Use when long-lived agents, project memories, system prompts, or playbooks are repeatedly summarized, rewritten, or optimized and risk losing domain detail, provenance, or execution learnings.
中文简介正在准备中。当前显示原文说明。
mouadja02/skills102026年10月17日 更新
免费在 GitHub 公开
smolagents-code-agents
Use when building Hugging Face smolagents, code-executing agents, Python-action agents, Hub-shared tools, or lightweight agent prototypes that need sandboxing and provider flexibility.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（3）
- SKILL.md2.9 KB
- references/sandboxing-checklist.md1.0 KB
- scripts/smolagent_safety_scaffold.py1.3 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Smolagents Code Agents
Use code actions when an agent benefits from loops, variables, data transforms, and multi-call tool composition. Treat generated code as untrusted unless it runs in a real sandbox.
Use When
- The user wants a lightweight agent prototype in Python.
- Tool calls need loops, branching, or batching.
- The agent should use Hugging Face Inference Providers, LiteLLM, OpenAI-compatible servers, local
transformers, or Ollama. - The agent needs MCP tools, Hub tools, or a shared Space.
- You must decide between
CodeAgentandToolCallingAgent.
Build Pattern
- Choose
CodeAgentwhen actions need Python control flow; chooseToolCallingAgentfor simple structured tool calls. - Keep tools small, typed, and side-effect explicit.
- Configure the model through environment variables or a provider object, never hard-code secrets.
- Run code execution in Docker, E2B, Modal, Blaxel, or another isolation boundary.
- Allow imports by explicit whitelist only.
- Stream logs and capture intermediate observations for debugging.
- Add a task-level timeout and max-step budget.
Safety Baseline
Never treat LocalPythonExecutor as a security boundary for untrusted code. Use it only for trusted local experiments.
Generate a starter safety scaffold:
python scripts/smolagent_safety_scaffold.py --name research_agent
Review sandboxing-checklist.md before running any agent that executes model-written code.
Quick Selection
| Requirement | Choose |
|---|---|
| Agent writes Python actions | CodeAgent |
| Strict JSON-like tool calls | ToolCallingAgent |
| Untrusted tasks or web data | Sandboxed executor |
| Local model experiments | TransformersModel or Ollama-compatible provider |
| Hosted provider flexibility | InferenceClientModel, LiteLLMModel, or OpenAI-compatible model |
Common Mistakes
| Mistake | Fix |
|---|---|
| Running untrusted code locally | Use Docker or managed sandbox |
| Exposing broad filesystem access | Mount a temporary workspace only |
| Giving tools vague docstrings | Make inputs, outputs, and side effects explicit |
| Letting agents import anything | Whitelist imports per task |
| Shipping without trace logs | Persist steps, code snippets, tool outputs, and final answer |
References
- GitHub: huggingface/smolagents - https://github.com/huggingface/smolagents
- Hugging Face docs: smolagents - https://huggingface.co/docs/smolagents/index
- Hugging Face docs: CodeAgent - https://huggingface.co/docs/smolagents/reference/agents
- Hugging Face docs: MCP tools - https://huggingface.co/docs/smolagents/tutorials/mcp
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
中文简介正在准备中。当前显示原文说明。
mouadja02/skills102026年10月17日 更新
Adds educational comments to a code file so it becomes a learning resource, asking for the file (with a list of close matches) if none is given. Use when preparing code for learners, onboarding, or teaching.
中文简介正在准备中。当前显示原文说明。
mouadja02/skills102026年10月17日 更新
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.
中文简介正在准备中。当前显示原文说明。
mouadja02/skills102026年10月17日 更新
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)
中文简介正在准备中。当前显示原文说明。
mouadja02/skills102026年10月17日 更新
Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
中文简介正在准备中。当前显示原文说明。
mouadja02/skills102026年10月17日 更新