agent-sdk
Das Agent-SDK ist ein Satz von Tools für Entwickler, die Schlüsselwörter effizient verwalten müssen
Durchsuchen und installieren Sie Tausende von AI Agent Skills im Killer-Skills-Verzeichnis. Kompatibel mit Claude Code, Windsurf, Cursor und mehr.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
Das Agent-SDK ist ein Satz von Tools für Entwickler, die Schlüsselwörter effizient verwalten müssen
Traceway: observability for LLM's
Personal Claude assistant for Chinese users - Feishu integration, persistent container, terminal CLI 面向中国用户的个人 Claude 助手 - 飞书集成、常驻容器、终端 CLI
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
Build a signed, notarized macOS .app and publish a GitHub release. Use when cutting a new version of WisprDuck.
Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.
Use when debugging failed CI/CD jobs, analyzing build logs, or investigating GitHub Actions failures. Access BuildBuddy remote build execution and caching service for detailed build insights.
Safe HTML templating patterns for Cloudflare Worker using Hono. Use when injecting dynamic content into HTML responses, generating meta tags, or rendering server-side HTML with user data.
JSON-based end-to-end test format, runner, and mock provider
Use when writing TypeScript code that interacts with dependencies, handles credentials, executes child processes, or manages configuration. Provides Shai-Hulud supply chain attack countermeasures at the code level including safe dependency usage, credential handling, subprocess hardening, and runtime integrity patterns.
create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis. Also trigger when users say things like turn this into a skill, make a skill for X, help me improve my skill, test my skill, evaluate skill performance, or reference any .skill file or SKILL.md. Even if the user just describes a repeatable workflow they want to capture, consider suggesting a skill.
GEODE v0.13.0 — 범용 자율 실행 에이전트 | LangGraph Agent CLI | Goal Decomposition · Grounding Truth · HITL Safety | 38 Tools | 134 Modules | 2366+ Tests