Who it is forA plant trainer or process engineer who needs a visual, clickable pump for operator training and has no 3D modelling skills.
The problemStatic diagrams of pumps do not show how the curve, NPSH margin and seal behave when conditions change.
The outcomeA single HTML file of an API 610 style process pump that trainees can drag, cut open, hover for part roles, and break by dropping the tower level.
What you need first
- Claude Code, or another Agent Skills host such as Codex or Cursor, to build machines
- A browser with WebGL 2 to run the generated pages
- Node 18+, Playwright and ffmpeg, only if you want to record films or stills
Steps
- Run
npx skills add AirsupHQ/machine-skill -g -a claude-codein a terminal. - Start a new Claude Code session, or run
/reload-skillsif the skills folder did not exist when the session started. - In Claude Code, run
/machine a refinery process pump, API 610 style, cut open for plant training. (inferred, check the README) - Open the generated HTML file in a browser and use the cutaway, explode and break modes.
- Share the single file with trainees or embed it in your training site.
Prompt for your agent
Using the repo AirsupHQ/machine-skill, build a cut-open refinery process pump for plant training as one HTML file. The expected output is a single .html file that opens from disk and shows the pump curve, NPSH available against required, and hover labels. Verify that the file opens in a WebGL 2 browser and that the cutaway and break modes respond.
Caveat. The physics is a small honest model, not CFD or FEA, so the pump numbers are checked against public figures rather than certified.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page