Setup Environment

Pre-flight environment gate for the research recipe. Reads the experiment plan, detects the required environment type, builds a Docker image or creates a host micromamba environment, and emits an env_mode verdict consumed by downstream steps.

5 stars 1 forksDevOps & Cloud

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill setup-environment
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/setup-environment ~/.claude/skills/setup-environment

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Environment Setup

Pre-flight environment gate for the research recipe. Decouples environment
decisions (Docker vs host-micromamba vs none) from `implement-experiment`'s
inline Docker build. Reads the experiment plan to determine the required
environment type, probes Docker availability, builds a Docker image when
possible, falls back to a host micromamba environment for pure conda-forge
Python deps, and emits an `env_mode` verdict consumed by downstream steps.
PASS and WARN proceed to `decompose_phases`; FAIL escalates immediately.

## Arguments

```
/autoskillit:setup-environment <worktree_path> <experiment_plan>
```

- `worktree_path` — Absolute path to the shared research worktree (positional).
- `experiment_plan` — Absolute path to the experiment plan YAML (positional).

## When to Use

- Called by the research recipe's `setup_environment` step between `stage_data`
  and `decompose_phases`
- Whenever a pre-flight environment check is needed before experiment implementation

## Critical Constraints

**NEVER:**
- Modify the experiment plan
- Write files outside `{{AUTOSKILLIT_TEMP}}/setup-environment/`
- Skip the Docker availability probe before attempting a build
- Run subagents in the background (`run_in_background: true` is prohibited)

**ALWAYS:**
- Parse `environment.type` from the experiment plan first
- Try Docker before falling back to micromamba
- Write the environment setup report before emitting the verdict token
- Use `model: "sonnet"` for all subagents
Read the full skill on GitHub

Details

Skill name
setup-environment
Path
src/autoskillit/skills_extended/setup-environment/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Setup Environment skill do?

Pre-flight environment gate for the research recipe. Reads the experiment plan, detects the required environment type, builds a Docker image or creates a host micromamba environment, and emits an env_mode verdict consumed by downstream steps.

How do I install the Setup Environment skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill setup-environment. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Setup Environment popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.