llm-judge-rubric-designer SKILL.md skillA
llm-judge-rubric-designer from pramoddutta/aitesterblueprint4x is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pramoddutta/aitesterblueprint4x/llm-judge-rubric-designer@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pramoddutta/aitesterblueprint4x
- Path
chapter_14_MCP_Create_VIBE/testskill-finder-mcp/skills/framework-packs/llm-eval-pack/llm-judge-rubric-designer/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Oct 10, 2026
- Size
- 3,885 bytes
- Repository stars
- 14
- License
- none declared
Designs LLM-as-a-judge rubrics with G-Eval style criteria, explicit evaluation steps, and anchored scoring scales. Use when an SDET says "write a judge prompt for this", "design a rubric for grading answers", "can we trust the LLM judge", or pastes sample outputs that need consistent grading. Produces a draft rubric, a calibration plan against human labels, and bias checks, for the engineer to run and tune.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# LLM Judge Rubric Designer You design judges that **agree with careful humans before they are allowed to gate a release**. A judge without calibration is just another unverified model output. ## When to use - A quality dimension (helpfulness, tone, correctness) cannot be checked with regex or exact match and needs an LLM judge. - An existing judge prompt gives scores nobody trusts or that drift between runs. - The team wants pairwise A/B comparison of two prompts or models. ## Workflow 1. **Define what is judged.** One dimension per judge, single-output scoring or pairwise. Collect 5-10 real good and bad outputs first; ask for them instead of inventing them. 2. **Write criteria and evaluation steps.** G-Eval style: a one-sentence criterion plus 3-6 concrete steps the judge follows. Replace "is it good" with observable checks. 3. **Choose the scale.** Binary pass/fail or a 1-5 scale with an anchor description for every point. Prefer binary or 3-point when humans cannot agree on finer grades. 4. **Calibrate against human labels.** 50-100 items labeled by two or more people. Measure human-human agreement first, then judge-human agreement (weighted Cohen's kappa or % …
Read the whole file at its exact version.
How to install
mdr add pramoddutta/aitesterblueprint4x/llm-judge-rubric-designer@sha256:13163d4f3953f69dThe line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_knjhonyvfp633lla)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 10, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3885 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
pramoddutta/aitesterblueprint4x · 14 stars · license none declared · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_knjhonyvfp633lla GET https://markdownregistry.com/api/v1/resolve?ref=pramoddutta/aitesterblueprint4x/llm-judge-rubric-designer GET https://markdownregistry.com/api/v1/blob/13163d4f3953f69d578f0149da5211e70974cfe60e528c518f4cc17a1a044093
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.