add-image-vision
Skill1 starsChanged 9 months agoMITView on GitHub
Add image vision to NanoClaw agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.
- Installs packages
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- add-discordSkill
- add-gmailSkill
- add-ollama-toolSkill
- add-parallelSkill
- add-pdf-readerSkill
- add-slackSkill
- add-telegramSkill
- add-telegram-swarmSkill
- add-voice-transcriptionSkill
- add-whatsappSkill
- convert-to-apple-containerSkill
- customizeSkill
- debugSkill
- get-qodo-rulesSkill
- qodo-pr-resolverSkill
- setupSkill
- update-nanoclawSkill
- use-local-whisperSkill
- x-integrationSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Check .nanoclaw/state.yaml for add-image-vision — skip if already applied
- Distinctive: line 60
Check the agent responds with understanding of the image content
- Distinctive: line 61
Check logs for "Processed image attachment":
- Distinctive: line 68
"Image - download failed": Check WhatsApp connection stability.
- Distinctive: line 70
Agent doesn't mention image content: Check container logs for "Loaded image" messages.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Image Vision Skill
Adds the ability for NanoClaw 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
.nanoclaw/state.yamlforadd-image-vision— skip if already applied - Confirm
sharpis installable (native bindings require build tools)
Phase 2: Apply Code Changes
- Initialize the skills system if not already done:
npx tsx -e "import { initNanoclawDir } from './skills-engine/init.ts'; initNanoclawDir();" - Apply the skill:
npx tsx skills-engine/apply-skill.ts add-image-vision - Install new dependency:
npm install sharp - Validate:
npm run typecheck npm test
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.nanoclaw
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

