Jobs Eval — Development skill for Claude Code
Scoring-quality check.
How to install Jobs Eval
Installs to ~/.claude/commands/ncalavera-llm-job-pipeline-jobs-eval.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ncalavera/llm-job-pipeline/HEAD/.claude/commands/jobs-eval.md -o ~/.claude/commands/ncalavera-llm-job-pipeline-jobs-eval.md Restart Claude Code, or start a new session, for it to be picked up.
What Jobs Eval does
description: Scoring-quality check. Build a small golden set of your own vacancies labelled fits / doesn't-fit, score them with the CURRENT prompt, and get one agreement number plus a list of disagreements to fix. Any user can run it; the set is personal and never leaves your machine.
/jobs-eval
Does the scorer actually agree with *you*? This command answers that with one number. It builds a **golden set** — a few dozen of your own vacancies each labelled `fit` or `nofit` with a shor
Alternatives in Development
- Market Segments — Identify 3-5 customer segments with JTBD and product fit 7.8k ★
- Quick Eval — Quick job evaluation 473 ★
- Migrations — Versioned breaking change migrations for Turbo 263 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Jobs Scout
Scan for new roles that fit the profile, direct from company careers pages and ATS boards plus web search, sco
Jobs Night
Headless nightly scoring session. Invoked by scripts/nightly_run.py as /jobs-night — one session per scoring g
Eval Author
Draft a new eval case (eval/cases/ .json) + scaffold its golden folder, golden_pending until captured on the V
Eval Prompts
Run a golden-set prompt eval suite against the pinned baseline; fail on any regression beyond threshold.
Fats
FUAK Applicant Tracking System — a Claude skill that scores jobs for fit to you, not the other way around.
Arckit.Application Inventory
Catalog existing applications with strategic fit scoring, dependencies, and lifecycle status
Related Agents
Night Scorer
Nightly headless discovery/scoring subagent. Reads ONE payload file from vacancies/nightly/ /score_in/ and wri
Quality Fit
Code quality check for types, lint, and project conventions. Verify code fits RDO patterns.
Gad Systematics Fitter
Builds the pyhf HistFactory workspace, performs fits, computes expected limits, and produces fit diagnostics (