verification-rubric SKILL.md skillA
verification-rubric from metraton/gaia is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add metraton/gaia/verification-rubric@git:20260923.bbc2f09Pins git:20260923.bbc2f09 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- metraton/gaia
- Path
skills/verification-rubric/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260923.bbc2f09, committed Sep 23, 2026
- First version recorded
- Jul 22, 2026
- Size
- 6,872 bytes
- Repository stars
- 4
- License
- MIT
Use when judging a task_gates entry whose verification_type is semantic or self_review -- reading the gate's evidence_shape as an explicit rubric, assessing the produced work against each stated criterion, and emitting a justified pass/fail verdict. Loaded by the verifier role for judgment-based gates.
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
# Verification Rubric Verification-rubric is the judging discipline for a `task_gates` entry whose `verification_type` is `semantic` or `self_review`: it reads the gate's `evidence_shape` as an explicit rubric, assesses the produced work against each stated criterion independently, and emits a structured, justified pass/fail verdict -- never a hollow "looks fine." It is the judgment-based counterpart to the deterministic-oracle mode, which re-runs a `command`/`code` gate and diffs the result; there is no command to re-run here, only evidence to weigh against criteria. ## Core principle Two of the four `verification_type` values (`gaia.state.VALID_VERIFICATION_TYPES`, `gaia/state/__init__.py`) route to this skill: **`semantic`** (`evidence_shape` carries an externally authored rubric -- the contract-envelope's own `requires_human` marker names the same discipline: "needs human/rubric validation") and **`self_review`** (`evidence_shape` is the producer's own statement of what it checked -- the envelope's `reviewed` field is the same idea, and it is the honesty-rule floor from `agent-protocol`, not a shortcut around it). Both are LLM-as-judge tasks, not code execution. …
Read the whole file at its exact version.
How to install
mdr add metraton/gaia/verification-rubric@sha256:d8e4f71eccac9ed1The line at the top of this page pins the label git:20260923.bbc2f09, 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_6xd23u22kabjhzaw)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 22, 2026 and Sep 23, 2026, about one every 31 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.bbc2f09 latest | 2026-09-23 | bbc2f09 | 6,872 B | A | view · diff |
| git:20260915.e888e07 | 2026-09-15 | e888e07 | 6,344 B | A | view · diff |
| git:20260722.268971e | 2026-07-22 | 268971e | 6,213 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 (6872 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
metraton/gaia · 4 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6xd23u22kabjhzaw GET https://markdownregistry.com/api/v1/resolve?ref=metraton/gaia/verification-rubric GET https://markdownregistry.com/api/v1/blob/d8e4f71eccac9ed1c18805fdd34a27cfa3365169f0e3178cca1eb2ed26725dc6
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.