AgentKit Space Package Downloader
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_647a297a/aaaaaa.
About this skill
Problem Being Solved
In multi-agent workflows, AgentKit skill packages are often stored in cloud spaces. Local debugging or offline reproduction requires pulling each package and extracting it without manually reconstructing directory structure, dependencies, or environment settings.
How the Skill Works
This skill targets a specified AgentKit skill space and downloads packages locally:
- Destination: caller provides a local path, such as
./my-skills. - Batch download: when
--skillsis omitted, it downloads all skills in the space. - Named selection: when
--skills skill-a skill-bis provided, it downloads only the listed skills. - Package handling: it fetches skill packages from TOS and extracts them for later loading or review.
It relies on the veadk Python package and requires VOLCENGINE_ACCESS_KEY, VOLCENGINE_SECRET_KEY, and SKILL_SPACE_ID; SKILL_SPACE_ID is a comma-separated list of space IDs, while AGENTKIT_TOOL_REGION is optional and defaults to cn-beijing.
Boundaries and Notes
It is best for engineers who need to sync cloud skill packages to a local directory. It does not execute skills, install dependencies, or validate permissions. Failures can occur if SKILL_SPACE_ID is missing, credentials are invalid, or the destination is not writable. For multi-space or cross-region use, confirm environment variables and space access first.
Use Cases
- Before local AgentKit debugging, download all skill packages from a space and extract them to ./my-skills.
- When reviewing only selected skills, specify skill-a and skill-b with --skills to fetch those packages.
- When preparing an offline workspace, pull all skill packages from the cloud space and extract them locally.
- In a script, retrieve packages by SKILL_SPACE_ID and expand them for later inspection.
Best For
- Engineers debugging AgentKit skills locally who need to fetch and extract skill packages into a local directory.
- Architects maintaining skill repositories who need to sync selected packages into a local workspace before review.
- Platform engineers writing automation who need to batch-retrieve and unpack packages by skill space in scripts.
- Test engineers reproducing issues offline who need a set of AgentKit skill packages prepared locally.
Related Skills
Provides Claw with character-library selection, switching, saving, and global SOUL.md style sync for role-based conversation.
An AIONE Agentic AI Infrastructure SDK wrapper for building production AI agents with memory, skills, workflows, and hooks.
A Python/TypeScript SDK wrapper for the DeepSeek-Reasonix native AI coding agent, with prefix-cache support.
A browser automation tool for analysts, operators, and developers that locates elements, fills forms, extracts structured content, and supports no-code scheduling and export.