Home / ai-analyst-lab / ai-analyst · .claude/skills/evaluate-grader/SKILL.md · GitHub

evaluate-grader skillA

evaluate-grader is agent-read markdown (skill) from ai-analyst-lab/ai-analyst: Compare a narrow model grader with frozen human labels and inspect disagreement, bias probes, and repeated scoring stability. Use when building or changing a model-based evaluator..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Evaluate a grader

Freeze the human labels before running the grader. Use one narrow criterion with a written rubric and structured output. The grader must be able to return `unknown` or request human review.

Keep human labels outside the judge workspace. Use `python3 -m helpers.evals.cli run-isolated-judge` to create a fresh child workspace containing only the named examples and current rubric. Run every revised rubric in a different fresh child. A child must not receive human labels, prior verdicts, captured verdicts, or later rubric versions. Preserve the isolation record with the verdicts.

Use `helpers.evals.judges.evaluate_alignment` for the confusion table and disagreement set. Repeat at least one unchanged boundary example and use `repeated_label_stability` to measure scoring stability.

Inspect:

- every human and grader disagreement;
- label imbalance;
- an answer-order reversal when judging pairs;
- a verbosity trap where a longer answer is not the better answer;
- an ambiguous example that should produce `unknown`; and
- whether the generator and grader are actually independent contexts.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add ai-analyst-lab/ai-analyst/evaluate-grader@git:20260920.18d2675
Exact content
mdr add ai-analyst-lab/ai-analyst/evaluate-grader@sha256:64fb96fc239f015b

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lajytpzdymgzypu5.svg)](https://markdownregistry.com/a/art_lajytpzdymgzypu5)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260920.18d2675 latest2026-09-20 18d2675 1,560 BA view · diff
git:20260910.c4b91ef2026-09-10 c4b91ef 1,167 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1560 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ai-analyst-lab/ai-analyst · 302 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lajytpzdymgzypu5
GET https://markdownregistry.com/api/v1/resolve?ref=ai-analyst-lab/ai-analyst/evaluate-grader
GET https://markdownregistry.com/api/v1/blob/64fb96fc239f015beea02a5946bf56bc73f7f05b12a9527a048c9de1966a489c

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from ai-analyst-lab/ai-analyst

always-compare skill
ai-analyst-lab/ai-analyst · .claude/skills/always-compare/SKILL.md · Never present a metric or number in isolation; anchor every number to a comparison (prior period, benchmark, or another…
git:20260827.7ff2e25 · audit A · 302 stars
analysis-design skill
ai-analyst-lab/ai-analyst · .claude/skills/analysis-design/SKILL.md · Takes a vague analytical hunch, stakeholder request, or business question and produces a rigorous, stakeholder-ready…
git:20260902.b370de6 · audit A · 302 stars
analyst-core skill
ai-analyst-lab/ai-analyst · .claude/skills/analyst-core/SKILL.md · Operating rules for every data analysis. Apply for ANY data-analysis intent: "analyze", "investigate", "why did X…
git:20260921.652dcb5 · audit A · 302 stars
archaeology skill
ai-analyst-lab/ai-analyst · .claude/skills/archaeology/SKILL.md · Retrieve proven SQL patterns, table cheatsheets, and join patterns from .knowledge/query-archaeology/ so past work gets…
git:20260827.7ff2e25 · audit A · 302 stars
archive-analysis skill
ai-analyst-lab/ai-analyst · .claude/skills/archive-analysis/SKILL.md · Save completed analyses to the knowledge system's analysis archive for future reference. Use this skill after…
git:20260902.b370de6 · audit A · 302 stars
auth-preflight skill
ai-analyst-lab/ai-analyst · .claude/skills/auth-preflight/SKILL.md · Verify Google Workspace MCP authentication at the start of any session that needs Google APIs (Docs, Slides, Drive)…
git:20260902.b370de6 · audit A · 302 stars
business skill
ai-analyst-lab/ai-analyst · .claude/skills/business/SKILL.md · Browse, search, and explore your organization's business context system — glossary terms, product catalog, metric…
git:20260902.b370de6 · audit A · 302 stars
causal skill
ai-analyst-lab/ai-analyst · .claude/skills/causal/SKILL.md · Causal inference toolkit for when experiments are not possible: estimate treatment effects from observational data with…
git:20260828.01c26bc · audit A · 302 stars
chart-to-drive skill
ai-analyst-lab/ai-analyst · .claude/skills/chart-to-drive/SKILL.md · Standardized workflow for uploading local chart PNGs to Google Drive and making them available for insertion into…
git:20260827.7ff2e25 · audit A · 302 stars
close-the-loop skill
ai-analyst-lab/ai-analyst · .claude/skills/close-the-loop/SKILL.md · Ensure every analysis that includes a recommendation ends with a clear, actionable follow-up plan. CRITICAL RULE - Only…
git:20260902.b370de6 · audit A · 302 stars
codex-review skill
ai-analyst-lab/ai-analyst · .claude/skills/codex-review/SKILL.md · Independently validate the current analysis with a second model (OpenAI Codex). Codex re-derives the same answer from…
git:20260902.b370de6 · audit A · 302 stars
compare-datasets skill
ai-analyst-lab/ai-analyst · .claude/skills/compare-datasets/SKILL.md · Compare metrics, findings, and patterns across two or more connected datasets. Helps identify cross-dataset patterns…
git:20260902.b370de6 · audit A · 302 stars

Every file in ai-analyst-lab/ai-analyst

Browse by kind, by grade A, or by owner.