spectackl

Command-line interface to the Spectackl Public REST API — built for AI agents and operators who need programmatic access to artifacts, scenes and task executions without going through the web UI.

pip install spectackl

Quick start

spectackl init --api-key spc_… --backend-url https://api.spectackl.ai --project my-project
spectackl artifact list --json

API keys are managed in the Spectackl Admin Console. init writes .spectackl/settings.yaml in the current directory and a user-global ~/.config/spectackl/settings.yaml; both are created 0600 and neither should be committed.

What it does

Every command accepts --json for machine-readable output, and every command returns a documented exit code — 0 success, 10 auth required, 20 validation, 30 not found, 40 upstream unavailable, and so on — so scripts can branch on failures precisely rather than parsing text.

Designed for agents

Output is stable and parseable, errors are structured, and the exit-code scheme is part of the public contract. spectackl assets sync writes agent and skill definitions in the exact layout Claude Code reads, built from the same artifacts the platform provisions into a sandbox — so an agent invoked on a workstation is the one that runs in production.

Requirements

• Python 3.10+
• A Spectackl tenant and an API key (spc_ prefix)

Documentation

Full guide: https://docs.spectackl.ai

License

MIT