judge-llm-batch SKILL.md skillA
judge-llm-batch from enricai/leerie is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add enricai/leerie/judge-llm-batch@git:20260702.5a086ebPins git:20260702.5a086eb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- enricai/leerie
- Path
skills/judge-llm-batch/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260702.5a086eb, committed Jul 2, 2026
- First version recorded
- May 27, 2026
- Size
- 7,720 bytes
- Repository stars
- 10
- License
- MIT
Apply a 3-dimensional accuracy rubric (schema adherence, factual grounding, hallucination-freeness) to a batch of leerie LLM call captures and write verdict JSON. Used to measure whether a leerie worker (classifier, planner, implementer, etc.) is producing accurate output under its system-prompt contract.
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
<objective>
Read leerie LLM call captures from a `calls.ndjson` telemetry file (one
JSON object per line), filter by `call_type`, evaluate every sample against
a 3-dimensional rubric, and write a verdict JSON file.
The `calls.ndjson` file lives at `<state-root>/runs/<run-id>/calls.ndjson`,
where `<state-root>` is the resolved leerie state directory (default
`$HOME/.leerie/<basename>/`, overridable via `LEERIE_STATE_DIR` /
`--state-dir` / `leerie.toml state_dir`; `/leerie-state` inside the
container) — never a path relative to CWD.
Output shape:
```json
{
"call_type": "<from filter>",
"run_id": "<from file>",
"judged_at": "<ISO-8601>",
"judge_model": "claude-sonnet-4-6",
"verdicts": [
{
"call_id": "<UUID from the capture>",
"schema_ok": true,
"schema_rationale": "<one sentence>",
"factually_grounded": true,
"factual_rationale": "<one sentence>",
"hallucination_free": true,
"hallucination_rationale": "<one sentence>",
"pass": true,
"worst_offender": "<optional — 1-line quote when any dimension failed>"
}
],
"aggregate": {
"n": 0,
"schema_pass": 0,
"factual_pass": 0,
…Read the whole file at its exact version.
How to install
mdr add enricai/leerie/judge-llm-batch@sha256:0d10e9f855f3791bThe line at the top of this page pins the label git:20260702.5a086eb, 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_vnveip7apcdz3ccu)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 27, 2026 and Jul 2, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260702.5a086eb latest | 2026-07-02 | 5a086eb | 7,720 B | A | view · diff |
| git:20260602.08cf96f | 2026-06-02 | 08cf96f | 7,217 B | A | view · diff |
| git:20260528.75194ec | 2026-05-28 | 75194ec | 7,195 B | A | view · diff |
| git:20260527.fb717d9 | 2026-05-27 | fb717d9 | 7,239 B | A | view · diff |
| git:20260527.77d602b | 2026-05-27 | 77d602b | 7,274 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 (7720 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
enricai/leerie · 10 stars · license MIT · pushed 2026-10-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vnveip7apcdz3ccu GET https://markdownregistry.com/api/v1/resolve?ref=enricai/leerie/judge-llm-batch GET https://markdownregistry.com/api/v1/blob/0d10e9f855f3791b49c2de2feda73cc58927f0e676b532be6a28a89ed378151a
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.