llm-align SKILL.md skillA
llm-align from calibre-labs/reforge-ai-evals is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add calibre-labs/reforge-ai-evals/llm-align@git:20261016.c78dbc2Pins git:20261016.c78dbc2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- calibre-labs/reforge-ai-evals
- Path
skills/llm-align/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261016.c78dbc2, committed Oct 16, 2026
- First version recorded
- Oct 3, 2026
- Size
- 8,442 bytes
- Repository stars
- 94
- License
- MIT
Analyze alignment between LLM judge scores and human labels in an eval dataset. Use this skill whenever someone wants to evaluate how well an LLM judge agrees with human reviewers, calculate TPR/TNR, investigate disagreements, or improve a scorer prompt. Trigger on phrases like: "calculate TPR/TNR", "judge alignment", "where does the LLM disagree with humans", "improve my scorer", "why is the LLM getting these wrong", "compare human labels to LLM scores", "evaluate my eval", or any time…
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 Alignment Analysis You are helping analyze how well an LLM-based judge aligns with human labels in an eval dataset. Work through the five phases below in order, confirming with the user at each ambiguous step before proceeding. The methodology works regardless of eval platform (Braintrust, LangSmith, custom CSV/JSONL, or any other format). Phase 1 covers how to get the data you need from different sources. --- ## Phase 1: Discovery **Goal**: Figure out what score fields exist and which are human labels vs. LLM judge scores. ### Step 1 — Get the eval results Ask the user how their eval results are stored: **Option A — Local file (CSV or JSONL)** Read the file directly. Look for columns or fields that contain numeric or categorical scores. Common patterns: `human_score`, `llm_score`, `<judge_name>_score`, `label`, `rating`. **Option B — Eval platform (Braintrust, LangSmith, etc.)** Ask for the experiment/run ID or URL. Use the platform's API or MCP tools to fetch rows. You want: each row's input, the human label field, and the LLM judge score field. Typical Braintrust query (adapt syntax to other platforms): ``` select: id, span_id, scores …
Read the whole file at its exact version.
How to install
mdr add calibre-labs/reforge-ai-evals/llm-align@sha256:24891c8e2436c31aThe line at the top of this page pins the label git:20261016.c78dbc2, 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_tuehcw7zudo4qdup)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 3, 2026 and Oct 16, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261016.c78dbc2 latest | 2026-10-16 | c78dbc2 | 8,442 B | A | view · diff |
| git:20261003.9a39ab5 | 2026-10-03 | 9a39ab5 | 8,440 B | A | view |
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 (8442 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
calibre-labs/reforge-ai-evals · 94 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tuehcw7zudo4qdup GET https://markdownregistry.com/api/v1/resolve?ref=calibre-labs/reforge-ai-evals/llm-align GET https://markdownregistry.com/api/v1/blob/24891c8e2436c31a4a0046a7d12d2cb00a00ad66be101d193972438e828862f6
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.