Setup
- 74 installs
- 325 repo stars
- Updated August 2, 2026
- athola/claude-night-market
Setup is an agent skill that provisions the Oracle ML inference daemon with onnxruntime via uv for local skill quality evaluation.
About
Setup is a focused provisioning skill for the Claude Night Market Oracle plugin: it prepares a local Python 3.11+ environment with uv, installs onnxruntime, and verifies the venv so an ML inference daemon can evaluate agent skill quality offline. Solo builders maintaining skill marketplaces or custom skill lint/eval pipelines use it once per machine or after environment drift—not during everyday feature coding. The skill runs a single documented bash invocation against oracle.provision, surfaces the message to the user, and sets expectations that the daemon attaches on the next session when successful. Failures point to uv or network issues rather than opaque stack traces. It is intentionally narrow infrastructure glue between your repo’s plugins/oracle code and runnable ONNX inference, keeping skill quality checks local instead of cloud-only.
- 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
Setup by the numbers
- 74 all-time installs (skills.sh)
- Ranked #287 of 782 Skill Development skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill setupAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 74 |
|---|---|
| repo stars | ★ 325 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | athola/claude-night-market ↗ |
What it does
Provision the Oracle ONNX inference daemon with uv so local skill quality evaluation can run in Claude Night Market.
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 you get
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
By the numbers
- Python 3.11+ virtual environment
- onnxruntime install via uv
Files
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:
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.
Exit Criteria
- [ ]
provision_venv()returns a result with a non-errormessage
and the venv path exists on disk under plugins/oracle/
- [ ]
onnxruntimeis importable inside the provisioned venv;
verified by uv run python -c "import onnxruntime" exiting 0
- [ ] User receives a clear success message stating the daemon will
start on next session, or a clear failure message citing the specific error and whether it is a uv or network issue
- [ ] On failure, no partial venv left in a broken state that would
prevent a clean retry
Related skills
Find SkillsSo their agent can intelligently recommend and install the right modular skills from the open ecosystem when they ask how to do something.3M27.9k
Lark Skill MakerRapidly create custom skills for Lark (Feishu) that can be invoked by their AI agents and automation workflows.513k
Skill CreatorGenerate, test, and iterate on new reusable agent skills directly inside their Claude or Cursor workflow.337k166k
BrainstormingTurn vague product ideas into clear, approved designs and specifications through guided collaborative dialogue before writing any code.307k265k
Writing Great SkillsCreate high-quality, reusable agent skills that other developers can discover and install from the Skillselion catalog.290k200k
Find SkillsInstantly surface the best relevant agent skills, MCP servers, and workflows across multiple registries before starting any new project.226k12How it compares
One-shot environment provisioner—not a skill authoring or benchmarking workflow like skill-creator.
FAQ
Who is setup for?
Developers 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.