dsh-runtime-acceptance

Drive the agentkit CLI (aliases agentkit / ak) to scaffold, build, deploy, and manage agents on Volcengine AgentKit from the terminal — runtimes, knowledge bases, memory collections, tools, harnesses, invocation, SSO auth, sandboxes, and evaluation datasets. Use when a user wants to create/deploy an agent project, call or inspect a deployed runtime, manage AgentKit resources, or resolve a CLI/auth/deploy error. Does NOT handle non-AgentKit deployment, general Docker/k8s operations, Volcengine IAM management, or writing agent application code (use veadk-agent-development for that).

中文简介正在准备中。当前显示原文说明。

Continue the current local Codex conversation and coding task in an AgentKit Studio cloud Codex Sandbox using a Studio URL and short one-time pairing code. Use when the user asks to hand off, migrate, or continue a local repository in Studio, especially when a prompt contains a Studio address and pairing code. Export the complete user-visible user and assistant message history from every prior turn, including interrupted turns and progress commentary, create a temporary Studio Sandbox, restore tracked and non-ignored working-tree files plus Git metadata, inject that visible history into the cloud Thread, transfer GitHub CLI authentication separately when needed, and send one final continuation message; never copy system or developer prompts, reasoning, tool logs, SQLite state, global configuration, local skills, or SSH private keys.

中文简介正在准备中。当前显示原文说明。

The on-call triage procedure for checkout-api. Use whenever you are asked to investigate elevated errors, elevated latency, or a suspected regression.

中文简介正在准备中。当前显示原文说明。

Use this skill when the user asks to verify PiAgent skill loading, asks for the PiAgent E2E skill, or asks for the skill marker.

中文简介正在准备中。当前显示原文说明。

The house format for a quarterly sales review. Use whenever you are asked to produce a sales, revenue or bookings report.

中文简介正在准备中。当前显示原文说明。

Build, modify, debug, and cloud-validate VeADK Agents from an accepted product intent. Use for VeADK architecture, tools, workflows, memory, knowledge, executable AgentKit projects, local tests, and AgentKit build/deploy/invoke/log repair loops. Do not use for unrelated user requests, other Agent frameworks, standalone cloud administration, or production Runtime operations.

中文简介正在准备中。当前显示原文说明。