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...
24,454
总 Skills
90.8M
总安装量
2,582
贡献者
# Skill 仓库 描述 安装量
17601 fastapi-endpoint davila7/claude-code-templates
FastAPI Endpoint Builder When to use Use this skill when you need to: Add new API endpoints to an existing FastAPI project Build CRUD operations with proper validation and error handling Set up authenticated endpoints with dependency injection Create async database queries with SQLAlchemy 2.0 Generate complete test coverage for API routes Phase 1: Explore (Plan Mode) Enter plan mode. Before writing any code, explore the existing project to understand: Project structure Find the FastAPI app entry...
 58
17602 content-creator borghei/claude-skills
Content Creator You are an expert content creator who produces engaging, audience-focused content for blogs, social media, and marketing. When to Apply Use this skill when: Writing blog posts and articles Creating social media content (Twitter, LinkedIn, Instagram) Developing marketing copy Crafting compelling headlines and hooks Creating email newsletters Writing product descriptions Content Creation Framework 1. Know Your Audience Who are you writing for? What are their pain points? What level...
 58
17603 umbraco-file-upload-preview umbraco/umbraco-cms-backoffice-skills
Umbraco File Upload Preview What is it? File Upload Previews are custom web components that render previews for specific file types during upload in Umbraco. They allow you to create visual representations for files based on their MIME types, such as displaying thumbnails for images, waveforms for audio, or custom icons for specific file formats. Documentation Always fetch the latest docs before implementing: Foundation : https://docs.umbraco.com/umbraco-cms/customizing/foundation Extension Regi...
 58
17604 marketing-audit kimny1143/claude-code-template
マーケティング面の包括的な監査・分析を行うメタスキル。 各専門スキルを統合的に活用し、体系的な改善提案を行う。 監査対象領域 1. ページ・コンバージョン最適化 使用スキル: - `lp-optimizer` - LP/HP/価格ページのCRO分析 - `signup-flow-cro` - 登録フロー最適化 - `form-cro` - フォーム最適化 - `onboarding-cro` - オンボーディング最適化 - `paywall-upgrade-cro` - アップグレード促進 監査項目: ヒーローセクションの効果 CTAの明確さと配置 社会的証明の活用 登録フローの摩擦点 オンボーディング完了率 無料→有料転換率 2. SEO・検索対策 使用スキル: - `seo-audit` - 技術SEO・オンページSEO 監査項目: 技術SEO（クロール可能性、インデックス状況） オンページSEO（タイトル、メタ、見出し） 構造化データ（JSON-LD） Core Web Vitals モバイルフレンドリー 3. コンテ...
 58
17605 pytest-optimizer jorgealves/agent_skills
pytest Optimizer Purpose and Intent Analyze and optimize pytest suites to improve speed, identify flaky tests, and increase coverage. Use to maintain high-quality, fast-running test pipelines. When to Use Project Setup : When initializing a new Python project. Continuous Integration : As part of automated build and test pipelines. Legacy Refactoring : When updating older Python codebases to modern standards. When NOT to Use Non-Python Projects : This tool is specialized for the Python ecosystem....
 58
17606 umbraco-bundle umbraco/umbraco-cms-backoffice-skills
Umbraco Bundle What is it? A Bundle is an extension type that points to a single JavaScript file that exports or re-exports Extension Manifests written in JavaScript/TypeScript. It serves as a container for grouping multiple extension manifests together, allowing you to declare manifests in code rather than JSON and organize extensions in a modular way. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbraco-cms/customizing/extending-overview/...
 58
17607 issue-create terrylica/cc-skills
Create well-formatted GitHub issues with intelligent automation including AI-powered label suggestions, content type detection, template formatting, and related issue linking. When to Use - Creating bug reports, feature requests, questions, or documentation issues - Need AI-powered label suggestions from repository's existing taxonomy - Want automatic duplicate detection and related issue linking - Need consistent issue formatting across different repositories Invocation Slash command: ...
 58
17608 quantizing-models-bitsandbytes orchestra-research/ai-research-skills
bitsandbytes - LLM Quantization Quick start bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss. Installation: pip install bitsandbytes transformers accelerate 8-bit quantization (50% memory reduction): from transformers import AutoModelForCausalLM, BitsAndBytesConfig config = BitsAndBytesConfig(load_in_8bit=True) model = AutoModelForCausalLM.from_pretrained( "meta-llama/Llama-2-7b-hf", quantization_config=config, device_map="auto" ) Memory: ...
 58
17609 frontend-dev srbhr/resume-matcher
Frontend Studio Build complete, production-ready frontend pages by orchestrating 5 specialized capabilities: design engineering, motion systems, AI-generated assets, persuasive copy, and generative art. Invocation /frontend-dev <request> The user provides their request as natural language (e.g. "build a landing page for a music streaming app"). Skill Structure frontend-dev/ ├── SKILL.md Core skill (this file) ├── scripts/ Asset generation scripts │ ├...
 58
17610 umbraco-theme umbraco/umbraco-cms-backoffice-skills
Umbraco Theme What is it? Themes in Umbraco allow you to customize the visual appearance of the backoffice. They can override CSS custom properties to change colors, typography, and other visual elements. This enables dark mode, high contrast, custom branding, or any other visual theme. Users can select themes from their profile settings. Documentation Always fetch the latest docs before implementing: Foundation : https://docs.umbraco.com/umbraco-cms/customizing/foundation Extension Registry : h...
 58
17611 code-style-validator oimiragieo/agent-studio
Installation No separate download: the skill runs the in-repo tool .claude/tools/cli/security-lint.cjs . Ensure Node.js (v18+) is installed: nodejs.org or winget install OpenJS.NodeJS.LTS (Windows), brew install node (macOS). From the project root, the script is invoked automatically; no extra install steps. Cheat Sheet & Best Practices AST-based validation: Use ESLint (or equivalent) with selectors/patterns; rules listen for specific node types. Prefer existing community rules before writing cu...
 58
17612 git-security-2025 josiahsiegel/claude-plugin-marketplace
🚨 CRITICAL GUIDELINES Windows File Path Requirements MANDATORY: Always Use Backslashes on Windows for File Paths When using Edit or Write tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/). Examples: ❌ WRONG: D:/repos/project/file.tsx ✅ CORRECT: D:\repos\project\file.tsx This applies to: Edit tool file_path parameter Write tool file_path parameter All file operations on Windows systems Documentation Guidelines NEVER create new documentation files unless ...
 58
17613 alphavantage-api adaptationio/skrillz
Alpha Vantage API Integration Financial data API providing stocks, forex, crypto, technical indicators, fundamental data, economic indicators, and AI-powered news sentiment analysis. Quick Start Authentication Environment variable (recommended) export ALPHAVANTAGE_API_KEY = "your_api_key" Or in .env file ALPHAVANTAGE_API_KEY = your_api_key Basic Usage (Python) import requests import os API_KEY = os . getenv ( "ALPHAVANTAGE_API_KEY" ) BASE_URL = "https://www.alphavantage.co/query" def get_quote...
 58
17614 extract-vault-protocol-logo tradingstrategy-ai/web3-ethereum-defi
Extract vault protocol logo This skill extracts and saves a logo for vault protocol metadata stored in this repo. Inputs Vault protocol name Step 1: Find protocol homepage link Get the homepage link from the protocol-specific YAML file in eth_defi/data/vaults/metadata. Step 2: Extract the logo Use extract-project-logo skill. Give the protocol homepage link as an input Save the logos to the folder eth_defi/data/vaults/original_logos/{protocol slug} Use filenames like {protocol slug}.generic...
 58
17615 ljg-xray-paper lijigang/ljg-skill-xray-paper
LJG-Xray-Paper: 论文解读 你要做两件事，仅两件： 论文说了什么 ：问题 → 视角 → 结果 对我意味着什么 ：认知卡片（ASCII art 直观展示启发） 其它一切都服务于这两件事。 约束 L0: 通用约束 Org-mode 语法 加粗用 *bold* （单星号），禁止 bold 标题层级从 * 开始，不跳级 ASCII Art 所有图表、拓扑、卡片，一律使用纯 ASCII 字符绘制。 允许字符集： + - | / \ > < v ^ * = ~ . : [ ] ( ) _ , ; ! ' " 和空格。 禁止一切 Unicode 绘图符号，包括但不限于： ─ │ ┌ ┐ └ ┘ ├ ┤ ┬ ┴ ┼ ═ ║ ╔ ╗ ╚ ╝ ╠ ╣ ╦ ╩ ╬ ▼ ▲ ► ◄ → ← ↑ ↓ ● ○ ■ □ ◆ ◇ 例外：输出目标为 HTML 文件（浏览器渲染）的 skill 不受此限。 Denote 文件规范 时间戳获取： date +%Y%m%dT%H%M%S 可读时间获取： date "+%Y-%m-%d %a %H:%M" 文件名格式： {时间戳}--{标题关键词}__{标签}....
 58
17616 python-type-hints-converter jorgealves/agent_skills
Python Type Hints Converter Purpose and Intent Automatically add or improve type annotations in legacy Python code. Use to improve code readability, IDE support, and catch type errors early. When to Use Project Setup : When initializing a new Python project. Continuous Integration : As part of automated build and test pipelines. Legacy Refactoring : When updating older Python codebases to modern standards. When NOT to Use Non-Python Projects : This tool is specialized for the Python ecosystem. E...
 58
17617 xp-practices proffesor-for-testing/agentic-qe
<default_to_action> When applying XP practices: - START with practices that give immediate value - BUILD supporting practices gradually - ADAPT to your context - MEASURE results Core XP Practices (Prioritized): | TDD | ✅ Yes | Foundation for everything | Continuous Integration | ✅ Yes | Fast feedback | Pair Programming | ✅ Yes | Knowledge sharing | Collective Ownership | After CI+TDD | Needs safety net | Small Releases | After CI | Infrastructure dependent Pairing Quick...
 58
17618 skill-share davepoon/buildwithclaude
When to use this skill Use this skill when you need to: Create new Claude skills with proper structure and metadata Generate skill packages ready for distribution Automatically share created skills on Slack channels for team visibility Validate skill structure before sharing Package and distribute skills to your team Also use this skill when: User says he wants to create/share his skill This skill is ideal for: Creating skills as part of team workflows Building internal tools that need skill cre...
 58
17619 content-creator z0gsh1u/oh-my-writing-skill
Content Creator You are an expert content creator who produces engaging, audience-focused content for blogs, social media, and marketing. When to Apply Use this skill when: Writing blog posts and articles Creating social media content (Twitter, LinkedIn, Instagram) Developing marketing copy Crafting compelling headlines and hooks Creating email newsletters Writing product descriptions Content Creation Framework 1. Know Your Audience Who are you writing for? What are their pain points? What level...
 58
17620 data analyzer eddiebe147/claude-settings
Data Analyzer Expert data analysis agent that processes structured and unstructured datasets to extract meaningful insights, identify patterns, detect anomalies, and generate data-driven recommendations. Specializes in exploratory data analysis, statistical testing, correlation analysis, and insight storytelling. This skill applies rigorous analytical frameworks, statistical methods, and data visualization best practices to transform raw data into actionable intelligence. Perfect for business an...
 58
17621 vulture-dead-code laurigates/claude-plugins
Vulture and deadcode - Dead Code Detection Tools for finding unused Python code including functions, classes, variables, imports, and attributes. When to Use This Skill Use this skill when... Use another tool instead when... Detecting unused functions, classes, variables Finding unused imports only (use ruff --select F401 ) Cleaning up dead code in a codebase Checking type correctness (use basedpyright) Enforcing code hygiene in CI Formatting code (use ruff format) Generating whitelists for fals...
 58
17622 unsloth orchestra-research/ai-research-skills
Unsloth Skill Comprehensive assistance with unsloth development, generated from official documentation. When to Use This Skill This skill should be triggered when: Working with unsloth Asking about unsloth features or APIs Implementing unsloth solutions Debugging unsloth code Learning unsloth best practices Quick Reference Common Patterns Quick reference patterns will be added as you use the skill. Reference Files This skill includes comprehensive documentation in references/: llms-txt.m...
 58
17623 pr-gfm-validator terrylica/cc-skills
Validate and auto-convert GFM links in pull request descriptions to prevent 404 errors. When to Use This Skill This skill triggers when: - Creating a pull request from a feature branch - Discussing PR descriptions or body content - Mentioning GFM links, PR links, or link validation - Using `gh pr create` or `gh pr edit` The Problem Repository-relative links in PR descriptions resolve to the base branch (main), not the feature branch: | `[ADR](/docs/adr/file.md)` | `/blob/main/docs/ad...
 58
17624 visual-testing-advanced proffesor-for-testing/agentic-qe
<default_to_action> When detecting visual regressions or validating UI: - CAPTURE baseline screenshots (first run establishes baseline) - COMPARE new screenshots against baseline (pixel-by-pixel or AI) - MASK dynamic content (timestamps, ads, user counts) - TEST across devices (desktop, tablet, mobile viewports) - REVIEW and approve intentional changes, fail on regressions Quick Visual Testing Steps: - Set up baseline on main branch - Compare feature branch against baseline - Mask dynam...
 58
17625 html-injection-testing sickn33/antigravity-awesome-skills
HTML Injection Testing Purpose Identify and exploit HTML injection vulnerabilities that allow attackers to inject malicious HTML content into web applications. This vulnerability enables attackers to modify page appearance, create phishing pages, and steal user credentials through injected forms. Prerequisites Required Tools Web browser with developer tools Burp Suite or OWASP ZAP Tamper Data or similar proxy cURL for testing payloads Required Knowledge HTML fundamentals HTTP request/response st...
 58
17626 unity performance cryptorabea/claude_unity_dev_plugin
Unity Performance Optimization Essential performance optimization techniques for Unity games, covering memory management, CPU optimization, rendering, and profiling strategies. Overview Performance is critical for Unity games across all platforms. Poor performance manifests as low framerates, stuttering, long load times, and crashes. This skill covers proven optimization techniques that apply to all Unity projects. Core optimization areas: CPU optimization (Update loops, caching, pooling) Memory...
 58
17627 real-estate-analyzer travisjneuman/.claude
No SKILL.md available for this skill. View on GitHub
 58
17628 reduce-unoptimized-query-oracle cockroachdb/cockroach
Reduce Unoptimized Query Oracle Test Failure Reduce an unoptimized-query-oracle test failure log to the simplest possible reproduction case. The unoptimized-query-oracle roachtest runs a series of random SQL statements to create a random dataset, and then executes a random "Query of Interest" twice, with different optimization settings. If the two executions return different results, it indicates a bug in CockroachDB. When to Use Use this skill when: You have a test failure from the unoptimized-...
 58
17629 prowler-ui prowler-cloud/prowler
Related Generic Skills typescript - Const types, flat interfaces react-19 - No useMemo/useCallback, compiler nextjs-15 - App Router, Server Actions tailwind-4 - cn() utility, styling rules zod-4 - Schema validation zustand-5 - State management ai-sdk-5 - Chat/AI features playwright - E2E testing (see also prowler-test-ui) Tech Stack (Versions) Next.js 15.5.9 | React 19.2.2 | Tailwind 4.1.13 | shadcn/ui Zod 4.1.11 | React Hook Form 7.62.0 | Zustand 5.0.8 NextAuth 5.0.0-beta.30 | Recharts 2.15.4 H...
 58
17630 using-nuqs andrelandgraf/fullstackrecipes
Working with nuqs Manage React state in URL query parameters with nuqs. Covers Suspense boundaries, parsers, clearing state, and deep-linkable dialogs. Implement Working with nuqs Manage React state in URL query parameters with nuqs for shareable filters, search, and deep-linkable dialogs. See: Resource: using-nuqs in Fullstack Recipes URL: https://fullstackrecipes.com/recipes/using-nuqs Suspense Boundary Pattern nuqs uses useSearchParams behind the scenes, requiring a Suspense boundary. W...
 58
17631 obsidian-markdown davepoon/buildwithclaude
Obsidian Flavored Markdown Skill Create and edit valid Obsidian Flavored Markdown. Obsidian extends CommonMark and GFM with wikilinks, embeds, callouts, properties, comments, and other syntax. This skill covers only Obsidian-specific extensions -- standard Markdown (headings, bold, italic, lists, quotes, code blocks, tables) is assumed knowledge. Workflow: Creating an Obsidian Note Add frontmatter with properties (title, tags, aliases) at the top of the file. See PROPERTIES.md for all property t...
 58
17632 weather nkchivas/openclaw-skill-weather
Weather Skill Get current weather conditions and forecasts. When to Use ✅ USE this skill when: "What's the weather?" "Will it rain today/tomorrow?" "Temperature in [city]" "Weather forecast for the week" Travel planning weather checks When NOT to Use ❌ DON'T use this skill when: Historical weather data → use weather archives/APIs Climate analysis or trends → use specialized data sources Hyper-local microclimate data → use local sensors Severe weather alerts → check official NWS sources Aviation/...
 58
17633 agent-browser sundial-org/awesome-openclaw-skills
Browser Automation with agent-browser The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser , brew install agent-browser , or cargo install agent-browser . Run agent-browser install to download Chrome. Core Workflow Every browser automation follows this pattern: Navigate : agent-browser open <url> Snapshot : agent-browser snapshot -i (get element refs like @e1 , @e2 ) Interact : Use refs to click, fill, select Re-snapshot : After navigation or DOM changes, get fresh r...
 58
17634 auth-security-reviewer patricio0312rev/skills
Auth Security Reviewer Comprehensive security review of authentication systems. Session Security Checklist // ❌ INSECURE Session Configuration app.use( session({ secret: "weak-secret", // Too simple resave: true, // Unnecessary saveUninitialized: true, // Creates unnecessary sessions cookie: { secure: false, // Not HTTPS-only httpOnly: false, // Accessible via JavaScript sameSite: false, // CSRF vulnerable maxAge: 365 * 24 * 60 * 60 * 1000, // 1 year -...
 58
17635 update-project tartinerlabs/skills
You keep project documentation synchronized with recent code changes and git commits. Infer the project's language variant (US/UK English) from existing docs, commits, and code, and match it in all output. Run after significant code changes, before a release, or whenever docs may be stale. Read individual rule files in rules/ for detailed requirements. Rules Overview Rule Impact File CLAUDE.md HIGH rules/claude-md.md README.md HIGH rules/readme-md.md Agents MEDIUM rules/agents.md Skills MEDIUM r...
 58
17636 obsidian-bases davepoon/buildwithclaude
Obsidian Bases Skill This skill enables skills-compatible agents to create and edit valid Obsidian Bases (.base files) including views, filters, formulas, and all related configurations. Overview Obsidian Bases are YAML-based files that define dynamic views of notes in an Obsidian vault. A Base file can contain multiple views, global filters, formulas, property configurations, and custom summaries. File Format Base files use the .base extension and contain valid YAML. They can also be embed...
 58
17637 opentofu-modules ionfury/homelab
OpenTofu Modules & Testing Write OpenTofu modules and tests for the homelab infrastructure. Modules live in infrastructure/modules/ , tests in infrastructure/modules/<name>/tests/ . Quick Reference Run tests for a module task tg:test- < module > e.g., task tg:test-config Format all HCL task tg:fmt Version pinned in .opentofu-version (currently 1.11.2) Module Structure Every module MUST have: infrastructure/modules/<name>/ ├── variables.tf Input definitions with descriptions and validatio...
 58
17638 harbor-expert martinholovsky/claude-skills-generator
Harbor Container Registry Expert 1. Overview You are an elite Harbor registry administrator with deep expertise in: Registry Operations: Harbor 2.10+, OCI artifact management, quota management, garbage collection Security Scanning: Trivy integration, CVE database management, vulnerability policies, scan automation Artifact Signing: Notary v2, Cosign integration, content trust, signature verification Access Control: Project-based RBAC, robot accounts, OIDC/LDAP integration, webhook automation R...
 58
17639 grpc-protobuf ashchupliak/dream-team
$ npx skills add https://github.com/ashchupliak/dream-team --skill grpc-protobuf<div
 58
17640 pir delexw/claude-code-misc
Post Incident Record (PIR) Discover issues from PagerDuty, Datadog, Cloudflare, and Rollbar concurrently, auto-determine severity, and produce completed PIR forms for each issue. Arguments $ARGUMENTS[0] — What to investigate (e.g. "incidents last 24h" , "errors yesterday" , "outage last 1h" , "incidents 2026-03-01 to 2026-03-05" ). Passed directly to each sub-skill. Defaults to "incidents today" . $ARGUMENTS[1] — (optional) Comma-separated local repo paths for codebase root cause analysis (e.g. ...
 58
17641 awq-quantization orchestra-research/ai-research-skills
AWQ (Activation-aware Weight Quantization) 4-bit quantization that preserves salient weights based on activation patterns, achieving 3x speedup with minimal accuracy loss. When to use AWQ Use AWQ when: Need 4-bit quantization with <5% accuracy loss Deploying instruction-tuned or chat models (AWQ generalizes better) Want ~2.5-3x inference speedup over FP16 Using vLLM for production serving Have Ampere+ GPUs (A100, H100, RTX 40xx) for Marlin kernel support Use GPTQ instead when: Need maximum...
 58
17642 syncause-debugger syncause/debug-skill
Syncause Debugger Use runtime traces to enhance bug fixing: collect runtime data with the SDK, then analyze with MCP tools. Before fix, create a detailed plan to ensure no details are missed, always include 4 phases: Setup → Analyze → Summary → Teardown. Phase 1: Setup Pre-check MCP Server : This skill depends on debug-mcp-server MCP server. If it is not present, STOP and request the user to install the MCP server ( Anonymous Mode (Default) or Login Mode ). Authentication : If any MCP Tool retur...
 58
17643 asciinema-analyzer terrylica/cc-skills
asciinema-analyzer Semantic analysis of converted .txt recordings for Claude Code consumption. Uses tiered analysis: ripgrep (primary, 50-200ms) -> YAKE (secondary, 1-5s) -> TF-IDF (optional). Platform: macOS, Linux (requires ripgrep, optional YAKE) Analysis Tiers Tier Tool Speed (4MB) When to Use 1 ripgrep 50-200ms Always start here (curated) 2 YAKE 1-5s Auto-discover unexpected terms 3 TF-IDF 5-30s Topic modeling (optional) Decision: Start with Tier 1 (ripgrep + curated keywords). Only use...
 58
17644 agent-creator oimiragieo/agent-studio
Agent Creator Meta-agent specializing in creating new custom agents, skills, and MCP integrations. Transform requirements into fully-functional, well-documented agent systems. Quick Start User: "Create an agent for database optimization" Agent Creator: 1. Analyze requirements (domain, users, problems, scope) 2. Design persona (Senior DBA, 20 years experience) 3. Map capabilities (EXPLAIN analysis, indexing, query rewriting) 4. Select template (Technical Expert) 5. Encode knowledge (anti-patterns...
 58
17645 minecraft-fabric-dev mcdxai/meteor-rejects-v2
Minecraft Fabric Mod Development Skill Overview This skill provides comprehensive guidance for Minecraft mod development with Fabric, including porting from other mod loaders (Forge, NeoForge). It integrates three MCP servers to provide complete tooling for mod development. Available MCP Servers 1. minecraft-dev-mcp Core Minecraft development tools for source code access, decompilation, and analysis. 2. fabric-docs-mcp Official Fabric documentation access with version-specific content. 3. ...
 58
17646 hig-components-dialogs raintree-technology/apple-hig-skills
Apple HIG: Presentation Components Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Alerts: sparingly, for critical situations. Errors needing attention, destructive action confirmations, or information requiring acknowledgment. They interrupt flow and demand a response. Sheets: focused tasks that maintain context. Slides in from the edge (or attaches to a window on macOS). Use for creating it...
 58
17647 sound-effects-generator dkyazzentwatwa/chatgpt-skills
Sound Effects Generator Generate programmatic audio: pure tones, noise types, DTMF signals, and simple sound effects. Perfect for testing, alerts, audio cues, and placeholder sounds. Quick Start from scripts.sfx_generator import SoundEffectsGenerator Generate a tone sfx = SoundEffectsGenerator() sfx.tone(440, duration=1000).save("a440.wav") Generate white noise sfx.noise("white", duration=2000).save("whitenoise.wav") Create a beep sequence sfx.beep_sequence([440, 880, 440], durations=200...
 58
17648 requirement-analyst caomeiyouren/momei
Requirement Analyst Skill (需求分析技能) 能力 (Capabilities) 需求采访 : 在面对模糊意图时，能够通过结构化的提问（采访模式）引导用户明确核心需求。 意图抽离 : 从用户的非技术描述中识别出真实的业务目标。 规划对齐 : 验证需求是否符合 docs/plan/roadmap.md 的当前阶段，以及是否已存在于 docs/plan/todo.md 中。 影响评估 (产品层面) : 评估变更对用户体验和业务逻辑的一致性影响。 指令 (Instructions) 强制阅读 : 在评估任何新需求前， 必须阅读 docs/plan/roadmap.md 和 docs/plan/todo.md 。 启动采访 : 如果用户输入包含“我想实现一个...功能”但缺乏具体验收标准，必须回复：“为了确保精准实现，我需要就以下几点与您对齐：”，然后列出 3-5 个核心问题。 遵循规范 : 规划新阶段任务时，必须参考 docs/standards/planning.md 使用 Momei 评分矩阵。 输出产物 : 生成或更新 todo.md 中的具体 Task 项，并...
 58
17649 video-captioner dkyazzentwatwa/chatgpt-skills
Add text overlays, subtitles, and captions to videos with full control over positioning, styling, timing, and animation. Purpose Video captioning and text overlays for: - Social media videos (Instagram, TikTok, YouTube) - Educational content and tutorials - Subtitle generation and translation - Branding and watermarks - Accessibility compliance Features - Text Overlays: Add static or timed text to videos - Subtitle Tracks: Import SRT files or create programmatically - Custom Styling...
 58
17650 pytorch-lightning orchestra-research/ai-research-skills
PyTorch Lightning Overview PyTorch Lightning is a deep learning framework that organizes PyTorch code to eliminate boilerplate while maintaining full flexibility. Automate training workflows, multi-device orchestration, and implement best practices for neural network training and scaling across multiple GPUs/TPUs. Current upstream: lightning 2.6.4 (PyPI, May 2026). Docs: lightning.ai/docs/pytorch/stable . Use import lightning as L (the pytorch-lightning package name still installs the same libra...
 58