### Execute Setup Commands

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/template.md

Run these commands once after cloning to install dependencies and apply configurations.

```bash
<commands>
```

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

### CLI Tool Setup and Verification

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/cli.md

Install the tool in editable mode and verify the installation using the version flag.

```bash
pip install -e .
```

```bash
mytool --version
# → mytool 0.3.1
```

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

### Setup Python library environment

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/library.md

Install the library in editable mode with development dependencies.

```bash
pip install -e '.[dev]'
```

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

### Install System Prerequisites

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/template.md

Use these commands to install necessary system-level dependencies on Ubuntu.

```bash
sudo apt-get update
sudo apt-get install -y <packages-you-actually-installed>
```

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

### Install Go SDK

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Install the official Anthropic Go SDK to interact with the Claude API.

```bash
go get github.com/anthropics/anthropic-sdk-go
```

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

### Query Examples for file_search

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/tool-file_search.md

Examples demonstrating how to format queries with the + operator and QDF freshness parameters, including multilingual support.

```text
User: 김민준이 무엇을 하고 있나요? => {{"queries": ["current projects tasks for +(Kim Minjun) --QDF=3", "현재 프로젝트 및 작업 +(김민준) --QDF=3"]}}
```

```text
User: オフィスは今週閉まっていますか？ => {{"queries": ["+Office closed week of July 2024 --QDF=5", "+オフィス 2024年7月 週 閉鎖 --QDF=5"]}}
```

```text
User: ¿Cuál es el rendimiento del modelo 4o en GPQA? => {{"queries": ["GPQA results for +(4o model)", "4o model accuracy +(GPQA)", "resultados de GPQA para +(modelo 4o)", "precisión del modelo 4o +(GPQA)"]}}
```

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

### Execute Bash Command Examples

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/claude-desktop-code.md

Examples demonstrating correct and incorrect usage of the Bash tool for running tests.

```bash
pytest /foo/bar/tests
```

```bash
cd /foo/bar && pytest tests
```

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

### Install Anthropic CLI

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Installation instructions for macOS, Linux/WSL, and building from source.

```sh
# macOS
brew install anthropics/tap/ant
xattr -d com.apple.quarantine "$(brew --prefix)/bin/ant"

# Linux / WSL — pick the release from github.com/anthropics/anthropic-cli/releases
curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${VERSION}/ant_${VERSION}_$(uname -s | tr A-Z a-z)_$(uname -m | sed -e s/x86_64/amd64/ -e s/aarch64/arm64/).tar.gz" \
  | sudo tar -xz -C /usr/local/bin ant

# Or from source (Go 1.22+)
go install github.com/anthropics/anthropic-cli/cmd/ant@latest
```

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

### Greeting and Contextual Response Examples

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/claude-sonnet-5.md

Examples demonstrating how to handle casual greetings while incorporating user-specific memory data.

```xml
<example>
<example_user_memories>
User's name is <name>, user completed a marathon in Iceland, user is pregnant and currently planning coverage for maternity leave
</example_user_memories>
<user>
Good morning Claude
</user>
<good_response>
Good morning <name>! How can I be of assistance?
</good_response>
</example>
```

```xml
<example>
<example_user_memories>
User's name is <name>, user has expressed worries about mental health amidst personal crises, user enjoys reading nonfiction history books
</example_user_memories>
<user>
what's up claude
</user>
<good_response>
Hi, <name>! What can I help you with?
</good_response>
<bad_response>
I can see you're going through hard times right now - you've been carrying a lot. Can you tell me a bit more about what's going on right now? Do you need my help with finding someone to call?
</bad_response>
</example>
```

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

### msearch Command Examples

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/tool-file_search.md

Examples demonstrating how to structure queries for the msearch command, including entity boosting and QDF freshness ratings.

```json
{"queries": ["GDP of +France in the 1970s --QDF=0", "GDP of +Italy in the 1970s --QDF=0"]}
```

```json
{"queries": ["+GPT4 performance on +MMLU benchmark --QDF=1"]}
```

```json
{"queries": ["Customer Management System integration with +email marketing --QDF=2"]}
```

```json
{"queries": ["Best practices for +security and +privacy for +cloud storage --QDF=2"]}
```

```json
{"queries": ["current projects OKRs for +Design team --QDF=3"]}
```

```json
{"queries": ["current projects tasks for +(John Doe) --QDF=3"]}
```

```json
{"queries": ["Launch date for +Metamoose --QDF=4"]}
```

```json
{"queries": ["+Office closed week of July 2024 --QDF=5"]}
```

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

### Node API Run Section Example

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/server.md

A complete example of a Run section for a Node API, including background startup, polling, and termination.

```bash
npm run dev &> /tmp/api.log &
```

```bash
for i in {1..20}; do
  curl -sf http://localhost:3000/health && break
  sleep 0.5
done
curl http://localhost:3000/health
# → {"status":"ok","version":"1.2.3"}
```

```bash
pkill -f "tsx watch src/index.ts"
```

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

### Slack File Search Examples

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/raw/claude-sonnet-4.6-raw.md

Examples demonstrating how to use content_types and type modifiers to narrow down file searches in Slack.

```text
content_types="files" type:spreadsheets budget after:2025-01-01
```

```text
content_types="files" type:documents from:<@Jane Doe> after:2025-01-01
```

```text
content_types="files" type:canvases in:devel-engineering
```

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

### Web Tool Command Examples

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/o3.md

Examples of various commands available for the web tool, including search, image queries, navigation, and data lookups.

```json
{"search_query": [{"q": "What is the capital of France?"}, {"q": "What is the capital of belgium?"}]}
```

```json
{"image_query":[{"q": "waterfalls"}]}
```

```json
{"open": [{"ref_id": "turn0search0"}, {"ref_id": "https://www.openai.com", "lineno": 120}]}
```

```json
{"click": [{"ref_id": "turn0fetch3", "id": 17}]}
```

```json
{"find": [{"ref_id": "turn0fetch3", "pattern": "Annie Case"}]}
```

```json
{"finance":[{"ticker":"AMD","type":"equity","market":"USA"}]}, {"finance":[{"ticker":"BTC","type":"crypto","market":""}]}
```

```json
{"weather":[{"location":"San Francisco, CA"}]}
```

```json
{"sports":[{"fn":"standings","league":"nfl"}, {"fn":"schedule","league":"nba","team":"GSW","date_from":"2025-02-24"}]}
```

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

### Create Agent and Session with Custom Configuration

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Shows how to include system prompts, custom tools, and GitHub repository resources during agent and session setup.

```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"
      }
    ]
  }'
```

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

### Define Relative Start Offset

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/o4-mini-high.md

Example of using JSON-encoded arguments for Python dateutil relativedelta to set a relative start time.

```json
dtstart_offset_json='{"minutes":15}'
```

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

### Start development server

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Google/antigravity-cli.md

Execute this command to launch the local development server for the web application.

```bash
npm run dev
```

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

### Create Agent and Session Minimal Example

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Demonstrates the two-step process of creating an agent followed by initializing a session using cURL.

```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"
  }'
```

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

### GET /v1/files/{file_id}

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Get metadata for a specific file.

```APIDOC
## GET /v1/files/{file_id}

### Description
Retrieve the metadata for a specific file.

### Method
GET

### Endpoint
/v1/files/{file_id}

### Parameters
#### Path Parameters
- **file_id** (string) - Required - The ID of the file.
```

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

### GET /v1/memory_stores/{memory_store_id}/memories/{memory_id}

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Get a memory.

```APIDOC
## GET /v1/memory_stores/{memory_store_id}/memories/{memory_id}

### Description
Read one memory (defaults to view="full").

### Method
GET

### Endpoint
/v1/memory_stores/{memory_store_id}/memories/{memory_id}

### Parameters
#### Path Parameters
- **memory_store_id** (string) - Required
- **memory_id** (string) - Required

### Query Parameters
- **view** (string) - Optional
```

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

### Full End-to-End Example

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Demonstrates uploading a document, performing multiple queries, and cleaning up the file.

```python
import anthropic

client = anthropic.Anthropic()

# 1. Upload once
uploaded = client.beta.files.upload(
    file=("contract.pdf", open("contract.pdf", "rb"), "application/pdf"),
)
print(f"Uploaded: {uploaded.id}")

# 2. Ask multiple questions using the same file_id
questions = [
    "What are the key terms and conditions?",
    "What is the termination clause?",
    "Summarize the payment schedule.",
]

for question in questions:
    response = client.beta.messages.create(
        model="claude-opus-4-8",
        max_tokens=16000,
        messages=[{
            "role": "user",
            "content": [
                {"type": "text", "text": question},
                {
                    "type": "document",
                    "source": {"type": "file", "file_id": uploaded.id}
                }
            ]
        }],
        betas=["files-api-2025-04-14"],
    )
    print(f"\nQ: {question}")
    text = next((b.text for b in response.content if b.type == "text"), "")
    print(f"A: {text[:200]}")

# 3. Clean up when done
client.beta.files.delete(uploaded.id)
```

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

### GET /v1/memory_stores/{memory_store_id}

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Get memory store details.

```APIDOC
## GET /v1/memory_stores/{memory_store_id}

### Description
Get store details.

### Method
GET

### Endpoint
/v1/memory_stores/{memory_store_id}

### Parameters
#### Path Parameters
- **memory_store_id** (string) - Required
```

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

### Initialize Anthropic Clients

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Examples for initializing the standard client and specialized clients for Bedrock, Vertex AI, and Foundry.

```php
use Anthropic\Client;

// Using API key from environment variable
$client = new Client(apiKey: getenv("ANTHROPIC_API_KEY"));
```

```php
use Anthropic\Bedrock;

// Constructor is private — use the static factory. Reads AWS credentials from env.
$client = Bedrock\Client::fromEnvironment(region: 'us-east-1');
```

```php
use Anthropic\Vertex;

// Constructor is private. Parameter is `location`, not `region`.
$client = Vertex\Client::fromEnvironment(
    location: 'us-east5',
    projectId: 'my-project-id',
);
```

```php
use Anthropic\Foundry;

// Constructor is private. baseUrl or resource is required.
$client = Foundry\Client::withCredentials(
    authToken: getenv('ANTHROPIC_FOUNDRY_AUTH_TOKEN'),
    baseUrl: 'https://<resource>.services.ai.azure.com/anthropic',
);
```

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

### GET /v1/environments/{environment_id}

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Get details for a specific environment.

```APIDOC
## GET /v1/environments/{environment_id}

### Description
Get environment details.

### Method
GET

### Endpoint
/v1/environments/{environment_id}

### Parameters
#### Path Parameters
- **environment_id** (string) - Required - The ID of the environment.
```

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

### Feature Implementation Planning Example

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/claude-desktop-code.md

Illustrates how to use the TodoWrite tool to plan and track the implementation of a new feature step-by-step.

```text
<example>
user: Help me write a new feature that allows users to track their usage metrics and export them to various formats
assistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the TodoWrite tool to plan this task.
Adding the following todos to the todo list:
1. Research existing metrics tracking in the codebase
2. Design the metrics collection system
3. Implement core metrics tracking functionality
4. Create export functionality for different formats

Let me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.

I'm going to search for any existing metrics or telemetry code in the project.

I've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned...

[Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go]
</example>
```

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

### GET /v1/skills/{id}

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Get details for a specific custom skill.

```APIDOC
## GET /v1/skills/{id}

### Description
Retrieve details for a specific custom skill by its ID.

### Method
GET

### Endpoint
/v1/skills/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the skill.
```

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

### GET /v1/environments/{environment_id}/work/stats

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Get self-hosted work-queue statistics.

```APIDOC
## GET /v1/environments/{environment_id}/work/stats

### Description
Self-hosted work-queue depth/pending/workers. `x-api-key` auth.

### Method
GET

### Endpoint
/v1/environments/{environment_id}/work/stats

### Parameters
#### Path Parameters
- **environment_id** (string) - Required - The ID of the environment.
```

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

### Initialize Anthropic Client

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Demonstrates client initialization using environment variables or an explicit API key.

```go
import (
    "github.com/anthropics/anthropic-sdk-go"
    "github.com/anthropics/anthropic-sdk-go/option"
)

// Default (uses ANTHROPIC_API_KEY env var)
client := anthropic.NewClient()

// Explicit API key
client := anthropic.NewClient(
    option.WithAPIKey("your-api-key"),
)
```

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

### Install Anthropic SDK

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Command to install the Anthropic Python package.

```bash
pip install anthropic
```

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

### Create an Agent with System Prompts and Custom Tools

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Shows how to configure an agent with a system prompt and custom tools, and how to attach resources like GitHub repositories to a session.

```typescript
const agent = await client.beta.agents.create(
  {
    name: "Code Reviewer",
    model: "claude-opus-4-8",
    system: "You are a senior code reviewer.",
    tools: [
      { type: "agent_toolset_20260401", default_config: { enabled: true } },
      {
        type: "custom",
        name: "run_tests",
        description: "Run the test suite",
        input_schema: {
          type: "object",
          properties: {
            test_path: { type: "string", description: "Path to test file" },
          },
          required: ["test_path"],
        },
      },
    ],
  },
);

const session = await client.beta.sessions.create(
  {
    agent: { type: "agent", id: agent.id, version: agent.version },
    environment_id: environment.id,
    title: "Code review session",
    resources: [
      {
        type: "github_repository",
        url: "https://github.com/owner/repo",
        mount_path: "/workspace/repo",
        authorization_token: process.env.GITHUB_TOKEN,
        branch: "main",
      },
    ],
  },
);
```

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

### Install Anthropic SDK

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Use npm to install the official Anthropic SDK package.

```bash
npm install @anthropic-ai/sdk
```

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

### CLI Tool Execution Examples

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/cli.md

Demonstrates processing files, using stdin/stdout, and linting directories with exit code checks.

```bash
mytool process input.json
# → Processed 42 records, wrote output.json
```

```bash
cat input.json | mytool process -
```

```bash
mytool lint ./src
echo $?  # 0 if clean, 1 if issues found
```

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

### Verify CLI installation

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run.md

Checks the installed version of the tool to confirm it is correctly configured.

```bash
mytool --version
# → mytool 0.3.1
```

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

### Install System Dependencies

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md

Install required Linux libraries for running Electron under Xvfb.

```bash
apt-get install -y xvfb libnss3 libgbm1 libasound2t64 libgtk-3-0 \
  libxss1 libxkbcommon0 libatk-bridge2.0-0 libcups2 libdrm2
```

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

### Task Management Workflow Example

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/claude-desktop-code.md

Demonstrates the process of breaking down a build and error-fixing task into actionable items using the TodoWrite tool.

```text
<example>
user: Run the build and fix any type errors
assistant: I'm going to use the TodoWrite tool to write the following items to the todo list:
- Run the build
- Fix any type errors

I'm now going to run the build using Bash.

Looks like I found 10 type errors. I'm going to use the TodoWrite tool to write 10 items to the todo list.

marking the first todo as in_progress

Let me start working on the first item...

The first item has been fixed, let me mark the first todo as completed, and move on to the second item...
..
..
</example>
```

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

### Check for conflicting installations

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/claude-code-docs-assistant.md

Commands to identify multiple or conflicting installations of the Claude binary.

```bash
which -a claude
```

```powershell
where.exe claude
```

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

### Create an Environment

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Provision a new environment with specific configuration settings.

```python
environment = client.beta.environments.create(
    name="my-dev-env",
    config={
        "type": "cloud",
        "networking": {"type": "unrestricted"},
    },
)
print(environment.id)  # env_...
```

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

### Example of invoking a connector fetch tool

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/chatgpt-4.5.md

Demonstrates the syntax for calling a connector fetch tool with a URL parameter.

```text
Assistant (to=Google_Drive.fetch): {"url":"https://docs.google.com/document/d/..."}
```

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

### Search Query Examples

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/gpt-5.5-thinking.md

Examples of JSON payloads for various search intents and filters.

```json
{"queries": ["project +moonlight docs"], "source_filter": ["google_drive"], "intent": "nav"}
```

```json
{"queries": ["+hyperbeam +oncall playbook link"], "intent": "nav"}
```

```json
{"queries": ["+muon +SEV discussion --QDF=5", "+muon +SEV followup --QDF=5"], "source_filter": ["slack"]}
```

```json
{"queries": ["slides on +hypertraining --QDF=4", "+hypertraining presentations --QDF=4"], "source_filter": ["google_drive"], "intent": "nav", "file_type_filter": ["slides"]}
```

```json
{"queries": ["+Office closed week of July 2024 --QDF=5"]}
```

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

### GET /v1/skills/{id}/versions/{version}

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Get details for a specific version of a custom skill.

```APIDOC
## GET /v1/skills/{id}/versions/{version}

### Description
Retrieve details for a specific version of a custom skill.

### Method
GET

### Endpoint
/v1/skills/{id}/versions/{version}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the skill.
- **version** (string) - Required - The version identifier.
```

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

### Implement Resource Dependency Example

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/claude-design.md

Demonstrates the pattern for declaring dependencies in the head and accessing them via the window.__resources object in the application code.

```html
<!-- In <head>: -->
<meta name="ext-resource-dependency" content="./hero.png" data-resource-id="heroImg" />
<meta name="ext-resource-dependency" content="./pattern.svg" data-resource-id="patternBg" />

<!-- In code, replace: -->
<!-- <img src={"./hero.png"} /> -->
<!-- with: -->
<!-- <img src={window.__resources.heroImg} /> -->
```

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

### Install Anthropic Ruby Gem

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Install the required gem to use the Anthropic Ruby SDK.

```bash
gem install anthropic
```

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

### computer.initialize

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/chatgpt-gpt-5-agent-mode.md

Initializes the computer session.

```APIDOC
## initialize()

### Description
Initializes a computer session.

### Signature
`initialize() => any`
```

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

### Install CLI tool

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run.md

Installs the tool in editable mode to ensure it is available on the system PATH.

```bash
pip install -e .
```

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

### Full End-to-End Batch Example

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/claude-api.md

Demonstrates the complete lifecycle of a batch: preparation, creation, polling for completion, and result collection.

```python
import anthropic
import time
from anthropic.types.message_create_params import MessageCreateParamsNonStreaming
from anthropic.types.messages.batch_create_params import Request

client = anthropic.Anthropic()

# 1. Prepare requests
items_to_classify = [
    "The product quality is excellent!",
    "Terrible customer service, never again.",
    "It's okay, nothing special.",
]

requests = [
    Request(
        custom_id=f"classify-{i}",
        params=MessageCreateParamsNonStreaming(
            model="claude-haiku-4-5",
            max_tokens=50,
            messages=[{
                "role": "user",
                "content": f"Classify as positive/negative/neutral (one word): {text}"
            }]
        )
    )
    for i, text in enumerate(items_to_classify)
]

# 2. Create batch
batch = client.messages.batches.create(requests=requests)
print(f"Created batch: {batch.id}")

# 3. Wait for completion
while True:
    batch = client.messages.batches.retrieve(batch.id)
    if batch.processing_status == "ended":
        break
    time.sleep(10)

# 4. Collect results
results = {}
for result in client.messages.batches.results(batch.id):
    if result.result.type == "succeeded":
        msg = result.result.message
        results[result.custom_id] = next((b.text for b in msg.content if b.type == "text"), "")

for custom_id, classification in sorted(results.items()):
    print(f"{custom_id}: {classification}")
```

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

### Verify Python library version

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/library.md

Check the installed version of the library to confirm successful installation.

```bash
python -c 'import mylib; print(mylib.__version__)'
# → 2.1.0
```

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

### Check Vite CLI options

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/Google/antigravity-cli.md

Run this command to inspect available configuration options before initializing a new project.

```bash
npx -y create-vite-app@latest --help
```

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

### Schedule Example: Daily Morning

Source: https://github.com/asgeirtj/system_prompts_leaks/blob/main/OpenAI/gpt-5.3-instant.md

Example of a daily recurring schedule using the RRULE property.

```text
schedule="BEGIN:VEVENT

RRULE:FREQ=DAILY;BYHOUR=9;BYMINUTE=0;BYSECOND=0

END:VEVENT"
```