Skill4Agent
Skill4Agent
All SkillsSearchTools
|
Explore
Skill4Agent
Skill4Agent

AI Agent Skills Directory with categorization, English/Chinese translation, and script security checks.

Sitemap

  • Home
  • All Skills
  • Search
  • Tools

About

  • About Us
  • Disclaimer
  • Copyright

Help

  • FAQ
  • Privacy
  • Terms
Contact Us:osulivan147@qq.com

© 2026 Skill4Agent. All rights reserved.

All Skills

Total 32,343 skills

Categories

Showing 12 of 32343 skills

Per page
Downloads
Sort
Tools & Utilitiesstoryclaw-official/talent...

storyclaw-alpaca-trading

US stock and crypto trading via Alpaca API. Paper trading (simulated) and real trading supported. Real-time quotes, orders, positions, RSI strategy.

🇺🇸|EnglishTranslated
4
4 scripts/Attention
Platform Servicesstoryclaw-official/talent...

storyclaw-x2c-publish

X2C Distribution and Wallet API — publish video to X2C platform, manage assets (balance, claim X2C, swap to USDC, withdraw, transactions).

🇺🇸|EnglishTranslated
4
AI & Machine Learningaffaan-m/everything-claud...

pytorch-patterns

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

🇺🇸|EnglishTranslated
4
AI & Machine Learningaffaan-m/everything-claud...

context-budget

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

🇺🇸|EnglishTranslated
4
AI & Machine Learningaffaan-m/everything-claud...

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

🇺🇸|EnglishTranslated
4
Frontend Developmentaffaan-m/everything-claud...

nuxt4-patterns

Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.

🇺🇸|EnglishTranslated
4
AI & Machine Learninganthropics/claude-plugins...

build-mcpb

This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.

🇺🇸|EnglishTranslated
4
AI & Machine Learninganthropics/claude-plugins...

build-mcp-app

This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.

🇺🇸|EnglishTranslated
4
AI & Machine Learninganthropics/claude-plugins...

build-mcp-server

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.

🇺🇸|EnglishTranslated
4
Platform Serviceshaedallsd/haedal-skill

haedal-vehaedal

Use when the user mentions staking HAEDAL, locking, extending lock, claiming rewards, decay, or operating VeHaedal on Haedal Protocol (a DeFi ecosystem on SUI). Trigger phrases: "stake haedal", "lock haedal", "extend lock", "claim rewards from haedal", "unlock/redeem haedal", "add to stake", "start decay", "stop decay", "vehaedal". This skill calls https://skillsapi.haedal.xyz/api/v1/vehaedal/* via curl POST. add_stake and claim_rewards* need only signerAddress (+ amount/periods); add_to_existing_stake, extend_existing_lock, start_decay, stop_decay, unstake_and_claim require vehaedalObj — fetch via get_vehaedal_list(address), present the list with current_amount/locked_amount/is_decaying/lock_end_time to the user, then use their chosen objectId. All amounts are human-readable. On HTTP 200 returns txBytes (base64); on non‑200 returns msg.

🇺🇸|EnglishTranslated
4
Platform Serviceshaedallsd/haedal-skill

haedal-hawal

Use when the user mentions staking WAL, withdrawing hawal, claiming rewards, or operating haWAL on Haedal Protocol (a DeFi/LST protocol on SUI). Trigger phrases: “stake hawal”,"stake hawal", "withdraw hawal", "withdraw wal","instant withdraw hawal","instant withdraw wal","claim hawal rewards","claim wal rewards" . This skill calls https://skillsapi.haedal.xyz/api/v1/hawal/* via curl POST. On HTTP 200 returns txBytes (base64); on non‑200 returns msg.

🇺🇸|EnglishTranslated
4
Platform Serviceshaedallsd/haedal-skill

haedal-hasui

Use when the user mentions staking SUI, withdrawing, claiming rewards, or operating haSUI on Haedal Protocol (a DeFi/LST protocol on SUI). Trigger phrases: "haedal","stake sui","stake hasui", "withdraw hasui", "withdraw sui","instant withdraw hasui", "instant withdraw sui", "claim hasui rewards","claim sui rewards". This skill calls https://skillsapi.haedal.xyz/api/v1/hasui/* via curl POST. On HTTP 200 returns txBytes (base64); on non‑200 returns msg.

🇺🇸|EnglishTranslated
4
1...179180181182183...2696
Page