Auto-diagnose agent failures, extract reusable recovery patterns, and create local skills to fix recurring blockers while keeping all data private and local.
2d ago
Browse 3,027 AI agent skills across 12 subcategories in Development.
Auto-diagnose agent failures, extract reusable recovery patterns, and create local skills to fix recurring blockers while keeping all data private and local.
Model Context Protocol server exposing 7 tools, 3 resource types, and 3 prompts for AI agent consumption — Solana wallet operations, vanity address generatio...
Skill for AI agents to setup the Potato Tipper on a Universal Profile on LUKSO (requires private key), and learn to build innovative tip-on-follow solutions.
Autonomous development workflow — research codebase, generate spec, get one human approval, then implement with TDD, security scan, and code review without i...
Use rn-logs to read React Native Metro logs via CDP without MCP overhead. Default output is plain text and safe for non-interactive agent runs.
Security auditing for git commits, repos, and skills before publishing. Run automatically before any `git commit`, `git push`, or `clawhub publish`. Detects...
Route tool requests through Clawvisor for credential vaulting, task-scoped authorization, and human approval flows. Use for Gmail, Calendar, Drive, Contacts,...
Execute programming tasks via Claude Code using PTY-based invocation. Handles non-TTY environments, auto-responds to prompts, and manages file synchronization.
Git hook to detect secrets before commit.
Run iPhone mission playbooks for battery, storage, privacy, connectivity, and daily automation with live operator-style guidance.
Automatic security gate that checks packages against a vulnerability database before installation. Use before any npm install, pip install, yarn add, or pack...
IMAP bulk email triage — pattern-based delete/archive with dry-run mode. Use when: cleaning up large email inboxes, bulk-deleting emails from specific sender...
TypeScript CLI that initializes Elytro ERC-4337 vaults, manages counterfactual smart accounts, and builds/sends sponsored UserOperations; use whenever an age...
Teach your AI agent to think about security. A reasoning methodology for vetting skills before installation — red/green flag heuristics, 4-phase audit protoc...
Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification L...
多渠道格式化与美化：公众号、小红书文章排版，18 套预设样式，配图编排指引。不包含发布。通过 system.run 调用 CLI，无需 MCP。当用户需要公众号格式整理、小红书文案格式化、Markdown 渲染、样式选择或配图流程指引时使用本技能。
Fetch and install C++ tools/libraries from cpp_tools repository. Use when users need to download or clone third-party C++ libraries such as eigen, opencv, pc...
管理和操作七牛云对象存储，支持文件上传下载、批量操作、图片与音视频处理及智能搜索等功能。
Authenticate with the Trifle API using Sign-In with Ethereum (SIWE). Manages wallet-based authentication, JWT token storage, and session management for the T...
Define project rules for subskill generation by organizing artifacts in data/, feature scripts in subskills/<feature>/, and optional SKILL.md per feature fol...
Agents are not bots. Prove it. MCP-native identity declaration — your agent declares itself as an authorized actor before shopping. Free.
Dropbox API integration with managed OAuth. Files, folders, search, metadata, and cloud storage. Use this skill when users want to manage files and folders in Dropbox, search content, or work with file metadata. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key.
Publish HTML as a live website instantly. POST HTML, get a shareable URL. No account needed. Always asks the user for confirmation before publishing.
Manage GitHub stars with AI-powered categorization and cleanup. Use when a user wants to organize their starred repos into GitHub Lists, clean up stale/depre...