Files
nanoclaw/.claude/skills/add-image-vision/SKILL.md
meeech 211d2b5877 docs: convert all skill instructions from npm to pnpm
Batch update 62 files across .claude/skills/ — SKILL.md, REMOVE.md,
and script files. Conversions: npm run -> pnpm run, npm install ->
pnpm install, npx -> pnpm exec/dlx, npm uninstall -> pnpm uninstall,
package-lock.json -> pnpm-lock.yaml, shebangs updated.
2026-04-17 09:22:45 +03:00

2.8 KiB

name, description
name description
add-image-vision Add image vision to NanoClaw agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.

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

  1. Check if src/image.ts exists — skip to Phase 3 if already applied
  2. Confirm sharp is installable (native bindings require build tools)

Prerequisite: WhatsApp must be installed first (skill/whatsapp merged). This skill modifies WhatsApp channel files.

Phase 2: Apply Code Changes

Ensure WhatsApp fork remote

git remote -v

If whatsapp is missing, add it:

git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git

Merge the skill branch

git fetch whatsapp skill/image-vision
git merge whatsapp/skill/image-vision || {
  git checkout --theirs pnpm-lock.yaml
  git add pnpm-lock.yaml
  git merge --continue
}

This merges in:

  • 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.ts and src/container-runner.ts
  • Image content block support in container/agent-runner/src/index.ts
  • sharp npm dependency in package.json

If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides.

Validate code changes

pnpm install
pnpm run build
pnpm exec vitest run src/image.test.ts

All tests must pass and build must be clean before proceeding.

Phase 3: Configure

  1. Rebuild the container (agent-runner changes need a rebuild):

    ./container/build.sh
    
  2. Sync agent-runner source to group caches:

    for dir in data/sessions/*/agent-runner-src/; do
      cp container/agent-runner/src/*.ts "$dir"
    done
    
  3. Restart the service:

    launchctl kickstart -k gui/$(id -u)/com.nanoclaw
    

Phase 4: Verify

  1. Send an image in a registered WhatsApp group
  2. Check the agent responds with understanding of the image content
  3. 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 pnpm ls sharp to 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.