### Mem0 Integration Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/memory-systems/SKILL.md

Demonstrates adding user preferences to Mem0 and searching for the current preference. Ensure Mem0 is installed and initialized.

```python
from mem0 import Memory

m = Memory()
m.add("User prefers dark mode and Python 3.12", user_id="alice")
m.add("User switched to light mode", user_id="alice")

# Retrieves current preference (light mode), not outdated one
results = m.search("What theme does the user prefer?", user_id="alice")
```

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

### Manual Environment Setup

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/notebooklm/SKILL.md

Use these commands if automatic environment setup fails. This includes creating a virtual environment, activating it, installing dependencies, and installing the Chromium browser.

```bash
python -m venv .venv
source .venv/bin/activate  # Linux/Mac
pip install -r requirements.txt
python -m patchright install chromium
```

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

### One-Time Agent and Environment Setup using SDK

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/shared/managed-agents-onboarding.md

If the 'ant' CLI is unavailable or in-language setup is preferred, use these SDK calls to create agents and environments. Ensure these are run only once and the resulting IDs are stored, for example, in a .env file.

```python
# ONE-TIME SETUP — run once, save the IDs to config/.env
# environments.create()
# agents.create()
```

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

### Setup Authentication

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/notebooklm/references/usage_patterns.md

Initiate the authentication setup process using run.py with auth_manager.py and 'setup'. Note that this operation may open a browser window.

```bash
run.py auth_manager.py setup
```

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

### Run Express Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/express/Readme.md

Execute a specific example from the cloned Express repository. Replace 'content-negotiation' with the desired example name.

```console
$ node examples/content-negotiation
```

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

### Quick Start with Claude Agent SDK

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/python/agent-sdk/README.md

A basic example demonstrating how to use the `query` function to interact with an agent. It specifies allowed tools and prints the agent's results.

```python
import anyio
from claude_agent_sdk import query, ClaudeAgentOptions, ResultMessage

async def main():
    async for message in query(
        prompt="Explain this codebase",
        options=ClaudeAgentOptions(allowed_tools=["Read", "Glob", "Grep"])
    ):
        if isinstance(message, ResultMessage):
            print(message.result)

anyio.run(main)
```

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

### Start Visual Companion Server with Custom Host

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/visual-companion.md

Binds the server to a non-loopback host (0.0.0.0) and specifies the hostname for the returned URL. Useful for remote or containerized setups where the default localhost URL might be unreachable.

```bash
scripts/start-server.sh \
  --project-dir /path/to/project \
  --host 0.0.0.0 \
  --url-host localhost
```

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

### Setup Authentication with Timeout

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/notebooklm/references/troubleshooting.md

Performs a fresh authentication setup with a specified timeout. This can help if the default setup process times out.

```bash
python scripts/run.py auth_manager.py setup --timeout 15
```

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

### Install serve-static

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/serve-static/README.md

Install the serve-static module using npm.

```sh
$ npm install serve-static
```

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

### Initial Setup: Authentication and Notebook Addition

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/notebooklm/references/usage_patterns.md

Steps for initial setup, including checking authentication, performing setup if needed (requires visible browser), and adding the first notebook with user-provided details.

```bash
# 1. Check authentication (using run.py!)
python scripts/run.py auth_manager.py status
```

```bash
# 2. If not authenticated, setup (Browser MUST be visible!)
python scripts/run.py auth_manager.py setup
# Tell user: "Please log in to Google in the browser window"
```

```bash
# 3. Add first notebook - ASK USER FOR DETAILS FIRST!
# Ask: "What does this notebook contain?"
# Ask: "What topics should I tag it with?"
python scripts/run.py notebook_manager.py add \
  --url "https://notebooklm.google.com/notebook/..." \
  --name "User provided name" \
  --description "User provided description" \
  --topics "user,provided,topics"
```

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

### Install NotebookLM Claude Code Skill

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/notebooklm/README.md

Clone the NotebookLM skill repository into your Claude skills directory to get started. After installation, you can access your skills by asking Claude: "What are my skills?"

```bash
cd ~/.claude/skills
git clone https://github.com/PleasePrompto/notebooklm-skill notebooklm
# Open Claude Code: "What are my skills?"
```

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

### First-Time Setup - Media Handling Question

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-danger-x-to-markdown/SKILL.md

Asks the user how to handle images and videos during the first-time setup for the X to Markdown skill.

```text
Question 1 -- header: "Media", question: "How to handle images and videos in tweets?"
- "Ask each time (Recommended)" — After saving markdown, ask whether to download media
- "Always download" — Always download media to local imgs/ and videos/ directories
- "Never download" — Keep original remote URLs in markdown
```

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

### Message Request with System Prompt

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/typescript/claude-api/README.md

Send a message request with a system prompt to guide the AI's behavior. This example instructs the AI to provide Python examples.

```typescript
const response = await client.messages.create({
  model: "claude-opus-4-8",
  max_tokens: 16000,
  system:
    "You are a helpful coding assistant. Always provide examples in Python.",
  messages: [{ role: "user", content: "How do I read a JSON file?" }],
});
```

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

### First-Time Setup - Output Directory Question

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-danger-x-to-markdown/SKILL.md

Asks the user for the default output directory during the first-time setup for the X to Markdown skill.

```text
Question 2 -- header: "Output", question: "Default output directory?"
- "x-to-markdown (Recommended)" — Save to ./x-to-markdown/{username}/{tweet-id}.md
- (User may choose "Other" to type a custom path)
```

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

### Claude API with System Prompt

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/python/claude-api/README.md

Utilize a system prompt to guide the Claude API's behavior. This example sets the assistant to be a helpful coding assistant that provides Python examples.

```python
response = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=16000,
    system="You are a helpful coding assistant. Always provide examples in Python.",
    messages=[{"role": "user", "content": "How do I read a JSON file?"}]
)
```

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

### Full Preferences Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-infographic/references/config/preferences-schema.md

An example demonstrating all configurable preferences, including custom styles with specific prompt fragments.

```yaml
---
version: 1

preferred_layout: dense-modules
preferred_style: morandi-journal
preferred_aspect: portrait

language: zh

preferred_image_backend: codex-imagegen

custom_styles:
  - name: my-brand
    description: "Brand-aligned warm pastel infographic"
    prompt_fragment: "Use brand pastel palette (#F2C7B6, #B6D7E8, #C8E0B4); rounded rectangles; warm hand-drawn outlines; ample whitespace."
---

```

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

### Server Startup Response Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/visual-companion.md

Example JSON response from the server indicating a successful startup. Save the screen_dir and state_dir values for later use.

```json
# Returns: {"type":"server-started","port":52341,
#           "url":"http://localhost:52341/?key=ab12…",
#           "screen_dir":"/path/to/project/.superpowers/brainstorm/12345-1706000000/content",
#           "state_dir":"/path/to/project/.superpowers/brainstorm/12345-1706000000/state"}
```

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

### Usage Example: Accessing Array.prototype.slice

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/call-bound/README.md

Demonstrates how to use callBound to get a reference to Array.prototype.slice. This is useful when native methods might be deleted or overridden. The example then uses this bound slice function to extract a sub-array.

```js
const assert = require('assert');
const callBound = require('call-bound');

const slice = callBound('Array.prototype.slice');

delete Function.prototype.call;
delete Function.prototype.bind;
delete Array.prototype.slice;

assert.deepEqual(slice([1, 2, 3, 4], 1, -1), [2, 3]);
```

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

### Full Setup Questions

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-imagine/references/config/first-time-setup.md

Use AskUserQuestion with all questions in a single call for the full setup process when no EXTEND.md is found.

```yaml
header: "Provider"
question: "Default image generation provider?"
options:
  - label: "Google (Recommended)"
    description: "Gemini multimodal - high quality, reference images, flexible sizes"
  - label: "OpenAI"
    description: "GPT Image 2 - latest OpenAI image model, reference-image workflows"
  - label: "Azure OpenAI"
    description: "Azure-hosted GPT Image deployments with resource-specific routing"
  - label: "OpenRouter"
    description: "Router for Gemini/FLUX/OpenAI-compatible image models"
  - label: "DashScope"
    description: "Alibaba Cloud - Qwen-Image, strong Chinese/English text rendering"
  - label: "Z.AI"
    description: "GLM-image, strong poster and text-heavy image generation"
  - label: "MiniMax"
    description: "MiniMax image generation with subject-reference character workflows"
  - label: "Replicate"
    description: "Curated Replicate image families - nano-banana-2, Seedream, and Wan image models"
```

```yaml
header: "Google Model"
question: "Default Google image generation model?"
options:
  - label: "gemini-3-pro-image-preview (Recommended)"
    description: "Highest quality, best for production use"
  - label: "gemini-3.1-flash-image-preview"
    description: "Fast generation, good quality, lower cost"
  - label: "gemini-3-flash-preview"
    description: "Fast generation, balanced quality and speed"
```

```yaml
header: "OpenRouter Model"
question: "Default OpenRouter image generation model?"
options:
  - label: "google/gemini-3.1-flash-image-preview (Recommended)"
    description: "Best general-purpose OpenRouter image model with reference-image workflows"
  - label: "google/gemini-2.5-flash-image-preview"
    description: "Fast Gemini preview model on OpenRouter"
  - label: "black-forest-labs/flux.2-pro"
    description: "Strong text-to-image quality through OpenRouter"
```

```yaml
header: "Azure Deploy"
question: "Default Azure image deployment name?"
options:
  - label: "gpt-image-2 (Recommended)"
    description: "Use if your Azure deployment uses the GPT Image 2 model name"
  - label: "gpt-image-1.5"
    description: "Previous GPT Image deployment name"
  - label: "gpt-image-1"
    description: "Earlier GPT Image deployment name"
```

```yaml
header: "MiniMax Model"
question: "Default MiniMax image generation model?"
options:
  - label: "image-01 (Recommended)"
    description: "Best default, supports aspect ratios and custom width/height"
  - label: "image-01-live"
    description: "Faster variant, use aspect ratio instead of custom size"
```

```yaml
header: "Z.AI Model"
question: "Default Z.AI image generation model?"
options:
  - label: "glm-image (Recommended)"
    description: "Best default for posters, diagrams, and text-heavy images"
  - label: "cogview-4-250304"
    description: "Legacy Z.AI image model on the same endpoint"
```

```yaml
header: "Quality"
question: "Default image quality?"
options:
  - label: "2k (Recommended)"
    description: "2048px - covers, illustrations, infographics"
  - label: "normal"
    description: "1024px - quick previews, drafts"
```

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

### Express Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/raw-body/README.md

Integrates raw-body into an Express application to access the raw request body. Ensure 'content-type' and 'raw-body' are installed.

```javascript
var contentType = require('content-type')
var express = require('express')
var getRawBody = require('raw-body')

var app = express()

app.use(function (req, res, next) {
  getRawBody(req, {
    length: req.headers['content-length'],
    limit: '1mb',
    encoding: contentType.parse(req).parameters.charset
  }, function (err, string) {
    if (err) return next(err)
    req.text = string
    next()
  })
})

// now access req.text
```

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

### Full Preferences Configuration Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-image-gen/references/config/preferences-schema.md

This example demonstrates a comprehensive configuration including all default settings for providers, quality, aspect ratio, image size, API dialect, specific models for various providers, and detailed batch processing limits.

```yaml
---
version: 1
default_provider: google
default_quality: 2k
default_aspect_ratio: "16:9"
default_image_size: 2K
default_image_api_dialect: null
default_model:
  google: "gemini-3-pro-image"
  openai: "gpt-image-2"
  azure: "gpt-image-2"
  openrouter: "google/gemini-3.1-flash-image"
  dashscope: "qwen-image-2.0-pro"
  zai: "glm-image"
  minimax: "image-01"
  replicate: "google/nano-banana-2"
  agnes: "agnes-image-2.1-flash"
batch:
  max_workers: 10
  provider_limits:
    replicate:
      concurrency: 5
      start_interval_ms: 700
    azure:
      concurrency: 3
      start_interval_ms: 1100
    zai:
      concurrency: 3
      start_interval_ms: 1100
    openrouter:
      concurrency: 3
      start_interval_ms: 1100
    minimax:
      concurrency: 3
      start_interval_ms: 1100
    agnes:
      concurrency: 3
      start_interval_ms: 1100
---

```

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

### Start Visual Companion Server

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/visual-companion.md

Initiates the visual companion server. Use --project-dir to persist mockups and enable same-port restarts. The --open flag automatically opens the user's browser on the first screen.

```bash
scripts/start-server.sh --project-dir /path/to/project --open
```

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

### Clone Express Repository

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/express/Readme.md

Clone the Express repository to access and run examples. This command fetches the repository and installs necessary dependencies.

```console
$ git clone https://github.com/expressjs/express.git --depth 1
$ cd express
$ npm install
```

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

### Setup and Basic Document Creation

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/docx/SKILL.md

Import necessary components from the 'docx' library and create a basic document. The document is then packed into a buffer and saved to a file.

```javascript
const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun,
        Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink,
        InternalHyperlink, Bookmark, FootnoteReferenceRun, PositionalTab,
        PositionalTabAlignment, PositionalTabRelativeTo, PositionalTabLeader,
        TabStopType, TabStopPosition, Column, SectionType,
        TableOfContents, HeadingLevel, BorderStyle, WidthType, ShadingType,
        VerticalAlign, PageNumber, PageBreak } = require('docx');

const doc = new Document({ sections: [{ children: [/* content */] }] });
Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer));
```

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

### Style Reference Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-article-illustrator/references/workflow.md

For style references, analyze the image and append style traits to the prompt. This guides the generation towards a specific aesthetic.

```bash
"Style: clean lines, gradient backgrounds..."
```

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

### Install and Build Documentation

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/fill-range/README.md

Install global documentation generation tools and build the README file.

```sh
$ npm install -g verbose/verb#dev verb-generate-readme && verb
```

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

### Guided Setup Prompt for WeChat API Credentials

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-post-to-wechat/references/api-setup.md

Display this message to the user to guide them through obtaining WeChat API credentials and choosing a save location. It instructs users to visit the WeChat MP website and provides options for project-level or user-level credential storage.

```text
WeChat API credentials not found.

To obtain credentials:
1. Visit https://mp.weixin.qq.com
2. Go to: 开发 → 基本配置
3. Copy AppID and AppSecret

Where to save?
A) Project-level: .baoyu-skills/.env (this project only)
B) User-level: ~/.baoyu-skills/.env (all projects)
```

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

### Usage Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/side-channel-weakmap/README.md

Demonstrates how to use the side-channel-weakmap to set, get, assert, and delete keys. It also shows how to handle errors when asserting a non-existent key.

```js
const assert = require('assert');
const getSideChannelList = require('side-channel-weakmap');

const channel = getSideChannelList();

const key = {};
assert.equal(channel.has(key), false);
assert.throws(() => channel.assert(key), TypeError);

channel.set(key, 42);

channel.assert(key); // does not throw
assert.equal(channel.has(key), true);
assert.equal(channel.get(key), 42);

channel.delete(key);
assert.equal(channel.has(key), false);
assert.throws(() => channel.assert(key), TypeError);
```

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

### Full Preferences Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-article-illustrator/references/config/preferences-schema.md

A comprehensive example demonstrating a full preferences configuration, including watermark details, preferred image backend, generation batch size, and a custom style definition.

```yaml
---
version: 1
watermark:
  enabled: true
  content: "@myaccount"
  position: bottom-right

preferred_style:
  name: notion
  description: "Clean illustrations for tech articles"

language: zh

preferred_image_backend: codex-imagegen

generation_batch_size: 4

custom_styles:
  - name: corporate
    description: "Professional B2B style"
    color_palette:
      primary: ["#1E3A5F", "#4A90D9"]
      background: "#F5F7FA"
      accents: ["#00B4D8", "#48CAE4"]
    visual_elements: "Clean lines, subtle gradients, geometric shapes"
    typography: "Modern sans-serif, professional"
    best_for: "Business, SaaS, enterprise"
---

```

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

### Correct Parallelization with better-all

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/react-best-practices/rules/async-dependencies.md

Use better-all to automatically maximize parallelism for operations with partial dependencies. It starts each task as early as possible. Ensure you have 'better-all' installed.

```typescript
import { all } from 'better-all'

const { user, config, profile } = await all({
  async user() { return fetchUser() },
  async config() { return fetchConfig() },
  async profile() {
    return fetchProfile((await this.$.user).id)
  }
})
```

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

### Full Preferences Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-image-cards/references/config/preferences-schema.md

A comprehensive example showcasing all configurable preferences, including custom styles, layout, language, and image backend.

```yaml
---
version: 1
watermark:
  enabled: true
  content: "@myxhsaccount"
  position: bottom-right

preferred_style:
  name: notion
  description: "Clean knowledge cards for tech content"

preferred_layout: dense

language: zh

preferred_image_backend: codex-imagegen

generation_batch_size: 4

custom_styles:
  - name: corporate
    description: "Professional B2B style"
    color_palette:
      primary: ["#1E3A5F", "#4A90D9"]
      background: "#F5F7FA"
      accents: ["#00B4D8", "#48CAE4"]
    visual_elements: "Clean lines, subtle gradients, geometric shapes"
    typography: "Modern sans-serif, professional"
    best_for: "Business, SaaS, enterprise"
---

```

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

### Usage Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/side-channel-list/README.md

Demonstrates how to use the side-channel-list to set, get, assert, and delete data associated with a key. It also shows the behavior of `has` and `assert` methods before and after deletion.

```js
const assert = require('assert');
const getSideChannelList = require('side-channel-list');

const channel = getSideChannelList();

const key = {};
assert.equal(channel.has(key), false);
assert.throws(() => channel.assert(key), TypeError);

channel.set(key, 42);

channel.assert(key); // does not throw
assert.equal(channel.has(key), true);
assert.equal(channel.get(key), 42);

channel.delete(key);
assert.equal(channel.has(key), false);
assert.throws(() => channel.assert(key), TypeError);
```

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

### Build Documentation

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/picomatch/README.md

Install global dependencies for documentation generation and then run the build command. Note that the README is generated and should not be edited directly.

```sh
npm install -g verbose/verb#dev verb-generate-readme && verb
```

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

### Basic Presentation Setup

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/pptx/pptxgenjs.md

Initializes a new presentation, sets layout and metadata, adds a slide with text, and saves the presentation to a file.

```javascript
const pptxgen = require("pptxgenjs");

let pres = new pptxgen();
pres.layout = 'LAYOUT_16x9';  // or 'LAYOUT_16x10', 'LAYOUT_4x3', 'LAYOUT_WIDE'
pres.author = 'Your Name';
pres.title = 'Presentation Title';

let slide = pres.addSlide();
slide.addText("Hello World!", { x: 0.5, y: 0.5, fontSize: 36, color: "363636" });

pres.writeFile({ fileName: "Presentation.pptx" });
```

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

### Getting Nodes by Exact Line Number

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/docx/ooxml.md

Locate a node at a precise line number where its tag opens. Ensure the line number corresponds to the tag's start.

```python
# By exact line number (must be line number where tag opens)
para = doc["word/document.xml"].get_node(tag="w:p", line_number=42)
```

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

### First-Time Setup - Preferences Save Location Question

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-danger-x-to-markdown/SKILL.md

Asks the user where to save their preferences during the first-time setup for the X to Markdown skill.

```text
Question 3 -- header: "Save", question: "Where to save preferences?"
- "User (Recommended)" — ~/.baoyu-skills/ (all projects)
- "Project" — .baoyu-skills/ (this project only)
```

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

### Get Client IP Address (Behind Proxy)

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/ws/README.md

When a WebSocket server is behind a proxy, this example shows how to obtain the client's IP address from the `X-Forwarded-For` header.

```javascript
wss.on('connection', function connection(ws, req) {
  const ip = req.headers['x-forwarded-for'].split(',')[0].trim();

  ws.on('error', console.error);
});
```

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

### Usage Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/side-channel-map/README.md

Demonstrates how to use the side-channel-map to set, get, assert, and delete values associated with keys. It also shows how to handle errors when asserting a key that has not been set.

```js
const assert = require('assert');
const getSideChannelMap = require('side-channel-map');

const channel = getSideChannelMap();

const key = {};
assert.equal(channel.has(key), false);
assert.throws(() => channel.assert(key), TypeError);

channel.set(key, 42);

channel.assert(key); // does not throw
assert.equal(channel.has(key), true);
assert.equal(channel.get(key), 42);

channel.delete(key);
assert.equal(channel.has(key), false);
assert.throws(() => channel.assert(key), TypeError);
```

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

### Conditional Workflow Logic

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/skill-creator/references/workflows.md

Guide Claude through decision points for tasks with branching logic. This example shows how to determine the next steps based on content modification type.

```markdown
1. Determine the modification type:
   **Creating new content?** → Follow "Creation workflow" below
   **Editing existing content?** → Follow "Editing workflow" below

2. Creation workflow: [steps]
3. Editing workflow: [steps]
```

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

### Install @remotion/media-utils

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/remotion/rules/audio-visualization.md

Install the necessary package for audio visualization functionalities.

```bash
npx remotion add @remotion/media-utils
```

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

### Create and Start a Minimal Agent Session

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/go/managed-agents/README.md

This snippet demonstrates the essential steps to create a new agent with basic configurations (name, model, system prompt, tools) and then start a new session with that agent. It requires the `anthropic` Go SDK and an initialized Anthropic client.

```go
// 1. Create the agent (reusable, versioned)
agent, err := client.Beta.Agents.New(ctx, anthropic.BetaAgentNewParams{
    Name: "Coding Assistant",
    Model: anthropic.BetaManagedAgentsModelConfigParams{
        ID:   "claude-opus-4-8",
        Type: anthropic.BetaManagedAgentsModelConfigParamsTypeModelConfig,
    },
    System: anthropic.String("You are a helpful coding assistant."),
    Tools: []anthropic.BetaAgentNewParamsToolUnion{{
        OfAgentToolset20260401: &anthropic.BetaManagedAgentsAgentToolset20260401Params{
            Type: anthropic.BetaManagedAgentsAgentToolset20260401ParamsTypeAgentToolset20260401,
        },
    }},
})
if err != nil {
    panic(err)
}

// 2. Start a session
session, err := client.Beta.Sessions.New(ctx, anthropic.BetaSessionNewParams{
    Agent: anthropic.BetaSessionNewParamsAgentUnion{
        OfBetaManagedAgentsAgents: &anthropic.BetaManagedAgentsAgentParams{
            Type:    anthropic.BetaManagedAgentsAgentParamsTypeAgent,
            ID:      agent.ID,
            Version: anthropic.Int(agent.Version),
        },
    },
    EnvironmentID: environment.ID,
    Title:         anthropic.String("Quickstart session"),
})
if err != nil {
    panic(err)
}
fmt.Printf("Session ID: %s, status: %s\n", session.ID, session.Status)

```

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

### Token Management for GitHub Operations

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/hosted-agents/references/infrastructure-patterns.md

Manages tokens for GitHub operations, including getting short-lived installation tokens for repository access and user OAuth tokens for PR creation.

```python
class TokenManager:
    """Manage tokens for GitHub operations."""
    
    def get_app_installation_token(self, repo: str) -> str:
        """Get short-lived token for repo access."""
        # Token expires in 1 hour
        return github_app.create_installation_token(
            installation_id=self.get_installation_id(repo),
            permissions={"contents": "write", "pull_requests": "write"}
        )
    
    def get_user_token(self, user_id: str) -> str:
        """Get user's OAuth token for PR creation."""
        # Stored encrypted, decrypted at runtime
        encrypted = self.storage.get(f"user_token:{user_id}")
        return self.decrypt(encrypted)
```

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

### Run.py Script Wrapper Usage

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/notebooklm/references/api_reference.md

The `run.py` script acts as a wrapper for executing other skill scripts, handling environment setup automatically. It creates a virtual environment if needed and installs dependencies.

```bash
python scripts/run.py [script_name].py [arguments]
```

```bash
python scripts/run.py auth_manager.py status
```

```bash
python scripts/run.py ask_question.py --question "..."
```

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

### Start Remotion Studio Preview

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/remotion/SKILL.md

Use this command to launch the Remotion Studio, which provides a live preview of your video compositions. This is useful for iterative development and immediate feedback.

```bash
npx remotion studio
```

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

### Basic FFmpeg and FFprobe Commands

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/remotion/rules/ffmpeg.md

Use these commands to perform basic video and audio processing or to get media information. FFmpeg and FFprobe are bundled with Remotion, so no separate installation is needed.

```bash
npx remotion ffmpeg -i input.mp4 output.mp3
npx remotion ffprobe input.mp4
```

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

### Markdown to HTML Conversion Script Usage

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-post-to-x/references/articles.md

Examples of using the 'md-to-html.ts' script to convert Markdown files. Shows how to get JSON metadata, output only HTML, and save HTML to a file.

```bash
# Get JSON with all metadata
${BUN_X} {baseDir}/scripts/md-to-html.ts article.md

# Output HTML only
${BUN_X} {baseDir}/scripts/md-to-html.ts article.md --html-only

# Save HTML to file
${BUN_X} {baseDir}/scripts/md-to-html.ts article.md --save-html /tmp/article.html
```

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

### Create Environment

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/go/managed-agents/README.md

Create a new managed environment for agent deployment. This example demonstrates setting up unrestricted networking for the environment.

```go
environment, err := client.Beta.Environments.New(ctx, anthropic.BetaEnvironmentNewParams{
    Name: "my-dev-env",
    Config: anthropic.BetaCloudConfigParams{
        Networking: anthropic.BetaCloudConfigParamsNetworkingUnion{
            OfUnrestricted: &anthropic.UnrestrictedNetworkParam{},
        },
    },
})
if err != nil {
    panic(err)
}
fmt.Println(environment.ID) // env_...
```

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

### Install @remotion/layout-utils

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/remotion/rules/measuring-text.md

Install the necessary utility library for text measurement and layout operations.

```bash
npx remotion add @remotion/layout-utils
```

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

### Generic JSON and URL-encoded Parsers (Top-Level Middleware)

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/body-parser/README.md

This example shows how to add generic JSON and URL-encoded parsers as top-level middleware to parse all incoming request bodies. This is the simplest setup for Express/Connect.

```javascript
var express = require('express')
var bodyParser = require('body-parser')

var app = express()

// parse application/x-www-form-urlencoded
app.use(bodyParser.urlencoded({ extended: false }))

// parse application/json
app.use(bodyParser.json())

app.use(function (req, res) {
  res.setHeader('Content-Type', 'text/plain')
  res.write('you posted:\n')
  res.end(JSON.stringify(req.body, null, 2))
})
```

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

### Optimal Altitude System Prompt Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/context-fundamentals/references/context-components.md

Provides clear, heuristic-driven steps for pricing inquiries, balancing specificity with flexibility. It guides data retrieval, location adjustments, and formatting while preferring exact figures.

```plaintext
For pricing inquiries:
1. Retrieve current rates from docs/pricing.md
2. Apply user location adjustments (see config/location_defaults.json)
3. Format with appropriate currency and tax considerations

Prefer exact figures over estimates. When rates are unavailable,
say so explicitly rather than projecting.
```

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

### Install Dev Dependencies and Run Benchmark

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/braces/README.md

Installs development dependencies and then runs the benchmark script. Use this to compare performance.

```bash
npm i -d && npm benchmark
```

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

### Custom System Prompt for Agent Behavior

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/typescript/agent-sdk/patterns.md

Configures a custom system prompt to guide the agent's behavior and focus. This example sets a system prompt for a senior code reviewer, emphasizing security, performance, and maintainability.

```typescript
import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({
  prompt: "Review this code",
  options: {
    allowedTools: ["Read", "Glob", "Grep"],
    systemPrompt: `You are a senior code reviewer focused on:
1. Security vulnerabilities
2. Performance issues
3. Code maintainability

Always provide specific line numbers and suggestions for improvement.`,
  },
})) {
  if ("result" in message) console.log(message.result);
}

```

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

### Tutorial with Density

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-article-illustrator/references/usage.md

Generates a tutorial illustration with rich density.

```bash
/baoyu-article-illustrator how-to-deploy.md --preset tutorial --density rich
```

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

### Create an Agent with System Prompt and Custom Tools, then Start a Session with a Mounted Repository

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/curl/managed-agents.md

Creates an agent with a system prompt and a custom tool, then initiates a session with a GitHub repository mounted. This allows the agent to interact with specific codebases.

```bash
# 1. Create the agent
curl -X POST https://api.anthropic.com/v1/agents \
  "${HEADERS[@]}" \
  -d '{
    "name": "Code Reviewer",
    "model": "claude-opus-4-8",
    "system": "You are a senior code reviewer. Be thorough and constructive.",
    "tools": [
      { "type": "agent_toolset_20260401" },
      {
        "type": "custom",
        "name": "run_linter",
        "description": "Run the project linter on a file",
        "input_schema": {
          "type": "object",
          "properties": {
            "file_path": { "type": "string", "description": "Path to lint" }
          },
          "required": ["file_path"]
        }
      }
    ]
  }'

# 2. Start a session with the repo mounted
curl -X POST https://api.anthropic.com/v1/sessions \
  "${HEADERS[@]}" \
  -d '{
    "agent": { "type": "agent", "id": "agent_abc123", "version": "1772585501101368014" },
    "environment_id": "env_abc123",
    "title": "Code review session",
    "resources": [
      {
        "type": "github_repository",
        "url": "https://github.com/owner/repo",
        "mount_path": "/workspace/repo",
        "authorization_token": "ghp_...",
        "branch": "feature-branch"
      }
    ]'
  }'
```

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

### Organizing System Prompts

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/context-fundamentals/SKILL.md

This example demonstrates how to structure system prompts by placing critical information at the beginning and end, using explicit section boundaries for better model parsing. It's useful for guiding AI behavior in complex tasks.

```markdown
<BACKGROUND_INFORMATION>
You are a Python expert helping a development team.
Current project: Data processing pipeline in Python 3.9+
</BACKGROUND_INFORMATION>

<INSTRUCTIONS>
- Write clean, idiomatic Python code
- Include type hints for function signatures
- Add docstrings for public functions
- Follow PEP 8 style guidelines
</INSTRUCTIONS>

<OUTPUT_DESCRIPTION>
Provide code blocks with syntax highlighting.
Explain non-obvious decisions in comments.
</OUTPUT_DESCRIPTION>
```

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

### Server Object Methods and Settings

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/brainstorming/scripts/node_modules/express/History.md

Shows how to export the Server constructor and use methods like `helpers()` and `dynamicHelpers()` for view locals, and how to configure settings like `home`.

```javascript
exporting `Server` constructor
Server#helpers()
Server#dynamicHelpers()
_home_ setting defaults to `Server#route` for mounted apps.
```

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

### Custom System Prompt for Code Review (Python)

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/python/agent-sdk/patterns.md

Configure the agent with a custom system prompt to guide its behavior, such as focusing on specific aspects of code review. This example uses `query` with `ClaudeAgentOptions` to specify allowed tools and a detailed system prompt.

```python
import anyio
from claude_agent_sdk import query, ClaudeAgentOptions, ResultMessage

async def main():
    async for message in query(
        prompt="Review this code",
        options=ClaudeAgentOptions(
            allowed_tools=["Read", "Glob", "Grep"],
            system_prompt="""You are a senior code reviewer focused on:
1. Security vulnerabilities
2. Performance issues
3. Code maintainability

Always provide specific line numbers and suggestions for improvement."""
        )
    ):
        if isinstance(message, ResultMessage):
            print(message.result)

anyio.run(main)
```

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

### Check Python Installation

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/ui-ux-pro-max/SKILL.md

Verify if Python is installed on the system. Use this command before attempting to install Python.

```bash
python3 --version || python --version
```

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

### Quick Mode Output Example

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/baoyu-cover-image/references/workflow/confirm-options.md

Illustrates the output format when the workflow skips the first six dimensions and proceeds to ask about the aspect ratio.

```text
Quick Mode: Auto-selected dimensions
• Type: [type] ([reason])
• Palette: [palette] ([reason])
• Rendering: [rendering] ([reason])
• Text: [text] ([reason])
• Mood: [mood] ([reason])
• Font: [font] ([reason])

[Then ask Question 7: Aspect Ratio]
```

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

### Create a Minimal Agent and Start a Session

Source: https://github.com/guanyang/open-agent-hub/blob/main/skills/claude-api/curl/managed-agents.md

First, creates a basic agent with a name, model, and toolset. Then, starts a session using the created agent and a specified environment.

```bash
# 1. Create the agent
curl -X POST https://api.anthropic.com/v1/agents \
  "${HEADERS[@]}" \
  -d '{
    "name": "Coding Assistant",
    "model": "claude-opus-4-8",
    "tools": [{ "type": "agent_toolset_20260401" }]
  }'
# → { "id": "agent_abc123", ... }

# 2. Start a session
curl -X POST https://api.anthropic.com/v1/sessions \
  "${HEADERS[@]}" \
  -d '{
    "agent": { "type": "agent", "id": "agent_abc123", "version": "1772585501101368014" },
    "environment_id": "env_abc123"
  }'
```