install

스타41

포크6

업데이트2026년 5월 20일 13:08

Use this skill if the required tools are not yet installed.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

int-brain-lab

int-brain-lab/ibl-ai-agent

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Preflight and Installation

Before the first research, report-writing, or publishing task in a fresh checkout, run a small setup preflight yourself. Check for a usable Python, uv, a project environment, core Python imports, Quarto for report rendering, Git/GitHub CLI for publishing, GitHub authentication when publishing is requested, and configured IBL data access or local dataset paths when data loading is needed.
If any of these items are missing STOP, do not proceed to scientific analyses. Even if the user has asked a scientific question, do not proceed with scientific analyses unless the user gives you explicit instructions to do so rather than completing installation.
Instead, interactively lead the user through installation of missing items, using uv unless explicitly instructed otherwise. Explain the missing item(s) and offer to install or configure them. Use tool calls to run the needed commands after approval when network, package installation, or external authentication is required.
Prefer uv for project setup. If uv is missing but Python is available, offer to install uv, then run UV_CACHE_DIR=.uv-cache uv sync --extra ibl --extra notebook --extra dev. Use uv run ... for project commands once the environment exists. Do not recommend plain pip install -e . as the primary setup path because brainwidemap is resolved through uv sources.
Verify Quarto, git, gh, and gh auth status, which are required for report publication.
For some packages such as Quarto, git, and gh, automatic installation may be difficult. In such cases, guide the user to appropriate websites to manually download and install what is needed.
If the BWM data shards are not yet present, ask the user if these files are already present on disk. If so, edit data_locations.local.yaml to point to them; if not, ask the user for a location to download to (defaulting to data/ within the current repo), download, then edit data_locations.local.yaml.

이 저장소의 다른 Skills

같은 저장소

ibl-analyze

int-brain-lab/ibl-ai-agent

Use this skill for quantitative scientific analysis of IBL data after the always-on scientific workflow in `AGENTS.md` is active.

2026-06-2341

ibl-load

int-brain-lab/ibl-ai-agent

Use this skill when loading IBL data, preferring the smallest sufficient local or aggregate surface before session-level loaders.

2026-06-2341

scientific-coding-style

int-brain-lab/ibl-ai-agent

describes how to write code to be read and validated by human scientists.

2026-06-1341

ibl-neuropixel

int-brain-lab/ibl-ai-agent

Use this skill for raw Neuropixels binary access, destriping, compression, waveform extraction, and probe-level preprocessing based on the `int-brain-lab/ibl-neuropixel` repository.

2026-05-2641

exploration-confirmation

int-brain-lab/ibl-ai-agent

Use this skill to analyze scientific data: refine, formalize and test hypotheses.

2026-05-2041

ibl-access

int-brain-lab/ibl-ai-agent

Use this skill when a task needs IBL data access setup, ONE/Alyx authentication, or selecting between public and private data modes.

2026-05-1941

Preflight and Installation

Before the first research, report-writing, or publishing task in a fresh checkout, run a small setup preflight yourself. Check for a usable Python, uv, a project environment, core Python imports, Quarto for report rendering, Git/GitHub CLI for publishing, GitHub authentication when publishing is requested, and configured IBL data access or local dataset paths when data loading is needed.

If any of these items are missing STOP, do not proceed to scientific analyses. Even if the user has asked a scientific question, do not proceed with scientific analyses unless the user gives you explicit instructions to do so rather than completing installation.

Instead, interactively lead the user through installation of missing items, using uv unless explicitly instructed otherwise. Explain the missing item(s) and offer to install or configure them. Use tool calls to run the needed commands after approval when network, package installation, or external authentication is required.

Prefer uv for project setup. If uv is missing but Python is available, offer to install uv, then run UV_CACHE_DIR=.uv-cache uv sync --extra ibl --extra notebook --extra dev. Use uv run ... for project commands once the environment exists. Do not recommend plain pip install -e . as the primary setup path because brainwidemap is resolved through uv sources.

Verify Quarto, git, gh, and gh auth status, which are required for report publication.

For some packages such as Quarto, git, and gh, automatic installation may be difficult. In such cases, guide the user to appropriate websites to manually download and install what is needed.

If the BWM data shards are not yet present, ask the user if these files are already present on disk. If so, edit data_locations.local.yaml to point to them; if not, ask the user for a location to download to (defaulting to data/ within the current repo), download, then edit data_locations.local.yaml.

name	install
description	Use this skill if the required tools are not yet installed.