ワンクリックで
ais-agents
AI Agent framework — tool registry, multi-step reasoning, memory, rate control. Không infinite loop, tự động timeout.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
AI Agent framework — tool registry, multi-step reasoning, memory, rate control. Không infinite loop, tự động timeout.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences. Use when: 3D website, three.js, WebGL, react three fiber, 3D experience.
Game art principles — art style, color theory, animation principles, asset pipeline
Game design principles — core loop, GDD, player psychology, difficulty balancing, progression
Orchestrator game — route to implementation skill (pxhopencode) + principle-based sub-skill (agent-skills-hub)
Mobile game principles — touch input, battery, thermal, app stores, monetization
Multiplayer game principles — networking architecture, synchronization, security, matchmaking
| name | ais-agents |
| description | AI Agent framework — tool registry, multi-step reasoning, memory, rate control. Không infinite loop, tự động timeout. |
Agents must never infinite loop. Every loop must have a hard timeout and max steps.
KHÔNG BAO GIỜ chạy agent loop KHÔNG có timeout + max steps
Mọi tool call phải có guard tràn token
| File | Mục đích |
|---|---|
templates/tool-registry.py | Tool + ToolRegistry — type-safe tool registration, OpenAI schema |
templates/agent.py | Agent — ReAct loop with timeout (30s) and max steps (15), tool execution |
templates/agent-memory.py | AgentMemory — deque short-term + dict long-term, summarize() for context |
from templates.tool-registry import Tool, ToolRegistry
from templates.agent import Agent
registry = ToolRegistry()
registry.register(Tool(name="search", ...))
agent = Agent(registry)
result = await agent.run("find docs about X")
Security:
| Excuse | Reality |
|---|---|
| "ReAct loop 15 steps là an toàn" | Tool call sai → loop tốn token, timeout |
| "Không cần memory summarization" | Context quá dài → LLM mất focus |
| "Tool result truncation 2000 chars thừa" | LLM context bị tràn bởi tool output dài |