Agentscope
Build and trace AI agents in Python with AgentScope, an open-source agent framework with a ReAct loop, tools, middleware, team pipelines and OpenTelemetry tracing. Use when building production agents that need observability, debugging an agent's model and tool calls, capping token spend per reply, or coordinating a leader with specialist agents.
Install
npx skills add TerminalSkills/skills --skill agentscopegit clone --depth 1 https://github.com/TerminalSkills/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/agentscope ~/.claude/skills/agentscopePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AgentScope ## Overview [AgentScope](https://github.com/agentscope-ai/agentscope) is a Python framework (Apache-2.0) for building agents on a reasoning-acting (ReAct) loop. Version 2.x (2.0.9 at the time of writing) is a rewrite of the 1.x line: the 1.x names (`agentscope.init`, `ReActAgent`, `DialogAgent`, `msghub`) are gone, and docs for the two majors must not be mixed. Check the installed version with `pip show agentscope` and read the matching docs at `https://docs.agentscope.io/stable/en/index`. Observability is built in through middleware. `TracingMiddleware` emits OpenTelemetry spans for each reply, model call and tool execution, so traces flow to any OTLP backend (Jaeger, Grafana Tempo, Langfuse, Datadog). AgentScope does not ship its own trace store, decision logger, audit-trail class or replay tool; use your OTLP backend, the streamed events, and persisted agent state for those jobs. Requires Python 3.11 or newer. There is no Node.js package. ## Instructions ### Install ```bash pip install agentscope # 2.0.9 already installs the OpenTelemetry SDK and OTLP exporters; pin them yourself if you depend on them pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http # Redis state storage and the agent service need extras pip install "agentscope[storage-redis,service]" ``` ### A minimal agent An agent needs a name, system prompt and a chat model. Credentials are objects built from environment variables, never literals.
Details
- Skill name
agentscope- Repository
- TerminalSkills/skills
- Path
skills/agentscope/SKILL.md- License
- Apache-2.0
- Repo updated
- 8 November 2026
FAQ
What does the Agentscope skill do?
Build and trace AI agents in Python with AgentScope, an open-source agent framework with a ReAct loop, tools, middleware, team pipelines and OpenTelemetry tracing. Use when building production agents that need observability, debugging an agent's model and tool calls, capping token spend per reply, or coordinating a leader with specialist agents.
How do I install the Agentscope skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add TerminalSkills/skills --skill agentscope. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agentscope popular?
It lives in TerminalSkills/skills, which has 213 GitHub stars and 34 forks.
Related skills
3dsmax Rendering
213TerminalSkills/skills
Scripts and configures production rendering in Autodesk 3ds Max with the V-Ray and Corona renderers: output size and files, render elements, denoising, light mix, batch and command-line rendering, and network rendering. Use when a user asks to set up a production render, render several cameras in one batch, render from the command line or on a render farm, add render passes for compositing, or cut render time for archviz and product shots.
3dsmax Scripting
213TerminalSkills/skills
Covers scripting Autodesk 3ds Max, the 3D modeling and rendering application, with MAXScript and Python (pymxs): scene manipulation, object creation, material assignment, camera and light setup, batch operations, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, running scripts headless with 3dsmaxbatch, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.
3proxy
213TerminalSkills/skills
3proxy is a small open-source proxy server that runs HTTP/HTTPS, SOCKS4/5, SNI and TCP/UDP port-mapping proxies from one config file. Use when a user asks to set up an HTTP or SOCKS5 proxy, add proxy users and passwords, write 3proxy access rules, chain or rotate upstream (parent) proxies, limit bandwidth, connections or monthly traffic per user, run 3proxy in Docker, or fix a 3proxy.cfg that will not start.
AI Eval CI
213TerminalSkills/skills
Run AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions integration.
Agent Workflow Packager
213TerminalSkills/skills
Turns a workflow a team keeps repeating with a coding agent (a pasted prompt, runbook, review checklist or AGENTS.md section) into a spec-valid Agent Skill folder with SKILL.md, triggers, approval gates and a done check. Use when asked to "turn this into a skill", "package our release checklist as a skill" or "convert this runbook to SKILL.md".
AI Guardrails
213TerminalSkills/skills
Adds safety guardrails to LLM applications in Python: prompt injection checks, a canary token for system-prompt leaks, OpenAI moderation, PII redaction, Pydantic output validation, rate and token limits, and grounding checks for RAG answers. Use when adding safety layers to a chatbot, detecting prompt injection, filtering harmful content, validating LLM output against a schema, or building a moderation pipeline.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.