How do I install the Areno Build Agentic Workflow skill?

Run npx skillmds@latest add inclusionai/areno-build-agentic-workflow in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Areno Build Agentic Workflow safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Areno Build Agentic Workflow?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Areno Build Agentic Workflow free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Areno Build Agentic Workflow?

inclusionai (@inclusionai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Areno Build Agentic Workflow by inclusionai

Name: Areno Build Agentic Workflow
Author: inclusionai

Areno Build Agentic Workflow

Create or debug an AReno multi-turn agentic dataset, run_agent implementation, tool schemas, tool execution, reward, loss masks, interactive TUI game with OpenAI-compatible LLM inference, or agentic training example. Use for text or multimodal agentic workflows, not ordinary single-turn rollout.

inclusionai 16299a2 4 files · 5.2 KB Updated Sep 17, 2026

File contents

Build an AReno Agentic Workflow

Inspect the nearest example under examples/agentic/ and public types in areno/api/agentic.py before implementation.

Develop on a local branch and pull committed changes into remote validation hosts. Use ModelScope for remote checkpoint and dataset references.

python .agents/skills/areno-build-agentic-workflow/scripts/validate_transcript.py transcript.json
python .agents/skills/areno-run-training/scripts/inspect_dataset.py \
  --dataset-path data.jsonl --loader examples/agentic/<name>/dataset_loader.py --algo gspo

Workflow

Define one deterministic environment/game domain and valid dataset records.
Keep dataset loaders processor/tokenizer independent.
Define strict JSON tool schemas and bounded execution. Read references/message-contract.md.
Build trajectories using AReno public agentic types. Preserve assistant tool-call and tool-result ordering.
Reward the intended outcome and process separately; test invalid, partial, and optimal paths.
Verify concurrency, timeout, cancellation, context truncation, multimodal content, and loss masks.
Run a bounded agentic rollout, inspect one full transcript, then one real training step.

Do not fabricate missing tool calls or alter raw model text to make a trajectory appear valid. Surface parser/capability failures.

Frequently asked questions