add-image-vision
Add image vision to Deus agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.
pinned to #704abc9updated 2 weeks ago
Ask your AI client: “install skills/add-image-vision”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/add-image-visionmetahub onboarded this repo on the author's behalf.
If you own github.com/sliamh11/Deus on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
48
Last commit
2 weeks ago
Latest release
published
- #ai-assistant
- #ai-memory
- #claude-code
- #container-isolation
- #persistent-memory
- #self-improving-ai
- #semantic-memory
- #semantic-search
About this skill
Pulled from SKILL.md at publish time.
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.
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.704abc9· 2 weeks ago
Kind-specific
31Skill: SKILL.md present
found at .claude/skills/add-image-vision/SKILL.md · frontmatter source: SKILL.md
Skill: body content present
354 words · 2,502 chars · 6 sections · 2 code blocks
Skill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Skill: allowed-tools scope
no allowed-tools restriction (Claude may use anything)
Release history
1- releasecurrent704abc9warn2 weeks ago
Contents
Image Vision Skill
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.
Phase 1: Pre-flight
- Check if
src/image.tsexists — skip to Phase 3 if already applied - Confirm
sharpis installable (native bindings require build tools)
Prerequisite: WhatsApp must be installed first (via /add-whatsapp). This skill modifies WhatsApp channel files.
Phase 2: Apply Code Changes
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)- Image attachment handling in
src/channels/whatsapp.ts - Image passing to agent in
src/index.tsandsrc/container-runner.ts - Image content block support in
container/agent-runner/src/index.ts sharpnpm dependency inpackage.json
Validate code changes
npm install
npm run build
npx vitest run src/image.test.ts
All tests must pass and build must be clean before proceeding.
Phase 3: Configure
-
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
Phase 4: Verify
- Send an image in a registered WhatsApp group
- Check the agent responds with understanding of the image content
- Check logs for "Processed image attachment":
tail -50 groups/*/logs/container-*.log
Troubleshooting
- "Image - download failed": Check WhatsApp connection stability. The download may timeout on slow connections.
- "Image - processing failed": Sharp may not be installed correctly. Run
npm ls sharpto verify. - Agent doesn't mention image content: Check container logs for "Loaded image" messages. If missing, ensure agent-runner source was synced to group caches.
Reviews
No reviews yet. Be the first.
Related
Frontend Slides
Create beautiful slides on the web using Claude's frontend skills
Guizang Ppt Skill
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
orchestration-patterns
>
mh install skills/add-image-vision