Install
openclaw skills install dash-cogAI dashboard and web app generation powered by CellCog. Interactive dashboards, KPI trackers, data visualization, charts, analytics apps, data explorers, calculators, games. Responsive HTML apps with real-time filters.
openclaw skills install dash-cogBuild interactive dashboards, data visualizations, and web apps with AI.
For your first CellCog task in a session, read the cellcog skill for the full SDK reference — file handling, chat modes, timeouts, and more.
OpenClaw (fire-and-forget):
result = client.create_chat(
prompt="[your task prompt]",
notify_session_key="agent:main:main",
task_label="my-task",
chat_mode="agent",
)
All agents except OpenClaw (blocks until done):
from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")
result = client.create_chat(
prompt="[your task prompt]",
task_label="my-task",
chat_mode="agent",
)
print(result["message"])
Interactive dashboards for data analysis:
Monitor key performance indicators:
Interactive charts and graphs:
Tools for exploring datasets:
Web applications beyond dashboards:
Simple web-based games:
CellCog dashboards can include:
| Feature | Description |
|---|---|
| Interactive Charts | Line, bar, pie, scatter, area, heatmaps, treemaps, and more |
| Filters | Date ranges, dropdowns, search, multi-select |
| KPI Cards | Key metrics with trends and comparisons |
| Data Tables | Sortable, searchable, paginated tables |
| Drill-Down | Click to explore deeper levels of data |
| Responsive Design | Works on desktop, tablet, and mobile |
| Dark/Light Themes | Automatic theme support |
You can provide data via:
Choose based on complexity:
| Scenario | Recommended Mode |
|---|---|
| Standard dashboards, KPI trackers, data visualizations, charts | "agent" |
| Complex interactive apps, games, novel data explorers | "agent team" |
Default to "agent" for most dashboard requests. CellCog's agent mode handles charts, tables, filters, and interactivity efficiently.
Reserve "agent team" for truly complex applications requiring significant design thinking—like building a novel game mechanic or a highly customized analytical tool with multiple interconnected features.
Sales analytics dashboard:
"Create an interactive sales analytics dashboard with:
- KPI cards: Total Revenue, Orders, Average Order Value, Growth Rate
- Line chart: Monthly revenue trend (last 12 months)
- Bar chart: Revenue by product category
- Pie chart: Sales by region
- Data table: Top 10 products by revenue
Include date range filter. Use this data: [upload CSV or describe data] Modern, professional design with blue color scheme."
Startup metrics dashboard:
"Build a SaaS metrics dashboard for a startup showing:
- MRR and growth rate
- Customer acquisition funnel (visitors → signups → trials → paid)
- Churn rate trend
- LTV:CAC ratio
- Revenue by plan tier
Generate realistic sample data for a B2B SaaS company growing from $10K to $100K MRR over 12 months."
Interactive data explorer:
"Create an interactive explorer for this employee dataset [upload CSV]. Include:
- Searchable, sortable data table
- Filters for department, location, tenure
- Charts: headcount by department, salary distribution, tenure histogram
- Summary statistics panel
Allow users to download filtered data as CSV."
Simple game:
"Create a Wordle-style word guessing game. 5-letter words, 6 attempts, color feedback (green = correct position, yellow = wrong position, gray = not in word). Include keyboard, game statistics, and share results feature. Clean, modern design."
Prioritize key metrics: Don't cram everything. Lead with the 3-5 most important KPIs.
Describe the data: What columns exist? What do they mean? What time period?
Specify chart types: "Line chart for trends, bar chart for comparisons, pie for composition."
Include interactivity: "Filter by date range", "Click to drill down", "Hover for details."
Design direction: "Modern minimal", "Corporate professional", "Playful and colorful", specific color schemes.
Responsive needs: "Desktop only" vs "Must work on mobile."
Run /cellcog-setup (or /cellcog:cellcog-setup depending on your tool) to install and authenticate.
OpenClaw users: Run clawhub install cellcog instead.
Manual setup: pip install -U cellcog and set CELLCOG_API_KEY. See the cellcog skill for SDK reference.