菜单
Discover how a robot is actually used by reading its deployed guide and SDK reference before writing code. Use when starting robot work, when the API is unclear, when a new robot is added, or when OpenClaw must determine the real robot usage pattern instead of guessing.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/amap-cvlab/ABot-Claw --skill abotclaw-sdk-discovery命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
External services and backend capabilities for AbotClaw robots — vision APIs, VLM/LLM endpoints, planners, speech services, grasping backends, and client SDKs. Use when a robot skill needs an external service, when checking what backend tools already exist, when debugging service reachability, or when deciding whether to build locally versus call a service.
Bundle an AbotClaw robot skill and its dependencies into a single executable Python file or portable submission artifact. Use when preparing robot code for execution environments that want one file, when flattening dependency chains, or when packaging a skill for deployment or review.
SpatialMemoryHub-based robot memory querying, writing, and retrieval for AbotClaw. Use when the agent needs to store or retrieve object memory, place memory, keyframe memory, or semantic frame memory; when checking whether a memory service is running; when using robot SDK camera frames to perform memory ingestion or memory-guided retrieval; or when grounding robot tasks in prior visual/spatial experience.
基于 SOC 职业分类
正在显示 SKILL.md
| name | abotclaw-sdk-discovery |
| description | Discover how a robot is actually used by reading its deployed guide and SDK reference before writing code. Use when starting robot work, when the API is unclear, when a new robot is added, or when OpenClaw must determine the real robot usage pattern instead of guessing. |
This skill owns one question:
How should OpenClaw discover the real usage pattern of a robot before writing code?
This skill is the single place for:
Other files should reference this skill instead of duplicating SDK discovery instructions.
For AbotClaw, discovery should start from known service and robot configuration, not from broad local searching.
Use this order:
service.mdROBOT.mdcurl -s -L <ROBOT_BASE_URL>/docs/guide/html
curl -s -L <ROBOT_BASE_URL>/code/sdk/markdown
If the deployment exposes a health endpoint, check it before deeper calls:
curl -s <ROBOT_BASE_URL>/health
Before writing robot code, determine:
Before writing code, summarize the real usage pattern in plain terms.
A good summary should answer:
Only use broader fallback sources when the guide or SDK reference is missing or clearly incomplete.
Fallback sources may include:
Do not treat those as the default path.
Do not invent methods because they sound plausible. If the deployed docs do not show a method, treat it as unknown until confirmed.