一键在 Manus 中运行任何 Skill

arl-cli

星标1

分支1

更新时间2026年7月18日 18:33

Guide for using the `arl` CLI to inspect, debug, and manage the ARL (Agentic RL) runtime: experiments, warm pools, sessions, files, snapshots, replay, private containers, logs, and metrics. Use this skill whenever the user asks about checking pool status, viewing experiment sessions, creating or debugging sessions, transferring files, restoring snapshots, replaying trajectories, streaming logs, exporting trajectories, waiting for pool readiness, running commands in private sidecar containers, or any operational task involving the ARL system. Also trigger when the user mentions `arl` CLI commands, asks "how do I see what's running", "show me the pools", "check experiment X", "debug this session", "看看 pool 状态", "查看实验", "导出 trajectory", or wants to combine multiple arl operations into a workflow.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

Lincyaw

Lincyaw/agent-env

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

ARL CLI

arl is the command-line tool for the ARL runtime. It talks to the Gateway REST API, which allocates sandbox-backed sessions and reaches sidecars inside pods.

Use this skill to choose the right CLI workflow and inspect the focused reference needed for the task.

Setup

make build-cli

export ARL_GATEWAY_URL=http://localhost:8080
export ARL_API_KEY=your-token
export ARL_FORMAT=json

Use --format json for scripts and automation. Do not use JSON format with arl session download <id> <remote> -, because stdout is reserved for raw file bytes.

Agent-facing introspection:

arl --dump-schema

Choose a Reference

Command syntax, flags, env vars, and exit codes: read references/commands.md.
Operational playbooks and best practices: read references/workflows.md.
Python SDK parity or implementation mapping: use the arl-python-sdk skill.

Core Workflow

Confirm ARL_GATEWAY_URL and auth context before mutating pools or sessions.
Start with arl status, arl pool list --format wide, and arl session list --format wide when diagnosing runtime state.
Use experiments for benchmark/training runs that need grouping and cleanup.
Use one-off sessions or pool exec for ad hoc debugging.
Capture snapshot IDs and trajectory JSONL when a run may need replay or training data export.
Clean up temporary sessions, experiments, and pools after debugging.

Verification

For CLI code changes, run focused Go checks:

go test ./cmd/arl/... ./pkg/gateway/...
go test ./...

同仓库更多 Skills

同仓库

arl-python-sdk

Lincyaw/agent-env

Conceptual map for maintaining or using the `arl-env` Python SDK (`from arl import ...`). Use this skill when the user asks about ARL Python SDK capabilities, how SDK features map to gateway/runtime code, where to implement a SDK change, or how Python users should interact with ARL sessions, managed experiments, warm pools, files, replay, trajectories, logs, auth, or interactive shells. Prefer this as a feature/file guide, not a detailed API tutorial.

2026-07-181

iroh-quic

Lincyaw/agent-env

Reference for using the iroh P2P QUIC library (iroh 1.0+) by n0-computer in Rust and Python. Use this skill whenever writing or modifying code that touches iroh — creating Endpoints, connecting peers, opening QUIC streams, implementing protocol handlers, TCP tunneling, or using the Python iroh bindings. Also use when debugging iroh connection issues, NAT traversal problems, or relay connectivity. Triggers on: iroh, QUIC, EndpointId, iroh transport, iroh tunnel, iroh relay, iroh connect, direct-connect, P2P QUIC, iroh Python, dumbpipe, iroh protocol handler, ALPN.

2026-07-121

kubernetes

Lincyaw/agent-env

Kubernetes operations, testing, and validation. Use when working with Kubernetes clusters for deploying resources, verifying deployments, testing operators/CRDs, debugging pods, monitoring workloads, or performing end-to-end testing and validation of K8s applications.

2026-03-101

code-review

Lincyaw/agent-env

Professional code review for anti-patterns, extensibility, architectural soundness, and code quality. Use when users request code review, ask to check for anti-patterns, need architectural validation, want to ensure extensibility, or request analysis of code quality. Apply to tasks involving code auditing, refactoring recommendations, design pattern validation, or ensuring every line of code has purpose and meaning.

2026-01-071

doc

Lincyaw/agent-env

Modern documentation management with MkDocs Material theme and GitHub Pages publishing. Use when users need to create, maintain, or publish professional documentation websites. Supports initialization of new documentation projects, live preview with auto-reload, production builds, and automated deployment to GitHub Pages. Features modern Material Design theme with dark mode, full-text search, mobile responsiveness, code highlighting, and rich markdown extensions including Mermaid diagrams, admonitions, and tabs.

2026-01-071

python

Lincyaw/agent-env

Advanced Python development with architecture expertise and automated code quality enforcement. Use when developing Python applications, libraries, or scripts that require high code quality, type safety, best practices, and professional architecture patterns. Includes automated linting with Ruff, type checking with MyPy, security scanning with Bandit, and comprehensive testing. Apply for tasks involving Python code creation, refactoring, quality checks, project initialization, or implementing design patterns.

2026-01-061

name

arl-cli

description

ARL CLI

arl is the command-line tool for the ARL runtime. It talks to the Gateway REST API, which allocates sandbox-backed sessions and reaches sidecars inside pods.

Use this skill to choose the right CLI workflow and inspect the focused reference needed for the task.

Setup

make build-cli

export ARL_GATEWAY_URL=http://localhost:8080
export ARL_API_KEY=your-token
export ARL_FORMAT=json

Use --format json for scripts and automation. Do not use JSON format with arl session download <id> <remote> -, because stdout is reserved for raw file bytes.

Agent-facing introspection:

arl --dump-schema

Choose a Reference

Command syntax, flags, env vars, and exit codes: read references/commands.md.
Operational playbooks and best practices: read references/workflows.md.
Python SDK parity or implementation mapping: use the arl-python-sdk skill.

Core Workflow

Confirm ARL_GATEWAY_URL and auth context before mutating pools or sessions.
Start with arl status, arl pool list --format wide, and arl session list --format wide when diagnosing runtime state.
Use experiments for benchmark/training runs that need grouping and cleanup.
Use one-off sessions or pool exec for ad hoc debugging.
Capture snapshot IDs and trajectory JSONL when a run may need replay or training data export.
Clean up temporary sessions, experiments, and pools after debugging.

Verification

For CLI code changes, run focused Go checks:

go test ./cmd/arl/... ./pkg/gateway/...
go test ./...