PursuitOfDataScience

Fit — Development skill for Claude Code

Development community

Fit a job or sbatch script to what it actually used, with the sample size stated.

How to install Fit

Installs to ~/.claude/skills/pursuitofdatascience-cloudfit-plugin-fit/SKILL.md

Terminal
mkdir -p ~/.claude/skills/pursuitofdatascience-cloudfit-plugin-fit && curl -fsSL https://raw.githubusercontent.com/PursuitOfDataScience/cloudfit-plugin/HEAD/commands/fit.md -o ~/.claude/skills/pursuitofdatascience-cloudfit-plugin-fit/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Fit does


description: Fit a job or sbatch script to what it actually used, with the sample size stated. argument-hint:

Fit `$ARGUMENTS` with the `cloudfit` MCP tools.

  • A number that looks like a job id: measure it, then fit it.
  • A path: fit it from its past runs, then check it.
  • Neither: run capabilities and say which telemetry sources this machine has.

If a refusal turns on a partition or account name, run `site`. It reports what this cluster actu

Alternatives in Development

  • Market Segments — Identify 3-5 customer segments with JTBD and product fit 7.8k ★
  • Memory Gc — Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl) 3.8k ★
  • Memory Statistics — Show statistics about Claude's persistent memory file including total memories, storage size, and recent activ 332 ★

Full documentation available on GitHub

View Source Repository