aldegad

Tenstorrent — Communication skill for Claude Code

Communication community

Tenstorrent console.tenstorrent.com skill for Claude Code / Codex / Agent SDK — Wan 2.2 text-to-video + OpenAI-compatible chat (DeepSeek-R1 / Qwen3-32B / Qwen3-VL).

How to install Tenstorrent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aldegad/tenstorrent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tenstorrent does

Tenstorrent console.tenstorrent.com skill for Claude Code / Codex / Agent SDK — Wan 2.2 text-to-video + OpenAI-compatible chat (DeepSeek-R1 / Qwen3-32B / Qwen3-VL).

Alternatives in Communication

  • Lark Coding Agent Bridge — Bot that bridges Feishu/Lark messenger with a local Claude Code or Codex CLI 2.4k ★
  • Watch Video — Watch and analyze a video file or YouTube URL — extracts frames and audio for understanding 1.3k ★
  • Nekro Agent — NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架,集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体,兼具高扩展性、多模态交互、实时状态推送和自动化 800 ★

README

Tenstorrent Skill

Tenstorrent `console.tenstorrent.com` skill for Claude Code, Codex, and Agent SDK: Wan 2.2 text-to-video plus OpenAI-compatible chat with DeepSeek-R1 and Qwen3-32B.

Install

Place `SKILL.md` at one of these paths:

~/.claude/skills/tenstorrent/SKILL.md
~/.codex/skills/tenstorrent/SKILL.md

Authentication

Create a Tenstorrent Console account at `https://console.tenstorrent.com`, generate an API key, and export it as an environment variable:

export TENSTORRENT_KEY="your-api-key"

Do not commit `.env` files or real API keys.

Chat

curl -sS -X POST "https://console.tenstorrent.com/v1/chat/completions" \
  -H "Authorization: Bearer $TENSTORRENT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-32B",
    "messages": [{"role":"user","content":"Say hello in one short sentence."}],
    "max_tokens": 256
  }' | jq -r '.choices[0].message.content // .choices[0].message.reasoning // .choices[0].message.reasoning_content'

Video

curl -sS -X POST "https://console.tenstorrent.com/v1/video/jobs" \
  -H "Authorization: Bearer $TENSTORRENT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Wan2.2-T2V-A14B-Diffusers",
    "prompt": "A quiet cinematic shot of a small robot waving beside a workbench.",
    "negative_prompt": "low quality, distorted hands, blurry"
  }'

Minimal runnable examples live in `examples/`.

License

MIT. See `LICENSE`.