
Setup
Provision the Oracle ONNX inference daemon with uv so local skill quality evaluation can run in Claude Night Market.
Overview
Setup is an agent skill for the Build phase that provisions the Oracle ML inference daemon with onnxruntime via uv for local skill quality evaluation.
Install
npx skills add https://github.com/athola/claude-night-market --skill setupWhat is this skill?
- Creates Python 3.11+ virtual environment using uv
- Installs onnxruntime into the Oracle plugin venv
- Runs provision_venv verification via plugins/oracle Python module
- Reports success or failure and notes daemon starts on next session when provision succeeds
- Explicit prerequisites: uv installed and network for initial package download
- onnxruntime install via uv
Adoption & trust: 1 installs on skills.sh; 304 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You want ONNX-backed skill evaluation in Night Market but lack a verified Python venv with onnxruntime on this machine.
Who is it for?
Maintainers of claude-night-market or similar Oracle plugins who need one-command local ONNX setup with uv.
Skip if: General Python project bootstrap unrelated to Oracle, or production model training pipelines outside skill evaluation.
When should I use this skill?
Setting up local ONNX model inference for skill quality evaluation; when provisioning the oracle ML inference daemon.
What do I get? / Deliverables
A provisioned Oracle venv is verified and ready so the inference daemon can start on your next agent session.
- Verified Oracle virtual environment
- User-visible provision success or error message
Recommended Skills
Journey fit
Build/agent-tooling is where you wire local ML inference into your agent plugin stack before evaluating or shipping skills. Agent-tooling captures daemon provisioning and venv setup for evaluation infrastructure, not end-user product features.
How it compares
One-shot environment provisioner—not a skill authoring or benchmarking workflow like skill-creator.
Common Questions / FAQ
Who is setup for?
Solo builders and plugin maintainers installing Claude Night Market’s Oracle stack who need local ONNX inference for evaluating agent skills.
When should I use setup?
During Build/agent-tooling setup on a new machine, after cloning the repo, or when skill quality evaluation fails because onnxruntime or the venv is missing.
Is setup safe to install?
Review the Security Audits panel on this page; provisioning runs shell Python in plugins/oracle and requires network to download packages—use trusted repos only.
SKILL.md
READMESKILL.md - Setup
# Oracle Setup Provision the ML inference environment. ## What This Does 1. Creates a Python 3.11+ virtual environment using uv 2. Installs onnxruntime into the venv 3. Verifies the installation ## Prerequisites - uv must be installed - Internet connection for initial download ## Steps 1. Run provisioning: ```bash cd plugins/oracle && uv run python -c " from oracle.provision import provision_venv, get_venv_path result = provision_venv(get_venv_path()) print(result.message) " ``` 2. Report result to the user. 3. If successful, tell the user the daemon will start on next session. 4. If failed, show the error and suggest checking uv and network.