subagent-driven-development
[ Featured ]subagent-driven-development is a technique that leverages fresh subagents for independent tasks, ensuring spec compliance and code quality through a two-stage review process.
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
subagent-driven-development is a technique that leverages fresh subagents for independent tasks, ensuring spec compliance and code quality through a two-stage review process.
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
This skill should be used when the user asks to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
agents-sdk is an npm package that provides the tools to build persistent, stateful AI agents on Cloudflare Workers. It utilizes Durable Objects for statefulness and requires specific bindings and SQLite migrations in the wrangler.jsonc configuration file.
一个开源的,专注于提示词管理的平台 / An open-source platform focused on prompt management
Config files for my GitHub profile.
subagents-creator is a skill that enables the creation and management of specialized agents for specific tasks, such as explore, librarian, and oracle.
sub-agent-decompose-worker-review is a pipeline automation skill that decomposes tasks, executes them, and reviews the results using a chain of three agents: task-decomposer, task-worker, and reviewer.
Subagent-driven development is a methodology that executes plans by dispatching fresh subagents per task, with two-stage reviews for spec compliance and code quality.
compile-agents-context is a skill that standardizes AGENTS discovery and regeneration with explicit options, including scan depth and dependency inclusion.
agent-domain is a skill that focuses on the domain layer of an application, responsible for core business logic and rules, ensuring portability, testability, and stability.