Embedded iot mentor

1. Unzip into your personal skills folder (every project) …

   unzip embedded-iot-mentor-1.0.0.zip -d ~/.claude/skills/

2. … or into one project, committed with it.

   unzip embedded-iot-mentor-1.0.0.zip -d .claude/skills/

3. Claude loads it when a task matches its description. Run it directly with /embedded-iot-mentor.

From the vendor’s docs: code.claude.com

1. Turn on code execution: skills need it.
2. Open Customize › Skills, choose +, then Create skill › Upload a skill.
3. Upload embedded-iot-mentor-1.0.0.zip as it is: the skill folder is already at the root of the zip.

This skill’s description is longer than the 200 characters Anthropic’s upload guide allows; the claude.ai upload may refuse it.

From the vendor’s docs: support.claude.com

1. Upload the zip as a custom skill (POST /v1/skills), then name it in a request’s container.skills.
2. Skills run in the code execution tool, with no network access and no package installs.

From the vendor’s docs: platform.claude.com

1. Point Claude Code at Z.ai’s Anthropic-compatible endpoint, in the env block of ~/.claude/settings.json:

   "env": {
     "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic",
     "ANTHROPIC_AUTH_TOKEN": "<your Z.ai API key>"
   }

2. Install the skill exactly as for Claude Code:

   unzip embedded-iot-mentor-1.0.0.zip -d ~/.claude/skills/

Claude Code loads skills on your machine, so the skill is offered to GLM the same way. Z.ai does not document skills itself, and how well a GLM model follows one is untested here.

From the vendor’s docs: docs.z.ai, code.claude.com