How do I install the Env Inspect skill?

Run npx skillmds@latest add the-biomechanist/env-inspect in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Env Inspect skill do?

Inspect Windows host, runtime, toolchain, package-manager, and isolation state when those facts are needed for a development task. It is listed under Productivity on SkillMD.

Is Env Inspect safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Env Inspect?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Env Inspect free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Env Inspect?

The-Biomechanist (@the-biomechanist) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Env Inspect by the-biomechanist — Agent Skill

Name: Env Inspect
Author: The-Biomechanist

File contents

Environment Inspect

Call env_inspect when machine/runtime state can change the next action.
Read the returned snapshot as evidence. Availability values are tri-state:
- true — observed present/enabled;
- false — observed absent/disabled;
- null — the probe did not establish the fact.
Treat top-level status: degraded, snapshot.success: false, or a relevant entry in snapshot.errors as partial evidence. Do not convert an unknown/failed probe into “missing.”
The broad snapshot establishes Windows feature state and executable presence without launching developer binaries for version output. Use tool_discover only when a focused executable/version check can change the route. tool_discover executes discovered programs with a version argument, so it remains on the active host permission surface even though the requested effect is diagnostic. If the executable is present but its version probe fails, preserve version_status: unknown rather than inventing a version.
Treat cached environment state as time-bound. After an install, optional-feature change, PATH/toolchain mutation, or other action that can invalidate the field you are about to consume, prefer the narrow fresh probe; if a full snapshot is required, call env_inspect with force_refresh: true.
Use ecosystem_scan for MCP configs, extensions, project agent config, or host plugin inventory. Project-only inventory is the narrow default; request include_host: true only when user-level state is actually needed.
Suggest a repair only when observed state blocks or materially degrades the requested task.

For package installation, route to the package-install skill and package_search / package_install MCP tools rather than emitting an unreviewed install command.

Frequently asked questions

Env Inspect