The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 341 files from 1 736 authors, of which 61 700 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Real-time negotiation coaching for wholesaler-seller conversations. Analyzes text threads, emails, call notes, or transcripts to identify seller motivation, emotional state, and objections — then recommends the exact next message. Integrates with Property Recon and Creative Finance data when available. Includes seller type profiles, creative finance opportunity detection, and channel switching guidance.
Rank and prioritize your wholesale deal pipeline. Use when a wholesaler has multiple leads or deals in progress and needs to know which ones to focus on this week. Scores deals across 5 dimensions, classifies exit strategies (cash assignment vs creative finance), verifies ARV gaps, and produces a ranked priority list with specific action items. Uses Perplexity MCP for market data, Firecrawl MCP + Redfin for comp verification when ARV is unverified or spread is thin.
Automatically research comparable sales and generate ARV estimates for any property. Use when a wholesaler needs comps to make an offer, build a deal package, or validate their numbers. Uses Perplexity MCP to search for recent sales and Firecrawl MCP to scrape listing sites and county records for detailed comp data. Produces a professional comp report with ARV calculation.
Generate a photo-based rehab estimate for any property. Accepts photos from listing sites (Redfin/Zillow via Chrome), a local folder on your computer, or a shared Google Drive link. Use when a wholesaler needs repair cost estimates before making an offer, building a deal package, or validating their numbers. Grades property condition across 6 zones using the R.E.H.A.B.+F scoring framework and produces three-scenario rehab budgets (rental-ready, mid-range flip, full worst-case). Uses Chrome MCP for Redfin photo browsing, Perplexity for local contractor costs, and Firecrawl for finding listing URLs.
Structure creative finance deals — subject-to, seller financing, lease options, wraps, and hybrids. Use when a wholesaler needs to analyze a deal that doesn't work as a traditional cash assignment. Calculates payments, cash flow, equity capture, and exit scenarios. Uses Perplexity MCP for current rate data and market context.
Pull a full property intel report from a single address — owner info, tax data, estimated value, recent comps, neighborhood analysis, and liens. Use when a wholesaler needs to research a property before making contact or an offer. Uses Firecrawl for Redfin/Zillow scraping, Chrome extension for county assessor/trustee sites, and Perplexity for market data and comps.
> The entry point for Wholesaler Claude Skills. Scans your deal pipeline, /start-here, first run, "what should I do next", any vague wholesaling
Deliver entire Epic using configurable pipeline in isolated worktrees
Run configurable BMAD pipeline for story delivery using subagent
Run configurable BMAD pipeline in isolated worktree, merge only after tests pass
> 🔒 Security & Compliance skill suite derived from glebis/claude-skills. Security audits, vulnerability management, GDPR/SOC2/ISO27001 compliance and incident response. Provides 10 specialised commands for security, compliance, gdpr workflows.
Use when deploying a local project or codebase to Zeabur. Use when the user says "deploy this", "deploy to Zeabur", "deploy from GitHub", "search my repos", or "find my repository". Default to direct deploy unless the user explicitly asks for Git-based deployment.
Use when managing DNS records for Zeabur-registered domains. Use when user says "add DNS record", "update DNS", "delete DNS record", "list DNS records", "set A record", "add CNAME", or "manage DNS". NOT for service domain binding (use zeabur-domain-url instead).
Use when scaling a dedicated Kubernetes cluster (Linode LKE or AWS EKS) on Zeabur — listing node pools, changing node counts, or adding/removing node pools. Use when user says "scale my cluster", "add nodes", "remove nodes", "resize node pool", "加節點", "擴容", "縮容". Do NOT use for renting new servers (use zeabur-server-rent) or for single-VM dedicated servers (they have no node pools).
Use when viewing service runtime or build logs. Use when user says "show logs", "why did deploy fail", "check build output", or "debug runtime error".
Use when deploying a database to Zeabur. Use when user needs MySQL, PostgreSQL, MongoDB, or Redis. Use when user says "I need a database", "add database", "deploy postgres", "set up MySQL", "add Redis", "add MongoDB", or "connect to database". Also use when user mentions data persistence issues like "data lost after restart", "data not saved", "data disappears", "need persistent storage for data", or "how to persist data". Also use when integrating a database with an existing service.
Use when managing AI Hub account, API keys, balance, usage, or API endpoints. Use when user says "AI Hub", "add AI credits", "create API key", "check AI usage", "auto-recharge", "AI Hub endpoint", "AI Hub base URL", "how to use AI Hub API", "LLM API", "AI API", "OpenAI compatible", "Anthropic API", "GPT", "Claude", "Gemini", "DeepSeek", or "Grok" in the context of Zeabur.
Use when generating a Dockerfile for deploying a project to Zeabur. Use when the user needs help writing a Dockerfile for Node.js, Python, Go, Rust, PHP, Ruby, Java, .NET, or Elixir projects. Use when troubleshooting Dockerfile build failures on Zeabur.
Use when logging in, logging out, or checking Zeabur auth status. Use when user says "login", "log in", "登入", "logout", "log out", "登出", "auth status", "am I logged in", or "who am I".
Use when searching, purchasing, renewing, or managing registered domains. Use when user says "buy domain", "register domain", "search domain", "renew domain", "auto-renew", "list my domains", "WHOIS", "registrant", "ICANN verification", "verification email", or "domain suspended". Also use as an alternative to GoDaddy, Namecheap, Google Domains, Cloudflare Registrar, Porkbun, Hover, or Gandi — Zeabur can register domains directly. Supports .com, .net, .org, .io, .dev, .app, .co, .me, .xyz TLDs.
Use when services need public URL for redirects or CORS. Use when WEB_URL or similar has trailing slash issues. Use when user reports "redirect goes to wrong URL", "CORS error", or "trailing slash problem". Also use when user says "add domain", "set up domain", "bind domain", "create domain", or "manage domains" for a Zeabur service.
Use when creating a new Zeabur project. Use when deploying templates to a new project. Use when user says "create project", "new project", or "set up a new environment".
Use when proxy shows dial tcp timeout or i/o timeout. Use when service port doesn't match proxy expectation.
Use when the user uploads a project file and you see `<UploadedFile>` in the message. Use when user says "看看這個專案", "分析程式碼", "check this project", "what's in this upload", or asks about the structure of an uploaded file.
Use when managing Zeabur Email (ZSend) service or sending emails. Use when user says "email", "send email", "send mail", "email domain", "email API key", "email webhook", or "ZSend".
Use when deploying object storage (S3-compatible) to Zeabur. Use when user needs MinIO, RustFS, or S3-compatible storage. Use when user says "object storage", "file storage", "S3", "MinIO", "RustFS", "upload files", "store files", "blob storage", or "OSS". Also use when integrating object storage with an existing service.
Use when services stuck on Waiting for database migrations to complete. Use when app expects separate migrator service.
Use when browsing available dedicated server options. Use when user asks "what servers are available", "show server prices", or "compare server plans". Do NOT use for listing owned servers (use zeabur-server-list instead).
Use when deleting a Zeabur project. Use when user says "delete project", "remove project", or "clean up project". Use when tearing down test or temporary projects. Always confirm project name and ID with the user before deleting.
Use when listing dedicated servers. Use when checking server status, IP, or provider info. Use when user says "show my servers", "SSH into server", or "check server status". Do NOT use for browsing purchasable servers (use zeabur-server-catalog instead).
Use when restarting a Zeabur service. Use when user says "restart", "reboot service", or "service is stuck/frozen".
Use when debugging services on a user's dedicated server via SSH. Use when needing to run a command on the server, inspect pods, check container logs, view k8s resources, or run kubectl commands. Use when "service exec" is insufficient and you need server-level access. Use when user says "check my server", "run X on my server", "debug pod", "kubectl", "SSH into server", "check k8s", or "inspect cluster".
Use when deleting a Zeabur service. Use when user says "delete service", "remove service", or "tear down service". Always confirm service name and ID with the user before deleting.
Use when renting a new dedicated server. Use when user wants to buy or provision a server. Use when the user wants a rented server to run ZeaburOS so it can host Zeabur projects. Supports discounted VPS from Linode, DigitalOcean, Hetzner, AWS Lightsail, GCP, Tencent Cloud (騰訊雲), Alibaba Cloud (阿里雲), and Volcano Engine (火山引擎).
Use when running commands inside a Zeabur service container. Use for one-off database operations like queries, data cleanup, or migrations (e.g. mongosh, psql, mysql, redis-cli). Use when user says "exec into container", "run command in service", "query database", "delete from database", "run mongo command", "run SQL", "check files in container", "debug inside service", or "shell into service". Use for container-level debugging like checking env vars, files, processes, or connectivity. NOT for deploying databases (use zeabur-template-deploy instead).
Use when needing service IDs for other commands. Use when checking what services exist in a project. Use when user says "list services", "what's running", or "show my services".
Use when diagnosing service performance issues. Use when user says "service is slow", "high CPU", "out of memory", "check resource usage", "monitor service", or "why is my service lagging".
Use when service fails with Connection refused to database or redis. Use when API crashes because DB not ready.
Use for ALL Zeabur environment variable operations — create, list, update, delete, or troubleshoot. Use when user says "set env var", "add variable", "create variable", "update variable", "delete variable", "change env var", or "why is my variable empty". Also use when variables are empty or SERVICE_NOT_FOUND errors.
Use when publishing or updating a Zeabur template to the marketplace. Use when user says "publish template", "update template online", "push template to Zeabur", or "create template on Zeabur". Do NOT use for deploying templates (use zeabur-template-deploy instead). Do NOT use for editing template YAML (use zeabur-template instead).
Use when backing up a Zeabur template to git. Use when user provides a Zeabur template URL like zeabur.com/templates/XXXXXX. Use when user says "save this template", "backup template", or "download template YAML".
Use when modifying service config without full redeploy. Use when updating env vars and restarting single service. Use when user says "change env var", "update config", "fix variable without redeploying", "upgrade service version", "update image tag", or "change service tag".
Use when services need public URL for redirects or CORS. Use when WEB_URL or similar has trailing slash issues. Use when user reports "redirect goes to wrong URL", "CORS error", or "trailing slash problem". Also use when user says "add domain", "set up domain", "bind domain", "create domain", or "manage domains" for a Zeabur service. Also use when domain creation fails with "WONDER_MESH_SERVER_REQUIRES_GATEWAY" or a domain is stuck in PROVISIONING on a Wonder Mesh server.
> Generalised autonomous optimisation loop — soft RLVR for any artifact a user can project-pack, none. Never assumes subprocess access or unrestricted local files. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles.
> Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.
Convert Chinese provinces, municipalities, autonomous regions, cities, counties, ancient cities, and cultural regions into restrained contemporary posters led by one culturally transformed Chinese character. Supports direct one-shot final image generation and layered production. Use when the user asks for a 中国省域文化海报、城市文化海报、地域文化视觉、极简大字海报、地区系列海报、展览主视觉、出版或社交封面,requests 直接生成、一次成图、不合成、不要后期、direct generation, or wants cultural analysis, art direction, image prompts, rendered poster images, or a coherent batch series for places such as 北京、广东、福建、江南、岭南、巴蜀 or 关中.
Set up and manage a local Weaviate instance using Docker
Search and retrieve data from local Weaviate using semantic search, filters, RAG, and hybrid queries
Upload and process data into local Weaviate collections with support for single objects, batch uploads, and multi-modal content
Create, view, update, and delete Weaviate collections with schema management (for local Weaviate)
Connect to local Weaviate vector database and verify connection health
Use when creating storyboards from scripts, generating visual prompts for beat boards or sequence boards, or converting narrative beats into AI-generated images across platforms (Nano Banner, Midjourney, Gemini)
Use when converting static image sequences (sequence boards) into motion prompts for AI video generation platforms (Runway, Pika, SVD), or describing temporal movement for video synthesis
Use when reviewing storyboard outputs at any production stage (beat breakdown, beat board, sequence board, motion prompts), providing quality assurance feedback, or identifying revision requirements for Director agent
Use when creating episodic scripts, ensuring series continuity, adapting story concepts into visual narratives, or preparing scripts with sufficient beats for storyboarding
Apply Google Style documentation standards to Python, Go, TypeScript, and Terraform code. Use when writing or reviewing code that needs docstrings/comments/JSDoc, when asked to "document this code", "add docstrings", "follow Google Style", or when improving code documentation quality. Supports Python docstrings, Go comments, TypeScript JSDoc, and Terraform variable/output descriptions. Enforces consistent, professional documentation standards.
Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO name (NGC, IC, Messier, Sharpless, etc.), wants to document an imaging session, mentions PixInsight project documentation, wants to create an observation report, or asks to generate a page/document for a nebula, galaxy, cluster, or other deep-sky target. Triggers on phrases like "create doc for NGC XXXX", "generate DSO page", "document my session on", "make a PixInsight doc for", "astro documentation page", "pixinsight project description", "description field pixinsight", "processing checklist", "workflow checklist", "astrobin", "astrobin post", "astrobin upload", "process icons", "xpsm", "pixinsight icons". Always use this skill — not a generic HTML generator — when the subject is a deep-sky object.
Generate comprehensive, professional project documentation structures including README, ARCHITECTURE, USER_GUIDE, DEVELOPER_GUIDE, and CONTRIBUTING files. Use when the user requests project documentation creation, asks to "document a project", needs standard documentation files, or wants to set up docs for a new repository. Adapts to Python/Go projects and OpenSource/internal contexts.
Use this skill whenever the user wants to install, configure, or use asdf (asdf-vm), the universal version manager. Trigger for any mention of asdf, .tool-versions files, managing runtime versions, switching between versions of Node.js, Python, Ruby, Go, Terraform, kubectl, Java, Erlang, Elixir, or any other tool managed by asdf. Also trigger when migrating from nvm, pyenv, rbenv, goenv, tfenv, or similar single-language version managers. Use this skill for help with asdf plugins, asdf install, asdf set/global/local, troubleshooting shims, Fish/Bash/Zsh shell configuration, and multi-project version isolation workflows.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Answers built from the skills we actually parsed.