一键导入
add-image-vision
Add image vision to Deus agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.
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。
菜单
Add image vision to Deus agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.
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。
基于 SOC 职业分类
Save this session to the vault and update the semantic memory index
Capture a repeatable task procedure from the just-completed work as a durable, queryable memory node, so the steps are recalled automatically next time instead of re-derived. Triggers on "learn this procedure", "remember how to do this", "save this as a procedure", "/learn-procedure".
Add Asana project management MCP integration to Deus. Gives host-side Claude Code sessions read/write access to Asana tasks, projects, sections, and tags via @roychri/mcp-server-asana.
[DEPRECATED] Replaced by scripts/code_search.py (native sqlite-vec + Ollama). Do not use.
Add OpenAI/Codex as a backend. Guides through API key setup, service backend configuration, optional CLI setup, and verification. Can run alongside Claude (default) or replace it.
Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.
| name | add-image-vision |
| description | Add image vision to Deus agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks. |
| disable-model-invocation | true |
Adds the ability for Deus agents to see and understand images sent via WhatsApp. Images are downloaded, resized with sharp, saved to the group workspace, and passed to the agent as base64-encoded multimodal content blocks.
src/image.ts exists — skip to Phase 3 if already appliedsharp is installable (native bindings require build tools)Prerequisite: WhatsApp must be installed first (via /add-whatsapp). This skill modifies WhatsApp channel files.
Image vision is part of the WhatsApp MCP package in packages/. Check if the image module already exists:
test -f src/image.ts && echo "Already present" || echo "Not present"
If not present, the WhatsApp MCP package should include image vision support. Ensure the WhatsApp channel is installed and up to date by running /add-whatsapp.
The following files are involved:
src/image.ts (image download, resize via sharp, base64 encoding)src/image.test.ts (8 unit tests)src/channels/whatsapp.tssrc/index.ts and src/container-runner.tscontainer/agent-runner/src/index.tssharp npm dependency in package.jsonnpm install
npm run build
npx vitest run src/image.test.ts
All tests must pass and build must be clean before proceeding.
Rebuild the container (agent-runner changes need a rebuild):
./container/build.sh
Sync agent-runner source to group caches:
for dir in data/sessions/*/agent-runner-src/; do
cp container/agent-runner/src/*.ts "$dir"
done
Restart the service:
launchctl kickstart -k gui/$(id -u)/com.deus
tail -50 groups/*/logs/container-*.log
npm ls sharp to verify.