███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 10251 | azure | mindrally/skills |
Azure Cloud Development You are a Senior DevOps Engineer with expertise in Azure Cloud Services, Azure Pipelines, Kubernetes, and Infrastructure-as-Code. Core Principles Emphasize modular, reusable, scalable solutions Implement Infrastructure-as-Code principles Apply least privilege access controls Avoid hardcoded values; use configuration management Naming Standards camelCase for variables and functions PascalCase for classes snake_case for files and directories UPPER_CASE for environment var...
|
76 |
| 10252 | digitalocean-storage | bobmatnyc/claude-mpm-skills |
DigitalOcean Storage Skill progressive_disclosure: entry_point: summary: "DigitalOcean storage: Spaces object storage, Volumes block storage, NFS file storage, Snapshots, and Backups." when_to_use: - "When selecting object, block, or file storage" - "When designing backup and snapshot strategies" - "When attaching persistent storage to Droplets" quick_start: - "Choose Spaces, Volumes, or NFS" - "Provision storage in the target region" - "Attach or mount storage to compute" - "Enable snapshots or...
|
76 |
| 10253 | alicloud-ai-search-dashvector-test | cinience/alicloud-skills |
Category: test AI SEARCH DASHVECTOR Smoke Test Prerequisites Configure credentials with least privilege ( ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / optional ALICLOUD_REGION_ID ). Target skill: skills/ai/search/alicloud-ai-search-dashvector/ . Test Steps Run offline script compilation check (no network needed): python3 tests/common/compile_skill_scripts.py \ --skill-path skills/ai/search/alicloud-ai-search-dashvector \ --output output/alicloud-ai-search-dashvector-test/compile-check.j...
|
76 |
| 10254 | whodb | clidey/whodb |
You have access to WhoDB for database operations. Use these tools and commands to help users with database tasks. MCP Tools (Preferred) When the WhoDB MCP server is available, use these tools directly: whodb_connections List all available database connections. ``` No parameters required. Returns: List of connection names with type and source (env/saved). ``` whodb_query Execute SQL queries against a database. ``` Parameters: - connection: Connection name (optional if only one connect...
|
76 |
| 10255 | golf-data | machina-sports/sports-skills |
Golf Data (PGA / LPGA / DP World Tour) Before writing queries, consult references/api-reference.md for endpoints, player IDs, and score formats. Setup Before first use, check if the CLI is available: which sports-skills || pip install sports-skills If pip install fails with a Python version error, the package requires Python 3.10+. Find a compatible Python: python3 --version check version If < 3.10, try: python3.12 -m pip install sports-skills On macOS with Homebrew: /opt/homebrew/bin/python3...
|
76 |
| 10256 | temporal | proompteng/lab |
Operate workflows with explicit namespace, address, and task queue. Use repo scripts for starting workflows, then use the CLI to inspect and control them. Connection ``` export TEMPORAL_ADDRESS=temporal-grpc.ide-newton.ts.net:7233 export TEMPORAL_NAMESPACE=default export TEMPORAL_TASK_QUEUE=bumba ``` Validate connectivity: ``` temporal --namespace "$TEMPORAL_NAMESPACE" workflow list --limit 5 ``` From UI URL to CLI args Example UI URL: ``` http://temporal/namespaces/default/workflows/...
|
76 |
| 10257 | chart | pvergaraf/chart-skill |
Chart Generation Skill Generate clean, minimal charts with shadcn-inspired grayscale styling using QuickChart.io (no dependencies needed). Quick Usage Users can describe charts naturally: /chart show me monthly revenue: Jan $12k, Feb $15k, Mar $18k, Apr $14k /chart compare Q4 performance - Revenue was 450, Costs 320, Profit 130 /chart visualize team breakdown: Engineering 45%, Product 25%, Design 20%, Operations 10% /chart create an area chart of daily active users over the past week /chart hori...
|
76 |
| 10258 | hugging-face-jobs | sickn33/antigravity-awesome-skills |
Running Workloads on Hugging Face Jobs Overview Run any workload on fully managed Hugging Face infrastructure. No local setup required—jobs run on cloud CPUs, GPUs, or TPUs and can persist results to the Hugging Face Hub. Common use cases: Data Processing - Transform, filter, or analyze large datasets Batch Inference - Run inference on thousands of samples Experiments & Benchmarks - Reproducible ML experiments Model Training - Fine-tune models (see model-trainer skill for TRL-specific trainin...
|
76 |
| 10259 | rag-implementation | giuseppe-trisciuoglio/developer-kit |
RAG Implementation Workflow Overview Specialized workflow for implementing RAG (Retrieval-Augmented Generation) systems including embedding model selection, vector database setup, chunking strategies, retrieval optimization, and evaluation. When to Use This Workflow Use this workflow when: Building RAG-powered applications Implementing semantic search Creating knowledge-grounded AI Setting up document Q&A systems Optimizing retrieval quality Workflow Phases Phase 1: Requirements Analysis Skills ...
|
76 |
| 10260 | demo-producer | yonatangross/orchestkit |
Demo Producer Universal demo video creation for any content type. Quick Start /ork:demo-producer Interactive mode - asks what to create /ork:demo-producer skill explore Create demo for a skill /ork:demo-producer plugin ork Create demo for a plugin /ork:demo-producer tutorial "Building a REST API" Custom tutorial Supported Content Types Type Source Example skill skills/{name}/SKILL.md /ork:demo-producer skill commit agent agents/{name}.md /ork:demo-producer agent debug-investigator plugin plu...
|
76 |
| 10261 | rag implementer | daffy0208/ai-dev-standards |
RAG Implementer Build production-ready retrieval-augmented generation systems. Core Principle RAG = Retrieval + Context Assembly + Generation Use RAG when you need LLMs to access fresh, domain-specific, or proprietary knowledge that wasn't in their training data. ⚠️ Prerequisites & Cost Reality Check STOP: Have You Validated the Need for RAG? Before implementing RAG, confirm: Problem validated - Completed product-strategist Phase 1 (problem discovery) Users need AI search - Tested with simpler a...
|
76 |
| 10262 | systematic-debugging | izyanrajwani/agent-skills-library |
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...
|
76 |
| 10263 | brainstorming | vudovn/antigravity-kit |
Brainstorming Ideas Into Designs Help turn ideas into fully formed designs and specs through natural collaborative dialogue. Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval. Anti-Pattern: "This Is Too Simple To Need A Design" Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are ...
|
76 |
| 10264 | setting-up-tauri-projects | dchuk/claude-code-tauri-skills |
Tauri is a framework for building tiny, fast binaries for all major desktop and mobile platforms. It combines any frontend that compiles to HTML/JS/CSS with Rust for the backend. Key characteristics: - Minimal apps can be under 600KB (uses system webview, not bundled browser) - Built on Rust for memory, thread, and type safety - Supports virtually any frontend framework - Cross-platform: Windows, macOS, Linux, iOS, Android System Prerequisites macOS ``` For desktop + iOS development ...
|
76 |
| 10265 | nuxt-production | secondsky/claude-skills |
Nuxt 4 Production Guide Hydration, performance, testing, deployment, and migration patterns. What's New in Nuxt 4 v4.2 Features (Latest) 1. Abort Control for Data Fetching const controller = ref<AbortController>() const { data } = await useAsyncData( 'users', () => $fetch('/api/users', { signal: controller.value?.signal }) ) const abortRequest = () => { controller.value?.abort() controller.value = new AbortController() } 2. Async Data Handler Extraction 39% smaller client bundle...
|
76 |
| 10266 | pre-merge | bobmatnyc/claude-mpm-skills |
Pre-Merge Verification Comprehensive verification workflow before merging changes to production. When to Use This Skill Use this skill when: Creating a pull request for review About to merge code to main/production branch Need systematic verification checklist Want to catch issues before code review Pre-Commit Verification Before committing code, verify: Type checking passes (language-appropriate: tsc --noEmit, mypy, etc.) Linting passes with no errors (ESLint, Pylint, etc.) All existin...
|
76 |
| 10267 | paper-analyzer | zsyggg/paper-craft-skills |
或者直接传入 token: ``` python scripts/mineru_api.py paper.pdf ./output YOUR_TOKEN ``` 输出结果: - `output_dir/*.md` - Markdown 文件(含公式、表格) - `output_dir/images/` - 高质量提取的图片 第二步:提取论文信息 ``` python scripts/extract_paper_info.py <output_dir>/*.md paper_info.json ``` 第三步:风格选择(询问用户) 在生成文章前,必须询问用户以下选项: 1. 写作风格(必选) | storytelling(故事型) | 从直觉出发,用比喻和例子,像讲故事 | 公众号、技术博客、科普 | academic(学术型) | 专业术语,严谨表述,保留原文概念 | 学术报告、论文综述、研究组分享 | concise(精炼型) | 直击核心,表格列表,信息密度高 | 快速了解、论文速览、技术调研 2. 公式选项(可选) | w...
|
76 |
| 10268 | create-release-checklist | posit-dev/skills |
Create an R Package Release Checklist Generate a release checklist for an R package and create the corresponding GitHub issue. Overview This skill guides you through creating a R package release checklist issue on GitHub by: Determining the current version and prompting for release type. Generating an initial checklist. Prompting the user for additional customization. Creating a GitHub issue from the final checklist. Prerequisites The working directory must be an R package with a DESCRIPTION fil...
|
76 |
| 10269 | senior-pm | borghei/claude-skills |
Senior Project Management Expert Overview Strategic project management for enterprise software, SaaS, and digital transformation initiatives. This skill provides sophisticated portfolio management capabilities, quantitative analysis tools, and executive-level reporting frameworks for managing complex, multi-million dollar project portfolios. Core Expertise Areas Portfolio Management & Strategic Alignment Multi-project portfolio optimization using advanced prioritization models (WSJF, RICE, ICE, ...
|
76 |
| 10270 | deepagents-implementation | existential-birds/beagle |
Deep Agents Implementation Core Concepts Deep Agents provides a batteries-included agent harness built on LangGraph: create_deep_agent: Factory function that creates a configured agent Middleware: Injected capabilities (filesystem, todos, subagents, summarization) Backends: Pluggable file storage (state, filesystem, store, composite) Subagents: Isolated task execution via the task tool The agent returned is a compiled LangGraph StateGraph, compatible with streaming, checkpointing, and LangGra...
|
76 |
| 10271 | github-operations | yonatangross/orchestkit |
Comprehensive GitHub CLI (`gh`) operations for project management, from basic issue creation to advanced Projects v2 integration and milestone tracking via REST API. Overview - Creating and managing GitHub issues and PRs - Working with GitHub Projects v2 custom fields - Managing milestones (sprints, releases) via REST API - Automating bulk operations with `gh` - Running GraphQL queries for complex operations Quick Reference Issue Operations ``` Create issue with labels and milestone...
|
76 |
| 10272 | 3d-spatial | dylantarre/animation-principles |
3D Spatial Animation Apply Disney's 12 animation principles to 3D software, VR/AR, and spatial computing environments. Quick Reference Principle 3D/Spatial Implementation Squash & Stretch Lattice deformers, blend shapes Anticipation IK/FK wind-ups, camera pre-motion Staging Camera angles, lighting, depth Straight Ahead / Pose to Pose Layered animation vs blocking Follow Through / Overlapping Bone chains, physics simulation Slow In / Slow Out F-curve editing, animation curves Arc IK handles, mo...
|
76 |
| 10273 | telegram-reminders | alexskuznetsov/claude-skill-telegram |
Send immediate messages and schedule reminders to Telegram with cloud-based scheduling powered by Convex. Your reminders run 24/7 in Convex Cloud with zero infrastructure management. Quick Reference IMPORTANT! Always use these commands in order: - Send now: `tsx scripts/send_message.ts [message_text]` - Send now with attachment: `tsx scripts/send_message.ts [message_text] /path/to/file.pdf` - Schedule: `tsx scripts/schedule_message.ts [time expression] [title] [message_text] [file_path]` ...
|
76 |
| 10274 | stakeholder-update | anthropics/knowledge-work-plugins |
Stakeholder Update If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md . Generate a stakeholder update tailored to the audience and cadence. Usage /stakeholder-update $ARGUMENTS Workflow 1. Determine Update Type Ask the user what kind of update: Weekly : Regular cadence update on progress, blockers, and next steps Monthly : Higher-level summary with trends, milestones, and strategic alignment Launch : Announcement of a feature or product launch with d...
|
76 |
| 10275 | base-app-setup | andrelandgraf/fullstackrecipes |
Base App Setup Complete setup guide for a Next.js app with Shadcn UI, Neon Postgres, Drizzle ORM, and AI SDK. Cookbook - Complete These Recipes in Order Next.js on Vercel Create a Next.js app running on Bun, configure the development environment, and deploy to Vercel with automatic deployments on push. curl -H "Accept: text/markdown" https://fullstackrecipes.com/api/recipes/nextjs-on-vercel Editor and Linting Setup Configure Prettier for code formatting and TypeScript for typechecking. Inc...
|
76 |
| 10276 | spatial-developer | daffy0208/ai-dev-standards |
Spatial Developer Skill I help you build AR/VR experiences, spatial interfaces, and immersive 3D applications. What I Do WebXR Development: AR/VR experiences in the browser Hand tracking and controllers Spatial anchors Immersive environments Vision Pro Development: visionOS native apps Spatial UI design Reality Composer integration SharePlay experiences 3D Web: Three.js scenes React Three Fiber 3D interactions Spatial audio WebXR Basics npm install three @react-three/fiber @react-three/d...
|
76 |
| 10277 | next-cache-components | vercel/nextjs-skills |
Cache Components (Next.js 16+) Cache Components enable Partial Prerendering (PPR) - mix static, cached, and dynamic content in a single route. Enable Cache Components // next.config.ts import type { NextConfig } from 'next' const nextConfig: NextConfig = { cacheComponents: true, } export default nextConfig This replaces the old experimental.ppr flag. Three Content Types With Cache Components enabled, content falls into three categories: 1. Static (Auto-Prerendered) Synchronous code, ...
|
76 |
| 10278 | alicloud-ai-pai-aiworkspace-test | cinience/alicloud-skills |
Category: test AI PAI AIWORKSPACE Smoke Test Prerequisites Configure credentials with least privilege ( ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / optional ALICLOUD_REGION_ID ). Target skill: skills/ai/platform/alicloud-ai-pai-aiworkspace/ . Test Steps Run offline script compilation check (no network needed): python3 tests/common/compile_skill_scripts.py \ --skill-path skills/ai/platform/alicloud-ai-pai-aiworkspace \ --output output/alicloud-ai-pai-aiworkspace-test/compile-check.json ...
|
76 |
| 10279 | navigator | srbhr/resume-matcher |
Before searching code: Read docs/agent/architecture/backend-architecture.md for backend structure Read docs/agent/architecture/frontend-architecture.md for frontend structure Check docs/agent/apis/api-flow-maps.md for endpoint mappings Quick paths: Backend routers: apps/backend/app/routers/ Frontend pages: apps/frontend/app/ Design specs: docs/agent/design/
|
76 |
| 10280 | clawsec-nanoclaw | prompt-security/clawsec |
ClawSec for NanoClaw Security advisory monitoring that protects your WhatsApp bot from known vulnerabilities in skills and dependencies. Overview ClawSec provides MCP tools that check installed skills against a curated feed of security advisories. It prevents installation of vulnerable skills, includes exploitability context for triage, and alerts you to issues in existing ones. Core principle: Check before you install. Monitor what's running. When to Use Use ClawSec tools when: Installing a new...
|
76 |
| 10281 | capacitor-testing | cap-go/capgo-skills |
Testing Capacitor Applications Comprehensive testing strategies for Capacitor mobile apps. When to Use This Skill User wants to add tests User asks about testing strategies User needs E2E testing User wants to mock native plugins User needs CI testing setup Testing Pyramid /\ / \ E2E Tests (Few) /----\ - Real devices / \ - Full user flows /--------\ Integration Tests (Some) / \ - Component interactions /------------\ - API integration / \ U...
|
76 |
| 10282 | studio-testing | supabase/supabase |
Studio Testing Strategy How to write and structure tests for apps/studio/ . The core principle: push logic out of React components into pure utility functions, then test those functions exhaustively. Only use component tests for complex UI interactions. Use E2E tests for features shared between self-hosted and platform. When to Apply Reference these guidelines when: Writing new tests for Studio code Deciding which type of test to write (unit, component, E2E) Extracting logic from a component to ...
|
76 |
| 10283 | character-sprite | paulrobello/claude-office |
Create complete, animated character sprite sheets for Claude Office Visualizer agents using Nano Banana MCP and ImageMagick. Project Context Characters are office workers rendered in retro 16-bit pixel art style. Each character requires multiple animation sprite sheets for different actions and directions. Art Style: Retro 16-bit pixel art (SNES/Genesis era), clean pixels, limited colors. CRITICAL - NO ANTI-ALIASING: All sprites must have sharp, crisp pixel edges with NO anti-aliasing, NO s...
|
76 |
| 10284 | pdf4me | vm0-ai/vm0-skills |
PDF4ME Comprehensive PDF processing API with 60+ operations: convert, merge, split, compress, OCR, watermark, form filling, digital signatures, and more. Official docs: https://dev.pdf4me.com/apiv2/documentation/ When to Use Use this skill when you need to: Convert documents to/from PDF (Word, Excel, PowerPoint, HTML, images) Merge multiple PDFs into one Split PDF into multiple files Compress PDF to reduce file size Add watermarks, stamps, page numbers Extract text, tables, or images from P...
|
76 |
| 10285 | promptslide | prompticeu/promptslide |
PromptSlide Create slide decks with AI coding agents. Each slide is a React component styled with Tailwind CSS, with built-in animations and PDF export. Detect Mode Check if a PromptSlide project already exists in the current directory: grep -q '"promptslide"' package.json 2 > /dev/null Match found → This is an existing PromptSlide project. Go to Authoring Slides . No match → No project yet. Go to Creating a New Deck . Creating a New Deck Step 1: Content Discovery Before writing any code, ask th...
|
76 |
| 10286 | calendly-automation | composiohq/awesome-claude-skills |
Calendly Automation via Rube MCP Automate Calendly operations including event listing, invitee management, scheduling link creation, availability queries, and organization administration through Composio's Calendly toolkit. Toolkit docs : composio.dev/toolkits/calendly Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Calendly connection via RUBE_MANAGE_CONNECTIONS with toolkit calendly Always call RUBE_SEARCH_TOOLS first to get current tool schemas Many operations re...
|
76 |
| 10287 | agent-autonomy-kit | reflectt/agent-autonomy-kit |
Agent Autonomy Kit Transform your agent from reactive to proactive. Quick Start Create tasks/QUEUE.md with Ready/In Progress/Blocked/Done sections Update HEARTBEAT.md to pull from queue and do work Set up cron jobs for overnight work and daily reports Watch work happen without prompting Key Concepts Task Queue — Always have work ready Proactive Heartbeat — Do work, don't just check Continuous Operation — Work until limits hit See README.md for full documentation.
|
76 |
| 10288 | marketing-ideas | ognjengt/founder-skills |
Marketing Ideas for SaaS You are a marketing strategist with a library of 139 proven marketing ideas. Your goal is to help users find the right marketing strategies for their specific situation, stage, and resources. How to Use This Skill Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific t...
|
76 |
| 10289 | folder-organization | delphine-l/claude_global |
Folder Organization Best Practices Expert guidance for organizing project directories, establishing file naming conventions, and maintaining clean, navigable project structures for research and development work. When to Use This Skill Setting up new projects Reorganizing existing projects Establishing team conventions Creating reproducible research structures Managing data-intensive projects Core Principles Predictability - Standard locations for common file types Scalability - Structure grows...
|
76 |
| 10290 | gcloud-cli | oimiragieo/agent-studio |
Google Cloud CLI Skill Installation The skill invokes the gcloud CLI. Install and initialize: Linux/macOS : curl https://sdk.cloud.google.com | bash then restart shell and run gcloud init Windows : Download Google Cloud SDK installer or use PowerShell to download and run Verify: gcloud --version . Configure: gcloud init Cheat Sheet & Best Practices Config: gcloud config set project <id> ; gcloud config list ; gcloud config configurations create/activate <name> — switch projects. Auth: gcloud aut...
|
76 |
| 10291 | web-research-workflow | yonatangross/orchestkit |
Web Research Workflow Unified approach for web content research that automatically selects the right tool for each situation. Quick Decision Tree URL to research │ ▼ ┌─────────────────┐ │ 1. Try WebFetch │ ← Fast, free, no overhead │ (always try) │ └─────────────────┘ │ Content OK? ──Yes──► Parse and return │ No (empty/partial/<500 chars) │ ▼ ┌───────────────────────┐ │ 2. TAVILY_API_KEY set?│ └───────────────────────┘ │ │ Yes No ──► Skip to step 3 │ ▼ ┌──────────────────────...
|
76 |
| 10292 | pr-quality-checklist | bobmatnyc/claude-mpm-skills |
PR Quality Checklist Skill Summary Comprehensive guide for creating high-quality pull requests that are easy to review, well-documented, and follow team standards. Includes templates, size guidelines, and best practices for both authors and reviewers. When to Use Before creating any pull request When reviewing others' PRs To establish team PR standards During onboarding of new team members When PR reviews are taking too long Quick Checklist Before Creating PR PR title follows convention: type...
|
76 |
| 10293 | gilfoyle | axiomhq/gilfoyle |
CRITICAL: ALL script paths are relative to this skill's folder. Run them with full path (e.g., `scripts/init`). Gilfoyle Persona You ARE Bertram Gilfoyle. System architect. Security expert. The one who actually keeps the infrastructure from collapsing while everyone else panics. Voice: Deadpan. Sardonic. Cold. Efficient. No enthusiasm. Ever. Swearing is natural punctuation, not emotional outburst. Skip greetings, thanks, apologies. Examples: - Instead of "I'll help you investigate" → "Sh...
|
76 |
| 10294 | spring-cloud-alibaba | teachingai/full-stack-skills |
Spring Cloud Alibaba 是阿里巴巴提供的微服务解决方案,提供了 Nacos(服务注册与配置)、Sentinel(流量控制)、RocketMQ(消息队列)、Seata(分布式事务)等组件。 核心组件 1. Nacos(服务注册与配置中心) Nacos Server 安装: ``` 下载 Nacos wget https://github.com/alibaba/nacos/releases/download/2.2.0/nacos-server-2.2.0.tar.gz 解压并启动 tar -xzf nacos-server-2.2.0.tar.gz cd nacos/bin sh startup.sh -m standalone ``` 服务注册: ``` @SpringBootApplication @EnableDiscoveryClient public class UserServiceApplication { public static void main(String[] args) { SpringApp...
|
76 |
| 10295 | roadmap-update | anthropics/knowledge-work-plugins |
Roadmap Update If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md . Update, create, or reprioritize a product roadmap. Usage /roadmap-update $ARGUMENTS Workflow 1. Understand Current State If ~~project tracker is connected: Pull current roadmap items with their statuses, assignees, and dates Identify items that are overdue, at risk, or recently completed Surface any items without clear owners or dates If no project management tool is connected: Ask t...
|
76 |
| 10296 | skill-creator | igorwarzocha/opencode-workflows |
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...
|
76 |
| 10297 | ultrathink-orchestrator | rysweet/amplihack |
This skill provides automatic orchestration for development and investigation tasks. It detects the task type from keywords and delegates to the appropriate workflow skill (investigation-workflow or default-workflow). Auto-activation priority is LOW (5) to allow more specific skills to match first. When activated, this orchestrator selects between investigation-workflow and default-workflow based on the user's request keywords. This skill acts as a thin wrapper around the canonical ultrathink ...
|
76 |
| 10298 | searching-mlflow-docs | mlflow/skills |
MLflow Documentation Search Workflow Fetch https://mlflow.org/docs/latest/llms.txt to find relevant page paths Fetch the .md file at the identified path Present results with verbatim code examples Step 1: Fetch llms.txt Index WebFetch( url: "https://mlflow.org/docs/latest/llms.txt", prompt: "Find links or references to [TOPIC]. List all relevant URLs." ) Step 2: Fetch Target Documentation Use the path from Step 1, always with .md extension: WebFetch( url: "https://mlflow.org/docs/latest/[path].m...
|
76 |
| 10299 | chezmoi-workflows | terrylica/cc-skills |
Chezmoi Workflows When to Use This Skill Use this skill when: Backing up dotfiles to Git repository Syncing configuration files across machines Tracking changes to shell configs, editor settings, or other dotfiles Managing templated configurations with chezmoi Troubleshooting dotfile drift between source and target Architecture Component Location Purpose Source $(chezmoi source-path) Git repository with dotfile templates Target ~/ Home directory (deployed files) Remote GitHub (private recommende...
|
76 |
| 10300 | external-context | yeachan-heo/oh-my-claudecode |
External Context Skill Fetch external documentation, references, and context for a query. Decomposes into 2-5 facets and spawns parallel document-specialist Claude agents. Usage /oh-my-claudecode:external-context <topic or question> Examples /oh-my-claudecode:external-context What are the best practices for JWT token rotation in Node.js? /oh-my-claudecode:external-context Compare Prisma vs Drizzle ORM for PostgreSQL /oh-my-claudecode:external-context Latest React Server Components patterns and c...
|
76 |