- GitHub repo created and pushed
- Code complete with all features
- Documentation (README, INTEGRATION, DEPLOY)
- BoTTube.ai links added
- TypeScript built
- Python wheel built
- Posted to Moltbook, Clawsta, ClawCities
cd /home/scott/grazer-skill
# Login to NPM (one time)
npm login
# Username: (your NPM username)
# Password: (your NPM password)
# Email: scott@elyanlabs.ai
# Publish
npm publish --access public
# Verify
npm view @elyanlabs/grazercd /home/scott/grazer-skill
# Install twine (if not installed)
pip install twine
# Upload to PyPI
python3 -m twine upload dist/*
# Username: __token__
# Password: (your PyPI token)
# Verify
pip search grazer-skill# Using ClawHub CLI or API
curl -X POST https://clawhub.ai/api/skills \
-H "Authorization: Bearer clh_w2cSUND_qu_ZUqusQqKV97-s2tROfJ5rsCxKbfQFVy4" \
-H "Content-Type: application/json" \
-d '{
"name": "grazer",
"description": "Multi-platform content discovery for AI agents",
"version": "1.0.0",
"tags": ["content-discovery", "ai-agents", "social-media"],
"platforms": ["bottube", "moltbook", "clawcities", "clawsta"],
"npm_package": "@elyanlabs/grazer",
"pypi_package": "grazer-skill",
"github_repo": "Scottcjn/grazer-skill"
}'Location: /home/scott/grazer-configs/
moltbook-bot-config.json- For VPS .131bottube-agent-config.json- For VPS .153claw-ai-config.json- For Mac M2sophia-config.json- For Godot voice bridge
Default: "auto_respond": false (safe start)
To enable: Edit ~/.grazer/config.json and set "auto_respond": true
Training data location: ~/.grazer/training.json
Monitor with:
# View training stats
cat ~/.grazer/training.json | jq '.patterns'
# Watch agent loop live
tail -f ~/.grazer/agent.log- Update BoTTube skill page with download stats
- Post announcement on X/Twitter (after rate limit reset)
- Add to Elyan Labs website
- Create demo video
- Write blog post
Target for first week:
- 10+ NPM downloads
- 5+ PyPI installs
- 3+ GitHub stars
- Listed on ClawHub trending