programmatic-claude

Execute Claude Code programmatically via CLI, Python SDK, and TypeScript SDK.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/WebSmartTeam/COR-CODE --skill programmatic-claude
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: programmatic-claude
Source: https://github.com/WebSmartTeam/COR-CODE/tree/main/skills/programmatic-claude
Command: npx skills add https://github.com/WebSmartTeam/COR-CODE --skill programmatic-claude

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates Claude Code execution, enabling complex workflows and integrations without manual interaction.

Core Features & Use Cases

  • Automated Workflows: Execute Claude tasks via CLI, Python, or TypeScript for scripting and CI/CD.
  • Session Chaining: Link multiple Claude interactions for multi-step processes.
  • Structured Output: Enforce specific data formats for reliable integration.
  • Use Case: Automate code reviews in a CI/CD pipeline, or build a custom agent that orchestrates multiple Claude calls to generate a complex report.

Quick Start

Use the programmatic-claude skill to fix all TypeScript errors in the src directory using the CLI.

Frequently Asked Questions about programmatic-claude

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Claude Code execution in a CI/CD pipeline?

Automating Claude Code execution in a CI/CD pipeline is achieved by running it programmatically via CLI, Python SDK, or TypeScript SDK for unattended workflows and custom integrations.

Can I enforce structured JSON output when running Claude programmatically?

Enforcing structured JSON output when running Claude programmatically is supported natively, allowing you to enforce specific data formats via JSON schema for reliable downstream integration.

Does the Claude Python SDK support session continuity for multi-step processes?

The Claude Python SDK supports session continuity by chaining multiple Claude interactions, enabling you to link sequential calls for complex multi-step orchestration processes.

How do I integrate custom tools when orchestrating Claude headless?

Integrating custom tools when orchestrating Claude headless is handled through in-process MCP servers, enabling custom tool integration within your automated execution workflow.

What is the best way to run unattended Claude tasks via TypeScript?

Running unattended Claude tasks via TypeScript is best handled through the TypeScript SDK, which supports custom system prompts and scripted orchestration without manual interaction.