Installation#
sklab is the CLI that ships with the skill-lab PyPI package. It runs the same static checks and LLM judge as the hosted API — but locally, against a skill directory on your machine. Python 3.10 or newer is required.
Install#
$ pip install skill-labOr with uv:
$ uv pip install skill-labVerify#
$ sklab --versionRunning sklab on its own scans the current directory for SKILL.md
files and prints a getting-started guide.
API Keys#
Most commands run without any credentials — check, scan, info, list-checks, prompt, stats, and setup. LLM-powered commands — evaluate (judge step), generate, trigger, and optimize — need an API key:
| Provider | Env var | Model prefix |
|---|---|---|
| Anthropic | ANTHROPIC_API_KEY | claude-* |
| OpenAI | OPENAI_API_KEY | gpt-* |
GEMINI_API_KEY | gemini-* |
Provider is auto-detected from the model prefix passed to --model. Keys are
read from the environment, a .env file in the current directory, or any
standard shell-profile setup. The default model is
claude-haiku-4-5-20251001 (Anthropic).
Trigger Testing Prerequisite#
sklab trigger drives a live LLM runtime. The default runtime uses the Claude CLI:
$ npm install -g @anthropic-ai/claude-codeFor container isolation (sklab trigger --provider docker), Docker must be installed and running.