How do I install the Chemtools Monitor Run skill?

Run npx skillmds@latest add charliecpeterson/chemtools-monitor-run 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.

Is Chemtools Monitor Run 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 Chemtools Monitor Run?

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 Chemtools Monitor Run free to use?

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

Who published Chemtools Monitor Run?

charliecpeterson (@charliecpeterson) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Chemtools Monitor Run by charliecpeterson

Name: Chemtools Monitor Run
Author: charliecpeterson

Chemtools Monitor Run

Refresh execution state and scientific progress for a calculation launched by the active Chemtools MCP process. Use when the user provides a Chemtools launch ID and asks whether its local process or Slurm job is queued, running, complete, or making scientific progress.

File contents

Monitor a Chemtools-owned run

Use the Chemtools monitor_run MCP tool for one explicit status refresh.

Require the complete launch_id returned by launch_run from the same active MCP server process.
Do not substitute a PID, Slurm job ID, output path, or guessed identifier.
Call monitor_run once and report execution state, recorded artifacts, backend scientific progress, uncertainty, and the highest-priority next action as separate facts.
Preserve unresolved scheduler or accounting state. Do not infer completion merely because a job is absent from the live queue.
For repeated checks, refresh only at the interval or follow-up requested by the user. Do not create an unbounded polling loop.

This workflow never submits, restarts, cancels, edits, or relaunches a run. If the identifier is unowned after a server restart, explain that ownership was process-local. Ask for the primary output path and use chemtools-inspect-run when the user wants a scientific verdict from an existing file.

Frequently asked questions