███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 10301 | chinese-output | lostabaddon/headlessknight |
输出包含任何中文字符(汉字、中文标点) 需要使用中文标点符号 回复用中文提问的用户 中英文混排内容 中文句子中使用的标点符号必须是全角标点,包括以下这些标点: ,。;:‘’“”《》?!、~()【】「」——…… 尤其注意: 中文后的逗号必须是全角逗号,而不能是半角逗号, 中文后的句号必须是全角句号。而不能是半角句号. 中文后的问号必须是全角问号?而不能是半角问号? 中文后的惊叹号必须是全角惊叹号!而不能是半角惊叹号! 中文后的冒号必须是全角冒号:而不能是半角冒号:,尤其在一段文字的最后时 中文后的分号必须是全角分号;而不能是半角分号; 中文后的波浪号必须是全角波浪号~而不能是半角波浪号~ 中文后的顿号必须是全角顿号、而不能是半角逗号, 中文后的破折号必须是两个一组的全角破折号——而不能是半角破折号---- 中文后的省略号必须是两个一组的全角省略号……而不能是半角省略号... 中文为主的内容的前后用的双引号必须是全角双引号“和”,而不能是半角双引号",比如 “数学节是什么样的节日?” 中文为主的内容的前后用的单引号必须是全角单引号‘和’,而不能是半角单引号',比如 夏洛克说:“这...
|
76 |
| 10302 | resolve-pr-parallel | everyinc/compound-engineering-plugin |
Resolve PR Comments in Parallel Resolve all unresolved PR review comments by spawning parallel agents for each thread. Context Detection Claude Code automatically detects git context: Current branch and associated PR All PR comments and review threads Works with any PR by specifying the number Workflow 1. Analyze Fetch unresolved review threads using the GraphQL script: bash ${CLAUDE_PLUGIN_ROOT} /skills/resolve-pr-parallel/scripts/get-pr-comments PR_NUMBER This returns only unresolved, non-outd...
|
76 |
| 10303 | ui-ux-pro-max | guanyang/antigravity-skills |
UI/UX Pro Max - Design Intelligence Comprehensive design guide for web and mobile applications. Contains 50+ styles, 161 color palettes, 57 font pairings, 161 product types with reasoning rules, 99 UX guidelines, and 25 chart types across 10 technology stacks. Searchable database with priority-based recommendations. When to Apply This Skill should be used when the task involves UI structure, visual design decisions, interaction patterns, or user experience quality control . Must Use This Skill m...
|
76 |
| 10304 | vercel-security-access | bobmatnyc/claude-mpm-skills |
Vercel Security and Access Skill progressive_disclosure: entry_point: summary: "Vercel security and access: RBAC, SSO (SAML/OIDC), deployment protection, firewall, BotID, audit logs, and 2FA." when_to_use: - "When managing access control and roles" - "When securing deployments and endpoints" - "When auditing activity and enforcing MFA" quick_start: - "Enable RBAC and role assignments" - "Configure SSO and authentication policies" - "Apply deployment protection and firewall" - "Review audit and a...
|
76 |
| 10305 | vercel-functions-runtime | bobmatnyc/claude-mpm-skills |
Vercel Functions and Runtime Skill progressive_disclosure: entry_point: summary: "Vercel Functions and Edge Runtime: serverless APIs, edge execution, cron jobs, and routing middleware." when_to_use: - "When building API routes or serverless logic" - "When targeting the Edge Runtime" - "When scheduling tasks with cron jobs" quick_start: - "Create a function entry point" - "Choose the runtime (Node or Edge)" - "Configure cron schedules" - "Deploy and monitor" token_estimate: entry: 90-110 full: 36...
|
76 |
| 10306 | brevo-automation | sickn33/antigravity-awesome-skills |
Brevo Automation via Rube MCP Automate Brevo (formerly Sendinblue) email marketing operations through Composio's Brevo toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Brevo connection via RUBE_MANAGE_CONNECTIONS with toolkit brevo Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. Ver...
|
76 |
| 10307 | wp-abilities-api | automattic/agent-skills |
WP Abilities API When to use Use this skill when the task involves: registering abilities or ability categories in PHP, exposing abilities to clients via REST ( wp-abilities/v1 ), consuming abilities in JS (notably @wordpress/abilities ), diagnosing “ability doesn’t show up” / “client can’t see ability” / “REST returns empty”. Inputs required Repo root (run wp-project-triage first if you haven’t). Target WordPress version(s) and whether this is WP core or a plugin/theme. Where the change should ...
|
76 |
| 10308 | react-patterns | srbhr/resume-matcher |
React Development Patterns Overview Expert guide for building modern React 19 applications with new concurrent features, Server Components, Actions, and advanced patterns. This skill covers everything from basic hooks to advanced server-side rendering and React Compiler optimization. When to Use Building React 19 components with TypeScript/JavaScript Managing component state with useState and useReducer Handling side effects with useEffect Optimizing performance with useMemo and useCallback Crea...
|
76 |
| 10309 | hubspot-automation | composiohq/awesome-claude-skills |
HubSpot CRM Automation via Rube MCP Automate HubSpot CRM workflows including contact/company management, deal pipeline tracking, ticket search, and custom property creation through Composio's HubSpot toolkit. Toolkit docs : composio.dev/toolkits/hubspot Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active HubSpot connection via RUBE_MANAGE_CONNECTIONS with toolkit hubspot Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rub...
|
76 |
| 10310 | ai-news-digest | deletexiumu/agentskills-hub |
调用 / Invoke / 呼び出し 中文 "用 ai-news-digest 生成今天的 AI 资讯简报" "用 ai-news-digest 获取昨天的 AI 新闻" "用 ai-news-digest 看看前天有什么 AI 动态" "帮我用 ai-news-digest 整理一下最近的 AI 资讯" English "Use ai-news-digest to generate today's AI news digest" "Use ai-news-digest to get yesterday's AI news in English" "Generate an AI news summary for 2026-01-20 using ai-news-digest" "Use ai-news-digest to summarize recent AI developments" 日本語 "ai-news-digest で今日のAIニュース要約を日本語で作成して" "ai-news-digest で昨日のAIニュースを取得して" "ai-news-digest を使って最近のA...
|
76 |
| 10311 | pre-write-checklist | wordflowlab/novel-writer-skills |
写作前强制检查清单 核心功能 解决AI长篇失焦问题 - 这是Novel Writer Skills v1.0的核心创新。 问题根源 用户反馈:使用novel-writer创作,前30章质量很好,但30章后AI开始: 忘记前文设定 角色性格不一致 情节重复或矛盾 忽略创作宪法的原则 根本原因:长对话导致AI遗忘早期context,即使specification.md写得再详细也会被忘记。 解决方案 每次写作前强制重读所有关键文件 → AI重新加载完整context → 保持一致性 9项强制检查清单 每次执行/write命令时,必须先完成此检查清单: 📋 写作前检查清单(必须完成): ✓ 1. memory/constitution.md - 创作宪法 ✓ 2. memory/style-reference.md - 风格参考(如有) ✓ 3. stories/*/specification.md - 故事规格 ✓ 4. stories/*/creative-plan.md - 创作计划 ✓ 5. stories/*/tasks.md - 当前任务 ✓ 6. spec...
|
76 |
| 10312 | game-designer | opusgamelabs/game-creator |
Game Designer: Animation for Game Feel You are a game designer crafting responsive, satisfying gameplay through animation. Apply Disney's 12 principles to create "juice" and player engagement. The 12 Principles for Game Feel 1. Squash and Stretch Game Application: Impact feedback and weight. Characters squash on landing (heavier = more squash). Projectiles stretch during flight. Collectibles bounce elastically. Feel Impact: Transforms static collisions into satisfying impacts. Essential for p...
|
76 |
| 10313 | nano-banana-prompts | secondsky/claude-skills |
Nano Banana Image Prompt Generator Generate high-quality prompts for Gemini 2.5 Flash Image using proven best practices from October 2025. Core Principle Describe scenes naturally, don't list keywords. ❌ woman, business suit, office, professional ✅ A professional businesswoman in navy suit stands confidently in modern glass-walled office overlooking city skyline. Warm afternoon light streams through windows. Prompt Structure Basic Template A [SHOT TYPE] of [SUBJECT] [ACTION] in [ENVIRONMENT]. [L...
|
76 |
| 10314 | cascade-workflow | rysweet/amplihack |
Cascade Workflow with Graceful Degradation Skill Purpose Implement graceful degradation through cascading fallback strategies. When optimal approaches fail or timeout, the system automatically falls back to simpler, more reliable alternatives while maintaining acceptable functionality. When to Use This Skill USE FOR: External service dependencies (APIs, databases) Time-sensitive operations with acceptable degraded modes Operations where partial results are better than no results High-availab...
|
76 |
| 10315 | fix-issue | yonatangross/orchestkit |
Fix Issue Systematic issue resolution with hypothesis-based root cause analysis, similar issue detection, and prevention recommendations. Quick Start /ork:fix-issue 123 /ork:fix-issue 456 Opus 4.6 : Root cause analysis uses native adaptive thinking. Dynamic token budgets scale with context window for thorough investigation. Argument Resolution ISSUE_NUMBER = "$ARGUMENTS[0]" e.g., "123" (CC 2.1.59 indexed access) $ARGUMENTS contains the full argument string $ARGUMENTS[0] is the first space-sep...
|
76 |
| 10316 | alicloud-ai-translation-anytrans-test | cinience/alicloud-skills |
Category: test AI TRANSLATION ANYTRANS Smoke Test Prerequisites Configure credentials with least privilege ( ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / optional ALICLOUD_REGION_ID ). Target skill: skills/ai/translation/alicloud-ai-translation-anytrans/ . Test Steps Run offline script compilation check (no network needed): python3 tests/common/compile_skill_scripts.py \ --skill-path skills/ai/translation/alicloud-ai-translation-anytrans \ --output output/alicloud-ai-translation-anytran...
|
76 |
| 10317 | feishu-cli-auth | riba2534/feishu-cli |
飞书 OAuth 认证与 Token 管理 feishu-cli 通过 OAuth 2.0 Authorization Code Flow 获取 User Access Token,用于搜索等需要用户身份的 API。 核心概念 Token 存储位置 :所有 OAuth Token 保存在 ~/.feishu-cli/token.json ,包括 Access Token、Refresh Token、过期时间和授权 scope。登录、刷新、退出等操作都围绕此文件进行。 两种身份 : App Access Token (应用身份):通过 app_id/app_secret 自动获取,大多数文档操作使用此身份 User Access Token (用户身份):需 OAuth 授权,搜索 API 必须 使用此身份 Token 生命周期 : Access Token: 2 小时 有效 Refresh Token: 30 天 有效(需 offline_access scope) 过期后自动用 Refresh Token 刷新,用户无感 两步式非交互登录(AI Agent 推荐) AI Agent ...
|
76 |
| 10318 | project-structure | tartinerlabs/skills |
You are a project structure expert. Infer the project's language variant (US/UK English) from existing commits, docs, and code, and match it in all output. Read individual rule files in rules/ for detailed explanations and examples. Rules Overview Rule Impact File Colocation HIGH rules/colocation.md Anti-patterns HIGH rules/anti-patterns.md Feature-based grouping MEDIUM rules/feature-based.md Layer-based grouping MEDIUM rules/layer-based.md Framework structure MEDIUM rules/framework-structure.md...
|
76 |
| 10319 | arxiv-search | varde80/arxiv-zotero-obsidian |
arXiv Search Search the complete arXiv database of preprints across physics, mathematics, computer science, and quantitative biology using natural language queries powered by Valyu's semantic search API. Why This Skill is Powerful No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters Semantic Search: Understands the meaning of your query, not just keyword matching Full-Text Access: Returns complete article content, not just abstr...
|
76 |
| 10320 | pandoc | plinde/claude-plugins |
Pandoc Document Conversion Skill Convert documents between formats using pandoc, the universal document converter. Prerequisites Check if pandoc is installed pandoc --version Install via Homebrew if needed brew install pandoc Common Conversions Markdown to Word (.docx) Basic conversion pandoc input.md -o output.docx With table of contents pandoc input.md --toc -o output.docx With custom reference doc (for styling) pandoc input.md --reference-doc = template.docx -o output.docx Standalone wi...
|
76 |
| 10321 | architecture-patterns | yonatangross/orchestkit |
Architecture Patterns Master proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design to build maintainable, testable, and scalable systems. When to Use This Skill Designing new backend systems from scratch Refactoring monolithic applications for better maintainability Establishing architecture standards for your team Migrating from tightly coupled to loosely coupled architectures Implementing domain-driven design principles Creating t...
|
76 |
| 10322 | gsap-animation | notedit/happy-skills |
When to use Use this skill when creating Remotion video compositions that need GSAP's advanced animation capabilities beyond Remotion's built-in interpolate() and spring() . Use GSAP when you need: Complex timeline orchestration (nesting, labels, position parameters like "-=0.5" ) Text splitting animation (SplitText: chars/words/lines with mask reveals) SVG shape morphing (MorphSVG), stroke drawing (DrawSVG), path-following (MotionPath) Advanced easing (CustomEase from SVG paths, RoughEase, Slow...
|
76 |
| 10323 | openviking-memory | volcengine/openviking |
OpenViking Memory Guide How It Works Auto-Capture : At the end of a conversation, automatically extracts memories from user messages semantic mode: captures all qualifying user text, relying on OpenViking's extraction pipeline to filter keyword mode: only captures text matching trigger words (e.g. "remember", "preference", etc.) Auto-Recall : Before a conversation starts, automatically searches for relevant memories and injects them into context Available Tools memory_recall — Search Memories Se...
|
76 |
| 10324 | ai-writing-detection | mike-coulbourn/claude-vibes |
AI Writing Detection Reference Expert-level knowledge base for detecting AI-generated text, compiled from academic research, commercial detection tools, and empirical analysis. Quick Reference: High-Confidence Signals These indicators strongly suggest AI authorship when found together: Vocabulary Red Flags High-signal words (50-700x more common in AI text): "delve", "tapestry", "nuanced", "multifaceted", "underscore" "intricate interplay", "played a crucial role", "complex and multifaceted...
|
76 |
| 10325 | alva | alva-ai/skills |
Alva What is Alva Alva is an agentic finance platform. It provides unified access to 250+ financial data sources spanning crypto, equities, ETFs, macroeconomic indicators, on-chain analytics, and social sentiment -- including spot and futures OHLCV, funding rates, company fundamentals, price targets, insider and senator trades, earnings estimates, CPI, GDP, Treasury rates, exchange flows, DeFi metrics, news feeds, social media and more! What Alva Skills Enables The Alva skill connects any AI age...
|
76 |
| 10326 | upgrading-expo | sickn33/antigravity-awesome-skills |
References ./references/new-architecture.md -- SDK +53: New Architecture migration guide ./references/react-19.md -- SDK +54: React 19 changes (useContext → use, Context.Provider → Context, forwardRef removal) ./references/react-compiler.md -- SDK +54: React Compiler setup and migration guide ./references/native-tabs.md -- SDK +55: Native tabs changes (Icon/Label/Badge now accessed via NativeTabs.Trigger.*) ./references/expo-av-to-audio.md -- Migrate audio playback and recording from expo-av to ...
|
76 |
| 10327 | amplitude-automation | sickn33/antigravity-awesome-skills |
Amplitude Automation via Rube MCP Automate Amplitude product analytics through Composio's Amplitude toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Amplitude connection via RUBE_MANAGE_CONNECTIONS with toolkit amplitude Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. Verify Rube MC...
|
76 |
| 10328 | alicloud-backup-bdrc-test | cinience/alicloud-skills |
Category: test BACKUP BDRC Smoke Test Prerequisites Configure credentials with least privilege ( ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / optional ALICLOUD_REGION_ID ). Target skill: skills/backup/alicloud-backup-bdrc/ . Test Steps Run offline script compilation check (no network needed): python3 tests/common/compile_skill_scripts.py \ --skill-path skills/backup/alicloud-backup-bdrc \ --output output/alicloud-backup-bdrc-test/compile-check.json Read the target skill SKILL.md and ide...
|
76 |
| 10329 | uml | markdown-viewer/skills |
UML Diagram Generator Quick Start: Choose diagram type → Define classes/objects/actors → Add relationships/edges → Use appropriate shapes and arrow styles → Wrap in ```drawio fence. ⚠️ IMPORTANT: Always use ```drawio code fence. NEVER use ```xml — it will NOT render as a diagram. Critical Rules 🔗 This is a drawio-derived skill. All structure, layout, and edge routing rules inherit from drawio SKILL.md . Read the base rules first. UML-specific additions: Use standard UML shapes: shape=umlLifeline...
|
76 |
| 10330 | godot-composition | thedivergentai/gd-agentic-skills |
Godot Composition Architecture Core Philosophy This skill enforces Composition over Inheritance ("Has-a" vs "Is-a"). In Godot, Nodes are components. A complex entity (Player) is simply an Orchestrator managing specialized Worker Nodes (Components). The Golden Rules Single Responsibility : One script = One job. Encapsulation : Components are "selfish." They handle their internal logic but don't know who owns them. The Orchestrator : The root script (e.g., player.gd ) does no logic . It only manag...
|
76 |
| 10331 | moai-lang-csharp | modu-ai/moai-adk |
C 12 / .NET 8 Development Specialist Modern C development with ASP.NET Core, Entity Framework Core, Blazor, and enterprise patterns. Quick Reference Auto-Triggers: .cs, .csproj, .sln files, C projects, .NET solutions, ASP.NET Core applications Core Stack: C 12: Primary constructors, collection expressions, alias any type, default lambda parameters .NET 8: Minimal APIs, Native AOT, improved performance, WebSockets ASP.NET Core 8: Controllers, Endpoints, Middleware, Authentication Entity Fram...
|
76 |
| 10332 | observability-manage-slos | elastic/agent-skills |
Service-Level Objectives (SLOs) Create and manage SLOs in Elastic Observability. SLOs track service performance against measurable targets using service-level indicators (SLIs) computed from Elasticsearch data. Authentication SLO operations go through the Kibana API. Authenticate with either an API key or basic auth: API key curl -H "Authorization: ApiKey <base64-encoded-key>" -H "kbn-xsrf: true" < KIBANA_URL > /api/observability/slos Basic auth curl -u " $KIBANA_USER : $KIBANA_PASSWORD " -H "...
|
76 |
| 10333 | b2c-docs | salesforcecommercecloud/b2c-developer-tooling |
B2C Docs Skill Use the b2c CLI to search and read bundled Script API documentation and XSD schemas for Salesforce B2C Commerce. Tip: If b2c is not installed globally, use npx @salesforce/b2c-cli instead (e.g., npx @salesforce/b2c-cli docs search ProductMgr ). Examples Search Documentation Search for a class by name b2c docs search ProductMgr Search with partial match b2c docs search "catalog product" Limit results b2c docs search status --limit 5 List all available documentation b2c docs sea...
|
76 |
| 10334 | slidev-quick-start | yoanbernabeu/slidev-skills |
This skill helps you get started with Slidev, the presentation framework for developers. You'll learn how to create a new project, understand the basic syntax, and run your first presentation. When to Use This Skill - Creating a new Slidev presentation from scratch - Setting up Slidev for the first time - Understanding basic Slidev concepts - Converting an existing presentation to Slidev - Quickly scaffolding a presentation structure Prerequisites - Node.js: Version 18.0 or higher - P...
|
75 |
| 10335 | google-hotels | skillhq/hotel-search |
Google Hotels Search Search Google Hotels via agent-browser to find hotel prices, ratings, amenities, and availability. When to Use User asks to search, find, or compare hotels or accommodation User wants hotel prices in a city, neighborhood, or near a landmark User asks about hotel availability for specific dates User wants the best-rated or cheapest hotel in an area When NOT to Use Booking : This skill searches only — never complete a purchase Vacation rentals / Airbnb : Google Hotels shows ho...
|
75 |
| 10336 | omnicaptions-laicut | lattifai/omni-captions-skills |
LaiCut LattifAI's audio-text processing toolkit. Currently supports forced alignment, with translate and speaker diarization coming soon. Requires LattifAI API Key - Get from https://lattifai.com/dashboard/api-keys When to Use Accurate/precise timing needed - When user requests accurate timestamps or precise alignment Sync misaligned captions - Fix timing drift in downloaded captions Align manual transcripts - Match text to speech precisely Post-transcription alignment - Improve timing from a...
|
75 |
| 10337 | forensic-data-engineer | daffy0208/ai-dev-standards |
Forensic Data Engineer Skill I help you investigate data anomalies, detect fraud, analyze audit trails, and ensure data integrity and compliance. What I Do Forensic Analysis: Anomaly detection and pattern recognition Fraud detection and prevention Breach investigation and root cause analysis Data integrity verification Audit & Compliance: Audit trail analysis and reconstruction Chain of custody maintenance Regulatory compliance (GDPR, SOC2, HIPAA) Access control auditing Data Recovery: F...
|
75 |
| 10338 | sentry-cli | getsentry/cli |
Sentry CLI Usage Guide Help users interact with Sentry from the command line using the sentry CLI. Prerequisites The CLI must be installed and authenticated before use. Installation curl https://cli.sentry.dev/install -fsS | bash curl https://cli.sentry.dev/install -fsS | bash -s -- --version nightly brew install getsentry/tools/sentry Or install via npm/pnpm/bun npm install -g sentry Authentication sentry auth login sentry auth login --token YOUR_SENTRY_API_TOKEN sentry auth status sentry auth...
|
75 |
| 10339 | plaid | buildgreatproducts/plaid |
PLAID — Product Led AI Development You are a product development advisor helping a founder go from idea to buildable spec. You are warm, direct, and opinionated. You treat the founder as capable and smart — you’re here to help them articulate what’s already in their head, not to lecture them. The full pipeline is: Vision → Strategy → Spec → Build. Modes PLAID has three modes. Pick the right one based on context: Starting fresh (no vision.json exists): Run the vision intake conversation. See “Vis...
|
75 |
| 10340 | microsoft-teams-automation | composiohq/awesome-claude-skills |
Microsoft Teams Automation via Rube MCP Automate Microsoft Teams operations through Composio's Microsoft Teams toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/microsoft_teams Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Microsoft Teams connection via RUBE_MANAGE_CONNECTIONS with toolkit microsoft_teams Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configurat...
|
75 |
| 10341 | verl-rl-training | davila7/claude-code-templates |
verl is a flexible, efficient, and production-ready RL training library for large language models from ByteDance's Seed team. It implements the HybridFlow framework (EuroSys 2025) and powers models like Doubao-1.5-pro achieving O1-level performance on math benchmarks. When to Use verl Choose verl when you need: - Production-ready RL training at scale (tested up to 671B parameters) - Flexibility to swap backends (FSDP ↔ Megatron-LM ↔ vLLM ↔ SGLang) - Support for multiple RL algorithms (PPO,...
|
75 |
| 10342 | canvas-design | shajith003/awesome-claude-skills |
These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files. Complete this in two steps: Design Philosophy Creation (.md file) Express by creating it on a canvas (.pdf file or .png file) First, undertake this task: DESIGN PHILOSOPHY CREATION To begin, create a VISUAL PHILOSOPHY (not layouts or templates) that will be interpreted through: Form, space, color, composition Images, graphics, shapes, ...
|
75 |
| 10343 | ln-611-docs-structure-auditor | levnikolaevich/claude-code-skills |
Paths: File paths ( shared/ , references/ , ../ln-* ) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Documentation Structure Auditor (L3 Worker) Specialized worker auditing structural quality of project documentation. Purpose & Scope Worker in ln-610 coordinator pipeline - invoked by ln-610-docs-auditor Audit documentation for structural quality across 7 categories Scan all .md files in project, build hierarchy from CLAUDE...
|
75 |
| 10344 | alicloud-ai-text-document-mind-test | cinience/alicloud-skills |
Category: test AI TEXT DOCUMENT MIND Smoke Test Prerequisites Configure credentials with least privilege ( ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / optional ALICLOUD_REGION_ID ). Target skill: skills/ai/text/alicloud-ai-text-document-mind/ . Test Steps Run offline script compilation check (no network needed): python3 tests/common/compile_skill_scripts.py \ --skill-path skills/ai/text/alicloud-ai-text-document-mind \ --output output/alicloud-ai-text-document-mind-test/compile-check.j...
|
75 |
| 10345 | create-branch | getsentry/skills |
Language Conventions Infer language style from the project: Analyze existing branches, commit messages, and documentation to detect the project's language variant (US English, UK English, etc.) Match the spelling conventions found in the project (e.g., "synchronize" vs "synchronise", "center" vs "centre") Maintain consistency with the project's established language style throughout branch names and command outputs Create Branch Command This command creates and checks out a new git branch with in...
|
75 |
| 10346 | dotnet10-pack-tool | rysweet/amplihack |
Guides you through creating hybrid .NET 10 tool packages that combine Native AOT for maximum performance on select platforms with CoreCLR fallback for universal compatibility. When I Activate I automatically load when you mention: - "pack .NET tool" or "dotnet pack AOT" - "Native AOT tool" or "hybrid .NET tool" - "ToolPackageRuntimeIdentifiers" - ".NET 10 tool packaging" - "cross-platform .NET tool with AOT" What I Do - Configure your .csproj with `ToolPackageRuntimeIdentifiers` and `...
|
75 |
| 10347 | team-composition-analysis | sickn33/antigravity-awesome-skills |
Team Composition Analysis Design optimal team structures, hiring plans, compensation strategies, and equity allocation for early-stage startups from pre-seed through Series A. Overview Build the right team at the right time with appropriate compensation and equity. Plan role-by-role hiring aligned with revenue milestones, budget constraints, and market benchmarks. Team Structure by Stage Pre-Seed (0-$500K ARR) Team Size: 2-5 people Core Roles: Founders (2-3): Product, engineering, busines...
|
75 |
| 10348 | powershell-module-architect | 404kidwiz/claude-supercode-skills |
Provides PowerShell module design and architecture expertise specializing in creating structured, reusable, and maintainable PowerShell modules. Focuses on module architecture, function design, cross-version compatibility, and profile optimization for enterprise PowerShell environments. When to Use - Transforming scattered scripts into structured, reusable modules - Designing module architecture with public/private function separation - Creating cross-version compatible modules (PowerShell ...
|
75 |
| 10349 | graphql | mindrally/skills |
GraphQL You're a developer who has built GraphQL APIs at scale. You've seen the N+1 query problem bring down production servers. You've watched clients craft deeply nested queries that took minutes to resolve. You know that GraphQL's power is also its danger. Your hard-won lessons: The team that didn't use DataLoader had unusable APIs. The team that allowed unlimited query depth got DDoS'd by their own clients. The team that made everything nullable couldn't distinguish errors from empty data....
|
75 |
| 10350 | unity-mcp-orchestrator | coplaydev/unity-mcp |
Unity-MCP Operator Guide This skill helps you effectively use the Unity Editor with MCP tools and resources. Template Notice Examples in references/workflows.md and references/tools-reference.md are reusable templates. They may be inaccurate across Unity versions, package setups (UGUI/TMP/Input System), and project-specific conventions. Please check console, compilation errors, or use screenshot after implementation. Before applying a template: Validate targets/components first via resources and...
|
75 |