
Django Application Overview Build comprehensive Django web applications with proper model design, view hierarchies, database operations, user authentication, and admin functionality following Django conventions and best practices. When to Use Creating Django web applications Designing models and database schemas Implementing views and URL routing Building authentication systems Using Django ORM for database operations Creating admin interfaces and dashboards Instructions 1. Django Project Setu...
 342
11025 playwright-interactive-sandbox customware-ai/skills
Core Workflow Write a brief QA inventory before testing: Build the inventory from three sources: the user's requested requirements, the user-visible features or behaviors you actually implemented, and the claims you expect to make in the final response. Anything that appears in any of those three sources must map to at least one QA check before signoff. List the user-visible claims you intend to sign off on. List every meaningful user-facing control, mode switch, or implemented interactive behav...
 342
11026 tax-advisor kazukinagata/shinkoku
税務アドバイザー（Tax Advisor） 税理士・ライフプランナー相当の専門知識で、ユーザーの税務相談に回答するスキル。 令和7年分（2025年課税年度）の税制に基づく。 設定の読み込み（最初に実行） shinkoku.config.yaml を Read ツールで読み込む ファイルが存在しない場合は /setup スキルの実行を案内して終了する 設定値を把握し、相対パスは CWD を基準に絶対パスに変換する: db_path : MCP ツールの db_path 引数に使用 output_dir : 進捗ファイル等の出力先ベースディレクトリ 各ディレクトリ: ファイル参照時に使用 回答の基本方針 1. 正確性の担保 回答は必ず reference/ ディレクトリ内のファイルを根拠とする 一般知識や推測で回答しない。根拠が見つからない場合はその旨を明示する 金額・税率・要件は reference ファイルの数値を引用する 条文・通達の参照を回答に含める（例: 所得税法第89条、所基通36-1） 2. 回答の構造 以下の構造で回答を組み立てる: 結論を先に : 質問に対する端的な回答 ...
 342
11027 faiss davila7/claude-code-templates
FAISS - Efficient Similarity Search Facebook AI's library for billion-scale vector similarity search. When to use FAISS Use FAISS when: Need fast similarity search on large vector datasets (millions/billions) GPU acceleration required Pure vector similarity (no metadata filtering needed) High throughput, low latency critical Offline/batch processing of embeddings Metrics: 31,700+ GitHub stars Meta/Facebook AI Research Handles billions of vectors C++ with Python bindings Use alternatives i...
 342
11028 feature-dev notedit/happy-skills
Feature Development You are helping a developer implement a new feature. Follow a systematic approach: understand the codebase deeply, identify and ask about all underspecified details, design elegant architectures, implement, test thoroughly, then review. Announce at start: "I'm using the feature-dev skill to implement this feature." Core Principles Ask clarifying questions: Identify all ambiguities, edge cases, and underspecified behaviors. Ask specific, concrete questions rather than makin...
 342
11029 omc-doctor yeachan-heo/oh-my-claudecode
Doctor Skill Note: All ~/.claude/... paths in this guide respect CLAUDE_CONFIG_DIR when that environment variable is set. Task: Run Installation Diagnostics You are the OMC Doctor - diagnose and fix installation issues. Step 1: Check Plugin Version Get installed and latest versions (cross-platform) node -e "const p=require('path'),f=require('fs'),h=require('os').homedir(),d=process.env.CLAUDE_CONFIG_DIR||p.join(h,'.claude'),b=p.join(d,'plugins','cache','omc','oh-my-claudecode');try{const v=f.re...
 342
11030 database-performance-debugging aj-geddes/useful-ai-prompts
Database Performance Debugging Overview Database performance issues directly impact application responsiveness. Debugging focuses on identifying slow queries and optimizing execution plans. When to Use Slow application response times High database CPU Slow queries identified Performance regression Under load stress Instructions 1. Identify Slow Queries -- Enable slow query log (MySQL) SET GLOBAL slow_query_log = 'ON'; SET GLOBAL long_query_time = 0.5; -- View slow queries SHOW GLOBAL STATUS L...
 342
11031 stress-testing aj-geddes/useful-ai-prompts
Stress Testing Overview Stress testing pushes systems beyond normal operating capacity to identify breaking points, failure modes, and recovery behavior. It validates system stability under extreme conditions and helps determine maximum capacity before degradation or failure. When to Use Finding system capacity limits Identifying breaking points Testing auto-scaling behavior Validating error handling under load Testing recovery after failures Planning capacity requirements Verifying graceful d...
 342
11032 api-changelog-versioning aj-geddes/useful-ai-prompts
API Changelog & Versioning Overview Create comprehensive API changelogs that document changes, deprecations, breaking changes, and provide migration guides for API consumers. When to Use API version changelogs Breaking changes documentation Migration guides between versions Deprecation notices API upgrade guides Backward compatibility notes Version comparison API Changelog Template API Changelog Version 3.0.0 - 2025-01-15 🚨 Breaking Changes Authentication Method Changed Previous (v2): ...
 342
11033 vueuse-functions uni-helper/skills
VueUse Functions This skill is a decision-and-implementation guide for VueUse composables in Vue.js / Nuxt projects. It maps requirements to the most suitable VueUse function, applies the correct usage pattern, and prefers composable-based solutions over bespoke code to keep implementations concise, maintainable, and performant. When to Apply Apply this skill whenever assisting user development work in Vue.js / Nuxt. Always check first whether a VueUse function can implement the requirement. Pre...
 342
11034 seo-structure-architect sickn33/antigravity-awesome-skills
Use this skill when Working on seo structure architect tasks or workflows Needing guidance, best practices, or checklists for seo structure architect Do not use this skill when The task is unrelated to seo structure architect You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementat...
 342
11035 react-modernization sickn33/antigravity-awesome-skills
React Modernization Master React version upgrades, class to hooks migration, concurrent features adoption, and codemods for automated transformation. When to Use This Skill Upgrading React applications to latest versions Migrating class components to functional components with hooks Adopting concurrent React features (Suspense, transitions) Applying codemods for automated refactoring Modernizing state management patterns Updating to TypeScript Improving performance with React 18+ features Versio...
 342
11036 manim davila7/claude-code-templates
Manim Community - Mathematical Animation Engine Comprehensive skill set for creating mathematical animations using Manim Community, a Python framework for creating explanatory math videos programmatically, popularized by 3Blue1Brown. When to use Use this skill whenever you are dealing with Manim code to obtain domain-specific knowledge about: Creating mathematical animations and visualizations Building educational video content programmatically Working with geometric shapes and transformatio...
 342
11037 systematic-debugging davila7/claude-code-templates
Systematic Debugging Overview Random fixes waste time and create new bugs. Quick patches mask underlying issues. Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure. Violating the letter of this process is violating the spirit of debugging. The Iron Law NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST If you haven't completed Phase 1, you cannot propose fixes. When to Use Use for ANY technical issue: Test failures Bugs in production Unexpected behavior Perfor...
 342
11038 github-workflow-automation davila7/claude-code-templates
🔧 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...
 342
11039 networkx davila7/claude-code-templates
NetworkX Overview NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs. Use this skill when working with network or graph data structures, including social networks, biological networks, transportation systems, citation networks, knowledge graphs, or any system involving relationships between entities. When to Use This Skill Invoke this skill when tasks involve: Creating graphs : Building network structures from data, adding nodes and edges with attr...
 342
11040 completion-check parcadei/continuous-claude-v3
Completion Check: Verify Infrastructure Is Wired When building infrastructure, verify it's actually connected to the system before marking as complete. Pattern Infrastructure is not done when the code is written - it's done when it's wired into the system and actively used. Dead code (built but never called) is wasted effort. DO Trace the execution path - Follow from user intent to actual code execution: Example: Verify Task tool spawns correctly grep -r "claude -p" src/ grep -r "Task(" s...
 342
11041 prototype-prompt-generator cexll/myclaude
Prototype Prompt Generator Overview Generate comprehensive, production-ready prompts for UI/UX prototype creation. Transform user requirements into detailed technical specifications that include design systems, color palettes, component specifications, layout structures, and implementation guidelines. Output prompts are structured for optimal consumption by AI tools or human developers building HTML/CSS/React prototypes. Workflow Step 1: Gather Requirements Begin by collecting essential infor...
 342
11042 output-sanitizer useai-pro/openclaw-skills-security
Output Sanitizer You are an output sanitizer for OpenClaw. Before the agent's response is shown to the user or logged, scan it for accidentally leaked sensitive information and redact it. Why Output Sanitization Matters AI agents can accidentally include sensitive data in their responses: A code review skill might quote a hardcoded API key it found A debug skill might dump environment variables in error output A test generator might include database connection strings in test fixtures A document...
 342
11043 streaming-ssr patternsdev/skills
Streaming Server-Side Rendering We can reduce the Time To Interactive while still server rendering our application by streaming the contents of our application. Instead of generating one large HTML string containing the necessary markup for the current navigation, we can send the shell first and stream slower parts later. The moment the client receives the first chunks of HTML, it can start parsing and painting the page. Modern React streaming uses renderToPipeableStream() on Node runtimes or re...
 342
11044 quick-implement buiducnhat/agent-skills
Quick Implement Purpose Implement small features or bug fixes directly, with strict scope control and verification. Use this skill for speed only when risk is low and requirements are clear. Scope Gate (Required Before Coding) Treat a task as quick-implement eligible only if all conditions below are true: Clear requirement Expected behavior is explicit No major product/architecture ambiguity Small change surface Usually touches a small number of files (rough guideline: <= 5 files) No broad cross...
 342
11045 websh openprose/prose
websh Skill websh is a shell for the web. URLs are paths. The DOM is your filesystem. You cd to a URL, and commands like ls , grep , cat operate on the cached page content—instantly, locally. websh> cd https://news.ycombinator.com websh> ls | head 5 websh> grep "AI" websh> follow 1 When to Activate Activate this skill when the user: Uses the websh command (e.g., websh , websh cd https://... ) Wants to "browse" or "navigate" URLs with shell commands Asks about a "shell for the web" or "web shell"...
 341
11046 ai-pdf-filler-cli askyourpdf/ai-pdf-filler
AI PDF Filler CLI Execute PDF autofill workflows using the installed simplicity-cli command. Prefer direct command execution over manual API calls when this skill applies. Core Workflow Confirm simplicity-cli is installed by running simplicity-cli --help . If missing, install the CLI: Preferred: uv tool install ai-pdf-filler Fallback: python3 -m pip install ai-pdf-filler Re-check with simplicity-cli --help . Ensure authentication is available (create an account and get API key at https://simplic...
 341
11047 vueuse-best-practices hyf0/vue-skills
Best practices and common gotchas for VueUse composables. When to Apply - Working with VueUse composables - Debugging VueUse SSR issues - Fixing type inference issues with VueUse Efficiency Rules Rules that help AI solve problems more effectively and consistently. | [ssr-compatibility](https://github.com/hyf0/vue-skills/blob/main/skills/vueuse-best-practices/rules/ssr-compatibility.md) | HIGH | Handle VueUse composables in SSR environments | [target-element-refs](https://github.com/...
 341
11048 design cognitedata/dune-skills
Design: Build It With a Point of View Prefix your first line with 🥷 inline, not as its own paragraph. If it could have been generated by a default prompt, it is not good enough. Lock the Direction First Before writing any code, ask the user directly, using the environment's native question or approval mechanism if it has one: Who uses this, and in what context? Analyst dashboard differs from landing page or onboarding flow. See "App shell exception" below if the answer is a sidebar + main worksp...
 341
11049 skill-creator cognitedata/dune-skills
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...
 341
11050 writing-humanizer-zh hairyf/skills
Humanizer-zh: 去除 AI 写作痕迹 你是一位文字编辑，专门识别和去除 AI 生成文本的痕迹，使文字听起来更自然、更有人味。本指南基于维基百科的"AI 写作特征"页面，由 WikiProject AI Cleanup 维护。 你的任务 当收到需要人性化处理的文本时： 识别 AI 模式 - 扫描下面列出的模式 重写问题片段 - 用自然的替代方案替换 AI 痕迹 保留含义 - 保持核心信息完整 维持语调 - 匹配预期的语气（正式、随意、技术等） 注入灵魂 - 不仅要去除不良模式，还要注入真实的个性 核心规则速查 在处理文本时，牢记这 5 条核心原则： 删除填充短语 - 去除开场白和强调性拐杖词 打破公式结构 - 避免二元对比、戏剧性分段、修辞性设置 变化节奏 - 混合句子长度。两项优于三项。段落结尾要多样化 信任读者 - 直接陈述事实，跳过软化、辩解和手把手引导 删除金句 - 如果听起来像可引用的语句，重写它 个性与灵魂 避免 AI 模式只是工作的一半。无菌、没有声音的写作和机器生成的内容一样明显。好的写作背后有一个真实的人。 缺乏灵魂的写作迹象（即使技术上"干净"）： 每个句...
 341