Skip to content

Commit afa21e0

Browse files
Merge pull request #110 from MarcSkovMadsen/enhancement/planners
Enhancement/planners
2 parents 1059dca + c2c9b82 commit afa21e0

15 files changed

Lines changed: 151 additions & 88 deletions

src/holoviz_mcp/config/resources/agents/holoviz-mcp-planner.agent.md renamed to .github/agents/holoviz-app-planner.agent.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
---
2-
name: HoloViz Planner
2+
name: HoloViz App Planner
33
description: Create a detailed implementation plan for HoloViz data visualizations, dashboards, and data apps without modifying code
44
tools: ['holoviz/*', 'read/readFile', 'read/problems', 'agent/runSubagent', 'web/fetch', 'web/githubRepo', 'search/codebase', 'search/usages', 'search/searchResults', 'vscode/vscodeAPI']
55
handoffs:

.gitignore

Lines changed: 2 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -381,9 +381,5 @@ $RECYCLE.BIN/
381381
# End of https://www.toptal.com/developers/gitignore/api/linux,macos,direnv,python,windows,pycharm+all,visualstudiocode,vim
382382

383383
.pixi
384-
.github/agents/holoviz-mcp-*.agent.md
385-
.github/skills/holoviews.md
386-
.github/skills/panel.md
387-
.github/skills/hvplot.md
388-
.github/skills/holoviews.md
389-
.github/skills/panel-material-ui.md
384+
.github/agents/*
385+
.github/skills/*
10.8 KB
Loading
24.3 KB
Loading
8.82 KB
Loading
3.01 KB
Loading
97.2 KB
Loading

docs/how-to/installation.md

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,14 @@ For other installation methods, see the [uv installation guide](https://docs.ast
2525
Install HoloViz MCP as a uv tool:
2626

2727
```bash
28+
# Basic installation
2829
uv tool install holoviz-mcp
30+
31+
# Alternative installation with a broad range of PyData packages
32+
uv tool install holoviz-mcp[pydata]
33+
34+
# Alternative installation with extra packages
35+
uv tool install holoviz-mcp --with altair --with polars
2936
```
3037

3138
### Install Chromium

docs/tutorials/copilot.md

Lines changed: 40 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -4,12 +4,14 @@
44
In this tutorial, you'll learn how to use the HoloViz MCP server with GitHub Copilot in VS Code.
55

66
!!! tip "What you'll learn"
7+
78
- How to use HoloViz MCP resources to enhance Copilot's responses
89
- How to add custom Copilot agents optimized for HoloViz MCP
910
- How to create a plot using Copilot + HoloViz MCP
1011
- How to build a dashboard using Copilot + HoloViz MCP
1112

1213
!!! note "Prerequisites"
14+
1315
- VS Code installed
1416
- GitHub Copilot subscription and extension installed
1517
- HoloViz MCP server installed and configured ([Installation guide](../how-to/installation.md))
@@ -20,10 +22,10 @@ In this tutorial, you'll learn how to use the HoloViz MCP server with GitHub Cop
2022

2123
Start the Holoviz MCP Server:
2224

23-
1. In VS Code, open the Command Palette (`Ctrl+Shift+P` or `Cmd+Shift+P`)
24-
2. Type "MCP: List Servers" and press Enter
25-
3. Choose the "holoviz" server
26-
4. Select "Start Server"
25+
- In VS Code, open the Command Palette (`Ctrl+Shift+P` or `Cmd+Shift+P`)
26+
- Type "MCP: List Servers" and press Enter
27+
- Choose the "holoviz" server
28+
- Select "Start Server"
2729

2830
Repeat 1.+2. and verify that the `holoviz` mcp server is now running.
2931

@@ -35,84 +37,87 @@ Repeat 1.+2. and verify that the `holoviz` mcp server is now running.
3537

3638
[Custom agents](https://code.visualstudio.com/docs/copilot/customization/custom-agents) enable you to configure the AI to adopt different personas tailored to specific development roles and tasks. To install the `holoviz-mcp` agents:
3739

38-
1. Open a terminal in VS Code (`` Ctrl+` `` or `Terminal > New Terminal`).
39-
2. Run the following command:
40+
- Open a terminal in VS Code (`` Ctrl+` `` or `Terminal > New Terminal`).
41+
- Run the following command:
4042

4143
```bash
42-
uvx holoviz-mcp update copilot
44+
uvx holoviz-mcp install copilot
4345
```
4446

45-
You should see output confirming that agents were installed to `.github/agents/`.
46-
3. Wait for the command to complete successfully.
47+
- Wait for the command to complete successfully.
48+
49+
You should see output confirming that agents were installed to `.github/agents/`.
4750

4851
!!! note "What's happening"
49-
This command installs custom Copilot agents specifically designed for HoloViz development. These agents understand the holoviz-mcp server and can use it to understand the architecture patterns and best practices for Panel, hvPlot, and other HoloViz libraries.
52+
This command installs custom Copilot agents specifically designed for HoloViz development. These agents understand the `holoviz-mcp` server and can use it to understand the architecture patterns and best practices for Panel, hvPlot, and other HoloViz libraries.
5053

5154
!!! tip
52-
Run `holoviz-mcp update copilot --skills` to populate the `.github/skills` folder too. See [Use Agent Skills in VS Code](https://code.visualstudio.com/docs/copilot/customization/agent-skills) for more info.
55+
Run `holoviz-mcp install copilot --skills` to populate the `.github/skills` folder too. See [Use Agent Skills in VS Code](https://code.visualstudio.com/docs/copilot/customization/agent-skills) for more info.
5356

5457
---
5558

56-
### Creating a Plan with the HoloViz Planner Agent
59+
### Creating a Plan with the HoloViz App Planner Agent
5760

5861
Instead of diving straight into code, let's use the specialized agent to plan our application architecture.
5962
60-
1. In the Copilot Chat interface, click the **Set Agent** dropdown.
61-
2. Select **`HoloViz Planner`** from the list.
62-
3. Type the following prompt:
63+
- In the Copilot Chat interface, click the **Set Agent** dropdown.
64+
- Select **`HoloViz App Planner`** from the list.
65+
66+
![HoloViz App Planner](../assets/images/copilot-holoviz-app-planner.png)
67+
68+
- Type the following prompt:
6369
6470
```text
6571
Create a plan for a stock dashboard that displays historical prices and trading volume
6672
```
6773
68-
4. Press Enter and wait for the agent to respond.
74+
- Press Enter and wait for the agent to respond.
6975
7076
![Copilot Dashboard Plan](../assets/images/copilot-dashboard-plan.png)
7177
7278
!!! note "What's happening"
73-
The HoloViz Planner agent analyzes your requirements and creates an architecture plan following HoloViz best practices. This ensures your application is well-structured before you write any code.
79+
The HoloViz App Planner agent analyzes your requirements and creates an architecture plan following HoloViz best practices. This ensures your application is well-structured before you write any code.
7480
7581
---
7682
7783
### Implementing the Dashboard
7884
7985
Now that you have a plan, let's ask Copilot to help implement it.
8086
81-
1. In the Copilot Chat, respond to the plan with:
87+
- In the Copilot Chat, respond to the plan with:
8288
8389
```text
8490
Implement the plan outlined above.
8591
```
8692
87-
2. Copilot will generate the code for your dashboard. Review the suggestions.
88-
89-
!!! note "What you'll see"
90-
A complete Python script that includes:
93+
- Copilot will generate the code for your dashboard and test it.
9194
92-
- Imports for Panel, hvPlot, and data handling libraries
93-
- Data loading logic (likely using pandas)
94-
- Interactive widgets for user controls
95-
- Plots created with hvPlot
96-
- Panel layout to organize everything
95+
To learn more check out the [Weather Dashboard Tutorial](weather-dashboard.md)!
9796
9897
---
9998
10099
## Using HoloViz Resources
101100
102101
MCP resources contain curated knowledge that enhances Copilot's understanding of specific frameworks. Let's load the hvPlot best practice skills and use them to create a basic data visualization.
103102
104-
1. In the Copilot Chat Interface, click "Add Context" (`CTRL + '`)
105-
2. Select "MCP Resources".
106-
3. You'll see a list of available resources. Select **`holoviz_hvplot`**.
107-
![HoloViz MCP Resources](../assets/images/holoviz-mcp-resources.png)
108-
4. Notice in the chat interface that the resource is now added to the context.
109-
![HvPlot Resource Added](../assets/images/holoviz-mcp-vscode-resource-added.png)
110-
5. Ask the agent:
103+
- In the Copilot Chat Interface, click "Add Context" (`CTRL + '`)
104+
- Select "MCP Resources".
105+
- You'll see a list of available resources. Select **`holoviz_hvplot`**.
106+
107+
![HoloViz MCP Resources](../assets/images/holoviz-mcp-resources.png)
108+
109+
- Notice in the chat interface that the resource is now added to the context.
110+
111+
![HvPlot Resource Added](../assets/images/holoviz-mcp-vscode-resource-added.png)
112+
113+
- Ask the agent:
111114
112115
```bash
113116
Please create a basic hvplot visualization in a script.py file.
114117
```
115118
119+
![HvPlot Plot](../assets/images/holoviz-mcp-vscode-resource-plot.png)
120+
116121
!!! tip
117122
You can add multiple resources to the context. Try browsing and adding `holoviz_panel` as well to get Panel-specific guidance.
118123
@@ -122,7 +127,7 @@ MCP resources contain curated knowledge that enhances Copilot's understanding of
122127
123128
In this tutorial, you've learned how to:
124129
125-
✅ **Use specialized agents** – You used the HoloViz Planner agent to design your application architecture.
130+
✅ **Use specialized agents** – You used the HoloViz App Planner agent to design your application architecture.
126131
127132
✅ **Use specialized resources** – You loaded HoloViz best practice skills into Copilot's context using MCP resources.
128133

docs/tutorials/stock-analysis.md

Lines changed: 28 additions & 31 deletions
Original file line numberDiff line numberDiff line change
@@ -1,58 +1,55 @@
11
# Tutorial: Building an Interactive Stock Analysis Report
22

3-
In this tutorial, you will create a complete stock analysis report that visualizes price movements and trading patterns for multiple stocks. By the end, you'll have built an interactive report that displays financial data with professional charts and statistics.
3+
In this tutorial, you will create a complete stock analysis report that visualizes price movements and trading patterns for multiple stocks.
44

5-
<iframe src="https://www.youtube.com/embed/placeholder" title="Tutorial: Building a Stock Analysis Report with HoloViz MCP" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen style="display:block;height:300px;width:500px;margin-left:auto;margin-right:auto"></iframe>
5+
By the end, you'll have built an interactive report that displays financial data with professional charts and statistics.
6+
7+
<!-- <iframe src="https://www.youtube.com/embed/placeholder" title="Tutorial: Building a Stock Analysis Report with HoloViz MCP" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen style="display:block;height:300px;width:500px;margin-left:auto;margin-right:auto"></iframe> -->
68

79
!!! tip "What you'll learn"
8-
- How to use the HoloViz Planner agent to design data applications
9-
- How to fetch and process financial data with Python
10-
- How to create interactive charts using hvPlot
11-
- How to build reports with Panel components
12-
- How to use the `holoviz_display` tool to visualize your work
10+
- How to use the *HoloViz Analysis Planner* agent to design data applications
11+
- How to use the `holoviz_display` tool to quickly visualize and persist your work
1312

1413
!!! note "Prerequisites"
1514
Before starting, ensure you have:
1615

17-
- HoloViz MCP installed and configured ([Getting Started Guide](getting-started.md))
1816
- VS Code with GitHub Copilot or another MCP-compatible AI assistant
19-
- Configured the `HoloViz Planner` agent. ([HoloViz Agents](copilot.md/#using-holoviz-agents))
17+
- HoloViz MCP installed and configured ([Getting Started Guide](getting-started.md))
18+
- Configured the `HoloViz Analysis Planner` agent. ([HoloViz Agents](copilot.md/#using-holoviz-agents))
2019
- The HoloViz MCP server running ([How to start the server](getting-started.md/#start-the-server))
2120
- `yfinance` installed in the virtual environment where you run `holoviz-mcp`: `pip install yfinance`
2221

23-
## Step 1: Plan Your Report with the HoloViz Planner
22+
## Step 1: Plan Your Report with the HoloViz Analysis Planner
2423

25-
First, let's use the HoloViz Planner agent to design our application architecture. This agent understands best practices for organizing Panel reports and will help us create a solid plan before writing code.
24+
First, let's use the HoloViz Analysis Planner agent to design our application architecture. This agent understands best practices for organizing Panel reports and will help us create a solid plan before writing code.
2625

2726
1. In VS Code, open the Copilot Chat interface
28-
2. Click the **Set Agent** dropdown and select **HoloViz Planner**
27+
2. Click the **Set Agent** dropdown and select **HoloViz Analysis Planner**
2928
3. Ask the agent:
3029

31-
```text
32-
Please plan how to analyze and create a report showing AAPL and META's hourly bar data history for the last 5 days and display the data as charts:
30+
```text
31+
Please plan how to analyze and create a report showing AAPL and META's hourly bar data history for the last 5 days and display the data as charts:
3332
34-
- Individual price charts for each stock
35-
- Summary statistics table
36-
- Normalized comparison overlay
37-
- Trading volume visualization
38-
- Professional styling and error handling
33+
- Individual price charts for each stock
34+
- Summary statistics table
35+
- Normalized comparison overlay
36+
- Trading volume visualization
37+
- Professional styling and error handling
3938
40-
Display using the #holoviz_display tool. KISS - Keep it simple stupid.
41-
```
39+
Display using the #holoviz_display tool. KISS - Keep it simple stupid.
40+
```
4241
43-
![HoloViz Planner](../assets/images/stock-analysis-holoviz-planner.png)
42+
![HoloViz Analysis Planner](../assets/images/stock-analysis-holoviz-planner.png)
4443
4544
4. Press Enter and wait for the agent to respond
4645
47-
!!! success "What you'll see"
48-
The planner will provide a detailed architecture plan including:
49-
50-
- Data sources and how to fetch stock data
51-
- Chart types to use for price and volume visualization
52-
- Panel components for layout and statistics
53-
- Error handling strategies
46+
!!! success "What you'll see"
47+
The planner will provide a detailed architecture plan including:
5448
55-
You should see a structured plan that breaks down the report into logical components. This planning step helps ensure we build a well-organized application.
49+
- Data sources and how to fetch stock data
50+
- Chart types to use for price and volume visualization
51+
- Panel components for layout and statistics
52+
- Error handling strategies
5653
5754
## Step 2: Implement the Report
5855
@@ -166,7 +163,7 @@ pip install yfinance
166163

167164
Congratulations! In this tutorial, you have:
168165

169-
- ✅ Used the HoloViz Planner agent to design a data report
166+
- ✅ Used the HoloViz Analysis Planner agent to design a data report
170167
- ✅ Implemented a complete stock analysis application
171168
- ✅ Created interactive charts with hvPlot
172169
- ✅ Built a multi-component report with Panel

0 commit comments

Comments
 (0)