### Initial Authentication Setup Workflow

Source: https://github.com/practicalswan/agent-skills/blob/main/notebooklm-management/references/workflows.md

Guides the user through the first-time authentication setup for NotebookLM, which involves opening a browser for Google OAuth. Requires internet connection and browser permissions.

```python
def initial_authentication_setup():
    """Complete first-time authentication setup"""
    
    print("=== NotebookLM Authentication Setup ===")
    print("This will open a browser window for Google OAuth.")
    print("\nRequirements:")
    print("• Google account with NotebookLM access")
    print("• Browser window permission")
    print("• Internet connection\n")
    
    proceed = input("Proceed? (yes/no): ").lower()
    if proceed != "yes":
        print("Setup cancelled.")
        return False
    
    print("\nOpening browser for authentication...")
    notebooklm.auth_setup()
    
    print("\n✓ Authentication complete!")
    print("\nVerifying health...")
    health_status = get_health()
    
    if health_status.get("status") == "authenticated":
        print("✓ Successfully authenticated!")
        return True
    else:
        print("✗ Authentication may have failed.")
        print("Please run authentication again or check troubleshoot guide.")
        return False
```

--------------------------------

### Create New Project with shadcn/ui

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-shadcn-ui/resources/setup-guide.md

Use this command to start a new project with shadcn/ui. It offers an interactive setup to customize framework, style, and more.

```bash
npx shadcn@latest create
```

--------------------------------

### Run NotebookLM Authentication Setup

Source: https://github.com/practicalswan/agent-skills/blob/main/notebooklm-management/references/troubleshooting.md

Use this command for the initial authentication setup. It opens a browser for OAuth, requests Google account login and NotebookLM permissions, and saves credentials locally. Verify setup with a health check.

```python
# Run authentication setup
notebooklm.auth-setup()

# This will:
# 1. Open browser for OAuth flow
# 2. Request Google account login
# 3. Request NotebookLM permissions
# 4. Save session credentials locally

# After setup, verify with health check
get_health()
```

--------------------------------

### Add Individual shadcn/ui Components

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-design/references/shadcn-components.md

Install specific shadcn/ui components using the 'add' command. This example shows how to add 'button', 'card', and 'dialog'.

```bash
npx shadcn-ui@latest add button
npx shadcn-ui@latest add card
npx shadcn-ui@latest add dialog
```

--------------------------------

### Manual Setup for Vite + React Project

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-shadcn-ui/resources/setup-guide.md

Steps to manually set up shadcn/ui in a Vite + React project. This involves creating the Vite project, installing Tailwind CSS, initializing shadcn/ui, and adding components.

```bash
npm create vite@latest my-app -- --template react-ts
cd my-app
npm install

npm install -D tailwindcss postcss autoprefixer
npx tailwindcss init -p

npx shadcn@latest init

npx shadcn@latest add button
```

--------------------------------

### YAML Configuration Example

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/nvinfer_config.md

Example of nvinfer configuration using the recommended YAML format.

```yaml
property:
  gpu-id: 0
  net-scale-factor: 0.00392156862745098
  onnx-file: /path/to/model.onnx
  batch-size: 1
  # ... more properties

class-attrs-all:
  topk: 20
  pre-cluster-threshold: 0.2
```

--------------------------------

### GitHub Actions npm Cache Setup

Source: https://github.com/practicalswan/agent-skills/blob/main/devops-tooling/examples/github-actions-templates.md

Sets up Node.js and enables npm caching for faster dependency installation.

```yaml
# .github/workflows/caching-examples.yml
name: Caching Reference

on:
  workflow_dispatch:

jobs:
  npm-cache:
    name: npm with built-in cache
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: '20'
          cache: 'npm'
      - run: npm ci
```

--------------------------------

### Multi-Stream Camera Configuration Example

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/tracker_config.md

This snippet demonstrates how to configure camera calibration files for multi-stream setups. Each stream requires its own calibrated camera information file due to varying positions and orientations.

```yaml
ObjectModelProjection:
  cameraModelFilepath:
    - configs/camInfo_stream0.yml    # stream 0
    - configs/camInfo_stream1.yml    # stream 1
    - configs/camInfo_stream2.yml    # stream 2
  outputVisibility: 1
  outputFootLocation: 1
  outputConvexHull: 1
  minPoseConfidence: 0.5

```

--------------------------------

### Start Benchmark Timer

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-import-vision-model/references/engine-build.md

Records the start time for Step 5 of the benchmarking process.

```bash
STEP5_START=$(date +%s.%N)
```

--------------------------------

### Install Tracker Support (libmosquitto)

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/docker_containers.md

Installs the libmosquitto1 package, which may be required for certain tracker functionalities.

```bash
apt-get install -y libmosquitto1
```

--------------------------------

### INI-style Configuration Example

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/nvinfer_config.md

Example of nvinfer configuration using the INI-style text format.

```ini
[property]
gpu-id=0
net-scale-factor=0.00392156862745098
onnx-file=/path/to/model.onnx
batch-size=1
# ... more properties

[class-attrs-all]
topk=20
pre-cluster-threshold=0.2
```

--------------------------------

### Setup Instructions for Icon Libraries

Source: https://github.com/practicalswan/agent-skills/blob/main/excalidraw-diagram-generator/SKILL.md

Use these instructions when a user requests specific architecture icons that are not yet available. This involves downloading a library, placing it correctly, and running a script to split it into individual icons.

```text
To use [AWS/GCP/Azure/etc.] architecture icons, please follow these steps:

1. Visit https://libraries.excalidraw.com/
2. Search for "[AWS Architecture Icons/etc.]" and download the .excalidrawlib file
3. Create directory: skills/excalidraw-diagram-generator/libraries/[icon-set-name]/
4. Place the downloaded file in that directory
5. Run the splitter script:
   python skills/excalidraw-diagram-generator/scripts/split-excalidraw-library.py skills/excalidraw-diagram-generator/libraries/[icon-set-name]/

This will split the library into individual icon files for efficient use.
After setup is complete, I can create your diagram using the actual AWS/cloud icons.

Alternatively, I can create the diagram now using simple shapes (rectangles, ellipses)
which you can later replace with icons manually in Excalidraw.
```

--------------------------------

### Install rag-perf with uv

Source: https://github.com/practicalswan/agent-skills/blob/main/rag-perf/SKILL.md

Installs the rag-perf package into its own uv-managed virtual environment. Use this for basic setup.

```bash
uv sync --project scripts/rag-perf
```

--------------------------------

### NVIDIA Container Toolkit Installation Message

Source: https://github.com/practicalswan/agent-skills/blob/main/rag-blueprint/references/deploy.md

Guides the user to install the NVIDIA Container Toolkit if it is missing and required for self-hosted deployments.

```shell
Install NVIDIA Container Toolkit. See https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
```

--------------------------------

### Set up Cosmos DB Emulator

Source: https://github.com/practicalswan/agent-skills/blob/main/microsoft-development/examples/azure-function-api-example.md

Instructions for setting up the Cosmos DB Emulator, either by downloading for Windows or using a Docker container.

```bash
# Windows: Download from https://aka.ms/cosmosdb-emulator
# Docker:
docker run -p 8081:8081 -p 10250-10255:10250-10255 mcr.microsoft.com/cosmosdb/linux/azure-cosmos-emulator
```

--------------------------------

### Example File Structure

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-shadcn-ui/resources/setup-guide.md

Illustrates a typical project structure for integrating shadcn/ui components.

```tree
src/
  ├── components/
  │   └── ui/
  ├── lib/
  │   └── utils.ts
  └── index.css (or globals.css)
```

--------------------------------

### Get Stream Info using curl

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/rest_api_dynamic.md

Example curl command to retrieve information about the current streams using the GET /api/v1/stream/get-stream-info endpoint.

```bash
# Get stream info
curl -X GET 'http://localhost:9000/api/v1/stream/get-stream-info'
```

--------------------------------

### Complete MCP Server Example

Source: https://github.com/practicalswan/agent-skills/blob/main/mcp-builder/reference/node_mcp_server.md

This script sets up an MCP server for the Example Service, including user search functionality. It requires the EXAMPLE_API_KEY environment variable and can run via stdio or HTTP transport.

```typescript
#!/usr/bin/env node
/**
 * MCP Server for Example Service.
 *
 * This server provides tools to interact with Example API, including user search, 
 * project management, and data export capabilities.
 */

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
import axios, { AxiosError } from "axios";

// Constants
const API_BASE_URL = "https://api.example.com/v1";
const CHARACTER_LIMIT = 25000;

// Enums
enum ResponseFormat {
  MARKDOWN = "markdown",
  JSON = "json"
}

// Zod schemas
const UserSearchInputSchema = z.object({
  query: z.string()
    .min(2, "Query must be at least 2 characters")
    .max(200, "Query must not exceed 200 characters")
    .describe("Search string to match against names/emails"),
  limit: z.number()
    .int()
    .min(1)
    .max(100)
    .default(20)
    .describe("Maximum results to return"),
  offset: z.number()
    .int()
    .min(0)
    .default(0)
    .describe("Number of results to skip for pagination"),
  response_format: z.nativeEnum(ResponseFormat)
    .default(ResponseFormat.MARKDOWN)
    .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable")
}).strict();

type UserSearchInput = z.infer<typeof UserSearchInputSchema>;

// Shared utility functions
async function makeApiRequest<T>(
  endpoint: string,
  method: "GET" | "POST" | "PUT" | "DELETE" = "GET",
  data?: any,
  params?: any
): Promise<T> {
  try {
    const response = await axios({
      method,
      url: `${API_BASE_URL}/${endpoint}`,
      data,
      params,
      timeout: 30000,
      headers: {
        "Content-Type": "application/json",
        "Accept": "application/json"
      }
    });
    return response.data;
  } catch (error) {
    throw error;
  }
}

function handleApiError(error: unknown): string {
  if (error instanceof AxiosError) {
    if (error.response) {
      switch (error.response.status) {
        case 404:
          return "Error: Resource not found. Please check the ID is correct.";
        case 403:
          return "Error: Permission denied. You don't have access to this resource.";
        case 429:
          return "Error: Rate limit exceeded. Please wait before making more requests.";
        default:
          return `Error: API request failed with status ${error.response.status}`;
      }
    } else if (error.code === "ECONNABORTED") {
      return "Error: Request timed out. Please try again.";
    }
  }
  return `Error: Unexpected error occurred: ${error instanceof Error ? error.message : String(error)}`;
}

// Create MCP server instance
const server = new McpServer({
  name: "example-mcp",
  version: "1.0.0"
});

// Register tools
server.registerTool(
  "example_search_users",
  {
    title: "Search Example Users",
    description: `[Full description as shown above]`,
    inputSchema: UserSearchInputSchema,
    annotations: {
      readOnlyHint: true,
      destructiveHint: false,
      idempotentHint: true,
      openWorldHint: true
    }
  },
  async (params: UserSearchInput) => {
    // Implementation as shown above
  }
);

// Main function
// For stdio (local):
async function runStdio() {
  if (!process.env.EXAMPLE_API_KEY) {
    console.error("ERROR: EXAMPLE_API_KEY environment variable is required");
    process.exit(1);
  }

  const transport = new StdioServerTransport();
  await server.connect(transport);
  console.error("MCP server running via stdio");
}

// For streamable HTTP (remote):
async function runHTTP() {
  if (!process.env.EXAMPLE_API_KEY) {
    console.error("ERROR: EXAMPLE_API_KEY environment variable is required");
    process.exit(1);
  }

  const app = express();
  app.use(express.json());

  app.post('/mcp', async (req, res) => {
    const transport = new StreamableHTTPServerTransport({
      sessionIdGenerator: undefined,
      enableJsonResponse: true
    });
    res.on('close', () => transport.close());
    await server.connect(transport);
    await transport.handleRequest(req, res, req.body);
  });

  const port = parseInt(process.env.PORT || '3000');
  app.listen(port, () => {
    console.error(`MCP server running on http://localhost:${port}/mcp`);
  });
}

// Choose transport based on environment
const transport = process.env.TRANSPORT || 'stdio';
if (transport === 'http') {
  runHTTP().catch(error => {
    console.error("Server error:", error);
    process.exit(1);
  });
} else {
  runStdio().catch(error => {
    console.error("Server error:", error);
    process.exit(1);
  });
}

```

--------------------------------

### Explicitly State Package Dependencies

Source: https://github.com/practicalswan/agent-skills/blob/main/writing-skills/anthropic-best-practices.md

Clearly list required package installations before providing code examples. This ensures users know what needs to be installed to run the script.

```markdown
Install required package: `pip install pypdf`

Then use it:
```python
from pypdf import PdfReader
reader = PdfReader("file.pdf")
```
```

--------------------------------

### DeepStream Configuration Example

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-import-vision-model/references/report-generation.md

Example of nvinfer configuration key fields, typically used in DeepStream applications. This block shows essential parameters for inference engine setup.

```ini
[property]
		gpu-id=0
		net-scale-factor=0.00392156862745098
		... (other parameters)
```

--------------------------------

### Run Example Validation for Various Languages

Source: https://github.com/practicalswan/agent-skills/blob/main/code-examples-sync/references/verification.md

Execute these commands to validate code examples for JavaScript/TypeScript, Python, Rust, and Go. Ensure your project has the necessary tools and dependencies installed.

```bash
# Example validation for various languages

```

```bash
npm run docs:test-examples  # JavaScript/TypeScript
```

```bash
python -m doctest docs/     # Python
```

```bash
cargo test --doc            # Rust
```

```bash
go test -run=Doc            # Go
```

--------------------------------

### AMQP Configuration File Example

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/kafka_messaging.md

Example configuration for connecting to a RabbitMQ server, including hostname, port, credentials, and exchange details.

```ini
[message-broker]
hostname = localhost
port = 5672
username = guest
password = guest
exchange = amq.topic
topic = deepstream-analytics
amqp-framesize = 131072
```

--------------------------------

### Local Testing

Source: https://github.com/practicalswan/agent-skills/blob/main/microsoft-development/examples/azure-function-api-example.md

Examples of how to test the API endpoints locally using curl after starting the function app.

```APIDOC
## Local Development

### Run Locally

```bash
# Start function app
func start

# Test endpoints
curl http://localhost:7071/api/recipes
curl -X POST http://localhost:7071/api/recipes \
  -H "Content-Type: application/json" \
  -d '{"title":"Test Pasta","description":"Delicious","ingredients":["pasta","sauce"],"instructions":["boil","mix"],"prepTimeMinutes":20}'

# OpenAPI/Swagger UI
# Navigate to http://localhost:7071/api/swagger/ui
```
```

--------------------------------

### Install Tailwind CSS and Initialize

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-shadcn-ui/resources/setup-guide.md

Installs Tailwind CSS and its peer dependencies, then initializes Tailwind CSS with PostCSS and Autoprefixer.

```bash
npm install -D tailwindcss postcss autoprefixer
npx tailwindcss init -p
```

--------------------------------

### Install MQTT Broker and Clients

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/troubleshooting.md

Install the `mosquitto` broker and `mosquitto-clients` packages if you need to run an MQTT broker locally or use CLI testing tools.

```bash
sudo apt-get install -y mosquitto           # broker daemon
sudo apt-get install -y mosquitto-clients   # CLI tools (mosquitto_pub, mosquitto_sub)
```

--------------------------------

### GitHub Actions Workflow for Playwright Tests

Source: https://github.com/practicalswan/agent-skills/blob/main/web-testing/references/test-patterns.md

This workflow automates the checkout, Node.js setup, dependency installation, Playwright installation, test execution, and artifact upload for Playwright tests on every push or pull request.

```yaml
name: Playwright Tests
on: [push, pull_request]

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: 20
      - run: npm ci
      - run: npx playwright install --with-deps
      - run: npx playwright test
      - uses: actions/upload-artifact@v4
        if: ${{ !cancelled() }}
        with:
          name: playwright-report
          path: playwright-report/
          retention-days: 30
```

--------------------------------

### GitHub Actions pip Cache Setup

Source: https://github.com/practicalswan/agent-skills/blob/main/devops-tooling/examples/github-actions-templates.md

Sets up Python and enables pip caching for faster package installation.

```yaml
pip-cache:
    name: pip with built-in cache
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'
          cache: 'pip'
      - run: pip install -r requirements.txt
```

--------------------------------

### Install ffmpeg for Video Preparation

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/docker_containers.md

Installs ffmpeg and related libraries, useful for sample video preparation scripts.

```bash
apt-get install --reinstall libflac8 libmp3lame0 libxvidcore4 ffmpeg
```

--------------------------------

### Configuration File Example

Source: https://github.com/practicalswan/agent-skills/blob/main/documentation-patterns/references/config-templates.md

This template illustrates the structure of a configuration file. It includes a table for detailing options and a sample YAML configuration.

```yaml
optionName: value
```

--------------------------------

### Manual Setup for Next.js Project

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-shadcn-ui/resources/setup-guide.md

Follow these steps to manually set up shadcn/ui in an existing or new Next.js project. This includes initializing the project, initializing shadcn/ui, and adding components.

```bash
npx create-next-app@latest my-app
cd my-app

npx shadcn@latest init

npx shadcn@latest add button
```

--------------------------------

### RabbitMQ Queue and Binding Setup Commands

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/kafka_messaging.md

Commands to enable the RabbitMQ management plugin, declare a queue, and bind it to an exchange.

```bash
sudo rabbitmq-plugins enable rabbitmq_management

sudo rabbitmqadmin -u guest -p guest -V / declare queue name=myqueue durable=false auto_delete=true

rabbitmqadmin -u guest -p guest -V / declare binding source=amq.topic destination=myqueue routing_key=deepstream-analytics
```

--------------------------------

### Front-Loading Key Information Example

Source: https://github.com/practicalswan/agent-skills/blob/main/documentation-authoring/references/writing-style-guide.md

Shows how to place the most important information at the beginning of a sentence to improve comprehension and guide the reader's attention effectively.

```text
To deploy, run `npm run build` first.
```

```text
Before you can deploy your application to the production server, you need to first run `npm run build`.
```

--------------------------------

### Check Pipeline Readiness using curl

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/rest_api_dynamic.md

Example curl command to check the DeepStream pipeline's readiness state using the GET /api/v1/health/get-dsready-state endpoint.

```bash
# Check pipeline readiness
curl -X GET 'http://localhost:9000/api/v1/health/get-dsready-state'
```

--------------------------------

### Continuity: Sequential Steps Example

Source: https://github.com/practicalswan/agent-skills/blob/main/canvas-design/references/design-principles.md

Shows how elements arranged along a line are perceived as more related. A connecting line guides the eye and implies order in sequential steps.

```text
Step 1 ──────── Step 2 ──────── Step 3 ──────── Step 4
  ●                ●                ●                ○

The connecting line guides the eye and implies order.
```

--------------------------------

### Skill Directory Structure Example

Source: https://github.com/practicalswan/agent-skills/blob/main/writing-skills/SKILL.md

Illustrates the standard directory structure for a skill, including the main SKILL.md file and optional supporting files.

```bash
skills/
  skill-name/
    SKILL.md              # Main reference (required)
    supporting-file.*	    # Only if needed
```

--------------------------------

### Document Modification Workflow

Source: https://github.com/practicalswan/agent-skills/blob/main/writing-skills/anthropic-best-practices.md

Guide Claude through decision points for document modification. This example outlines distinct workflows for creating new content versus editing existing content.

```markdown
## Document modification workflow

1. Determine the modification type:

   **Creating new content?** → Follow "Creation workflow" below
   **Editing existing content?** → Follow "Editing workflow" below

2. Creation workflow:
   - Use docx-js library
   - Build document from scratch
   - Export to .docx format

3. Editing workflow:
   - Unpack existing document
   - Modify XML directly
   - Validate after each change
   - Repack when complete
```

--------------------------------

### MQTT Configuration File (cfg_mqtt.txt)

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/kafka_messaging.md

Example configuration for the MQTT protocol adaptor. Customize client ID, TLS settings, and threading options.

```ini
[message-broker]
# Username for broker authentication (deprecated - use env var)
#username = user

# Password for broker authentication (deprecated - use env var)
#password = password

# Unique client ID (empty = random)
client-id = deepstream-client

# TLS Configuration
#enable-tls = 1
#tls-cafile = /path/to/ca-cert.pem
#tls-capath = /path/to/ca-certs-dir/
#tls-certfile = /path/to/client-cert.pem
#tls-keyfile = /path/to/client-key.pem

# Connection sharing
#share-connection = 1

# Mosquitto loop timeout in ms
#loop-timeout = 2000

# Keep-alive interval in seconds
#keep-alive = 60

# Enable threaded mode (required for nvmsgbroker plugin)
#set-threaded = 1
```

--------------------------------

### Azure IoT Configuration File Example

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/kafka_messaging.md

Example configuration for connecting to Azure IoT Hub, including connection string and custom message properties.

```ini
[message-broker]
#connection_str = HostName=<my-hub>.azure-devices.net;DeviceId=<device_id>;SharedAccessKey=<my-policy-key>

#custom_msg_properties = key1=value1;key2=value2;

#share-connection = 1

#cleanup-timeout = 20
```

--------------------------------

### Setup isolated virtual environment for ONNX export

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-import-vision-model/references/model-acquire.md

This script sets up and activates a shared virtual environment for model conversion tools like optimum, transformers, and torch. It ensures that these heavy dependencies are installed once and reused across models, preventing system pollution and saving installation time. The venv is located at build/.venv_optimum.

```bash
mkdir -p build
VENV=build/.venv_optimum
if [ ! -x "$VENV/bin/optimum-cli" ]; then
  python3 -m venv "$VENV"
  source "$VENV/bin/activate"
  pip install --upgrade pip
  pip install optimum[exporters] torch transformers safetensors onnxruntime matplotlib numpy markdown
else
  source "$VENV/bin/activate"
fi
```

--------------------------------

### Setup Python Virtual Environment

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-import-vision-model/SKILL.md

Creates and populates a shared Python virtual environment for model development. Installs necessary packages like optimum, torch, transformers, onnxruntime, and matplotlib.

```bash
mkdir -p build
VENV=build/.venv_optimum
if [ ! -x "$VENV/bin/python3" ]; then
  python3 -m venv "$VENV"
  "$VENV/bin/pip" install --upgrade pip -q
  "$VENV/bin/pip" install "optimum[exporters]>=1.20,<2.0" "torch<2.12" \
    transformers onnxruntime matplotlib numpy markdown -q
fi
```

--------------------------------

### Example Skill Directory Structure

Source: https://github.com/practicalswan/agent-skills/blob/main/writing-skills/anthropic-best-practices.md

Illustrates a recommended directory structure for a skill, separating the main SKILL.md from reference files organized by domain. This structure helps Claude efficiently access information on demand.

```bash
bigquery-skill/
├── SKILL.md (overview, points to reference files)
└── reference/
    ├── finance.md (revenue metrics)
    ├── sales.md (pipeline data)
    └── product.md (usage analytics)
```

--------------------------------

### SmartRecordConfig Example

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/utilities_config.md

Example demonstrating the creation of a SmartRecordConfig object with specific paths and settings for smart recording. This includes setting cache, container format, directory, and mode.

```python
from pyservicemaker import SmartRecordConfig

# Create smart recording configuration
sr_config = SmartRecordConfig(
    proto_lib="/opt/nvidia/deepstream/deepstream/lib/libnvds_kafka_proto.so",
    conn_str="localhost;9092",
    msgconv_config_file="/opt/nvidia/deepstream/deepstream/sources/libs/kafka_protocol_adaptor/cfg_kafka.txt",
    proto_config_file="/opt/nvidia/deepstream/deepstream/sources/libs/kafka_protocol_adaptor/cfg_kafka.txt",
    topic_list="sr-events",
    smart_rec_cache=30,      # 30 seconds cache
    smart_rec_container=0,   # MP4 format
    smart_rec_dir_path="./recordings",
    smart_rec_mode=0         # Record audio and video
)
```

--------------------------------

### Setup Virtual Environment with Pyservicemaker

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/SKILL.md

When a task requires a Python virtual environment for dependencies like model downloads, ensure pyservicemaker and pyyaml are installed within that venv. This prevents ModuleNotFoundError.

```bash
python3 -m venv venv
source venv/bin/activate
pip install /opt/nvidia/deepstream/deepstream/service-maker/python/pyservicemaker*.whl pyyaml
pip install -r requirements.txt  # other dependencies
```

--------------------------------

### Multi-Source Pipeline Configuration (INI)

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/kafka_messaging.md

This INI-style configuration example illustrates how to set up sensor and place entries for multi-source pipelines. Sensor entries map to source IDs, and place entries also map to source IDs.

```ini
# Sensor entries map to source_id in the pipeline
[sensor0]
enable=1
type=Camera
id=STREAM_0
description=Camera 0

[sensor1]
enable=1
type=Camera
id=STREAM_1
description=Camera 1

# Place entries map to source_id
[place0]
enable=1
id=0
type=intersection
name=Location_0

[place1]
enable=1
id=1
type=intersection
name=Location_1

```

--------------------------------

### Install Microsoft Learn Docs MCP

Source: https://github.com/practicalswan/agent-skills/blob/main/microsoft-development/references/microsoft-learn-mcp.md

Use this command to install the Microsoft Learn Docs MCP tool globally.

```bash
npx -y @microsoft/learn-docs-mcp
```

--------------------------------

### PHP Session Management Class

Source: https://github.com/practicalswan/agent-skills/blob/main/php-development/SKILL.md

A utility class for managing PHP sessions, including starting sessions, setting and getting session variables, removing variables, destroying the session, and regenerating the session ID.

```php
<?php
class Session {
    public static function start(): void {
        if (session_status() === PHP_SESSION_NONE) {
            session_start();
        }
    }

    public static function set(string $key, mixed $value): void {
        $_SESSION[$key] = $value;
    }

    public static function get(string $key, mixed $default = null): mixed {
        return $_SESSION[$key] ?? $default;
    }

    public static function remove(string $key): void {
        unset($_SESSION[$key]);
    }

    public static function destroy(): void {
        $_SESSION = [];
        session_destroy();
        if (ini_get("session.use_cookies")) {
            $params = session_get_cookie_params();
            setcookie(session_name(), '', time() - 42000,
                $params["path"], $params["domain"],
                $params["secure"], $params["httponly"]
            );
        }
    }

    public static function regenerateId(): void {
        session_regenerate_id(true);
    }
}

```

--------------------------------

### Example Error Handling in TypeScript

Source: https://github.com/practicalswan/agent-skills/blob/main/mcp-builder/reference/mcp_best_practices.md

Demonstrates how to catch errors during an operation and return a user-friendly error message, suggesting a potential solution. This pattern helps prevent exposing internal error details while guiding the user.

```typescript
try {
  const result = performOperation();
  return { content: [{ type: "text", text: result }] };
} catch (error) {
  return {
    isError: true,
    content: [{
      type: "text",
      text: `Error: ${error.message}. Try using filter='active_only' to reduce results.`
    }]
  };
}
```

--------------------------------

### Install Data Display Components

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-shadcn-ui/resources/component-catalog.md

Use this command to quickly install components for displaying data, including table, badge, avatar, progress, and skeleton.

```bash
npx shadcn@latest add table badge avatar progress skeleton
```

--------------------------------

### Start Development Server

Source: https://github.com/practicalswan/agent-skills/blob/main/nextjs-development/references/nextjs-mcp-server.md

Ensure your Next.js development server is actively running. This command starts the development server using npm.

```bash
npm run dev
```

--------------------------------

### Run Tech Writer Agent

Source: https://github.com/practicalswan/agent-skills/blob/main/agent-task-mapping/references/agent-details.md

Invoke this agent to create formal developer documentation, such as API references, setup guides, and tutorials. Provide the agent name, a task description, and a prompt detailing the documentation requirements.

```javascript
runSubagent({
  agentName: "Tech Writer",
  description: "Create API docs",
  prompt: "Generate professional developer documentation for the recipe management API. Include endpoint descriptions, request/response schemas, authentication requirements, and code examples for the official docs site."
})
```

--------------------------------

### Trunk-Based Development Workflow Example

Source: https://github.com/practicalswan/agent-skills/blob/main/devops-tooling/references/ci-cd-patterns.md

A simple GitHub Actions workflow demonstrating deployment on every push to the main branch, requiring tests to pass first.

```yaml
on:
  push:
    branches: [main]                # Deploy on every push to main

jobs:
  test:
    runs-on: ubuntu-latest
    steps: [...] # Placeholder for test steps

  deploy:
    needs: test
    runs-on: ubuntu-latest
    environment: production
    steps: [...] # Placeholder for deploy steps
```

--------------------------------

### Build and Run Azure Function App Locally

Source: https://github.com/practicalswan/agent-skills/blob/main/microsoft-development/examples/azure-function-api-example.md

Commands to restore dependencies, build the .NET project, and start the Azure Functions host locally. Includes examples for testing API endpoints and accessing Swagger UI.

```bash
# Restore and build
dotnet restore
dotnet build

# Start function app
func start

# Test endpoints
curl http://localhost:7071/api/recipes
curl -X POST http://localhost:7071/api/recipes \
  -H "Content-Type: application/json" \
  -d '{"title":"Test Pasta","description":"Delicious","ingredients":["pasta","sauce"],"instructions":["boil","mix"],"prepTimeMinutes":20}'

# OpenAPI/Swagger UI
# Navigate to http://localhost:7071/api/swagger/ui
```

--------------------------------

### nvmsgbroker Configuration for Dynamic Sources/Tee Splits

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/kafka_messaging.md

When using nvmsgbroker with dynamic sources or tee splits, it is critical to set 'async: 0' for the nvmsgbroker and all other sinks to prevent the pipeline from getting stuck in the PAUSED state. This example shows the correct configuration.

```python
# CORRECT - async=0 for tee/dynamic source pipelines
pipeline.add("nvmsgbroker", "msgbroker", {
    "proto-lib": "/opt/nvidia/deepstream/deepstream/lib/libnvds_kafka_proto.so",
    "conn-str": "localhost;9092",
    "sync": 0,   # Async message sending
    "async": 0,  # CRITICAL: Required for tee/dynamic sources!
})

# WRONG - missing async=0 causes pipeline stuck in PAUSED
pipeline.add("nvmsgbroker", "msgbroker", {
    "proto-lib": "/opt/nvidia/deepstream/deepstream/lib/libnvds_kafka_proto.so",
    "conn-str": "localhost;9092",
    "sync": 0,
    # async defaults to 1, causing state transition deadlock!
})
```

--------------------------------

### Initialize shadcn/ui

Source: https://github.com/practicalswan/agent-skills/blob/main/stitch-shadcn-ui/SKILL.md

Use this command to initialize shadcn/ui in your project. Ensure you have a `components.json` file, Tailwind CSS configuration, and path aliases set up.

```bash
npx shadcn@latest init
```

--------------------------------

### Install Azure IoT SDK Dependencies

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-dev/references/kafka_messaging.md

Installs necessary libraries and builds the Azure IoT SDK for C.

```bash
sudo apt-get update
sudo apt-get install -y libcurl4-openssl-dev libssl-dev uuid-dev libglib2.0-dev

git clone https://github.com/Azure/azure-iot-sdk-c.git
cd azure-iot-sdk-c
git checkout tags/1.11.0
git submodule update --init

# Modify CMakeLists.txt:
# - Line 61: set build_as_dynamic to ON
# - Line 65: set use_edge_modules to ON

mkdir cmake && cd cmake
cmake ..
cmake --build .
sudo make install
```

--------------------------------

### Auto-Detect RAG Library Mode

Source: https://github.com/practicalswan/agent-skills/blob/main/rag-blueprint/references/deploy/library.md

Automatically detects the operational mode (full or lite) by checking for Docker, GPU, Python, package manager availability, existing virtual environments, and the installation status of the 'nvidia_rag' package. Use this to determine the appropriate setup.

```bash
echo "=== DOCKER ===" && docker --version 2>/dev/null || echo "NO_DOCKER"; echo "=== GPU ===" && nvidia-smi --query-gpu=name --format=csv,noheader 2>/dev/null || echo "NO_GPU"; echo "=== PYTHON ===" && python3 --version 2>/dev/null || echo "NO_PYTHON"; echo "=== PKG_MANAGER ===" && which uv 2>/dev/null && echo "UV_AVAILABLE" || (which pip3 2>/dev/null && echo "PIP_AVAILABLE" || echo "NO_PKG_MANAGER"); echo "=== VENV ===" && ls -d .venv/ venv/ nvidia-rag-env/ 2>/dev/null || echo "NO_EXISTING_VENV"; echo "=== INSTALLED ===" && pip3 show nvidia_rag 2>/dev/null | head -3 || echo "NOT_INSTALLED"
```

--------------------------------

### Install System Tools

Source: https://github.com/practicalswan/agent-skills/blob/main/deepstream-import-vision-model/SKILL.md

Installs required system utilities like wkhtmltopdf and mediainfo if they are not already present. Also checks for the presence of deepstream-app.

```bash
which wkhtmltopdf || apt-get install -y wkhtmltopdf
```

```bash
which mediainfo    || apt-get install -y mediainfo
```

```bash
which deepstream-app  # required for KITTI dump (Step 6g) and benchmark perf-measurement (Step 7c); shipped with DeepStream SDK
```

--------------------------------

### CI Quality Gate Workflow

Source: https://github.com/practicalswan/agent-skills/blob/main/code-quality/SKILL.md

An example GitHub Actions workflow for a CI quality gate. It checks out code, sets up Node.js, installs dependencies, runs linting, checks formatting, runs tests with coverage, and performs a SonarQube scan. This gate fails fast on issues before code review.

```yaml
jobs:
  quality:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: 22
      - run: npm ci
      - run: npm run lint
      - run: npm run format:check
      - run: npm test -- --coverage
      - run: sonar-scanner
```