ai-scientist-evaluator SKILL.md skillA
ai-scientist-evaluator from fmschulz/omics-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fmschulz/omics-skills/ai-scientist-evaluator@git:20261001.bf5afd6Pins git:20261001.bf5afd6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fmschulz/omics-skills
- Path
skills/ai-scientist-evaluator/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261001.bf5afd6, committed Oct 1, 2026
- First version recorded
- Jul 11, 2026
- Size
- 9,366 bytes
- Repository stars
- 11
- License
- MIT
Score finished AI-generated biology or bioinformatics work against its task and required artifacts. Use when auditing or ranking AI scientist submissions for task completion, scientific validity, and reproducibility.
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
# AI Scientist Evaluator Act as a skeptical reviewer panel, not a research generator. Evaluate completed outputs, not plans. ## Instructions 1. Confirm the request is evaluative. Use this skill to audit or compare existing outputs, not to perform the original research task. 2. Restate the exact task in one or two sentences so the review stays anchored to the real objective and required deliverables. 3. Inventory the submitted artifacts and note what is missing. Prefer primary artifacts over summaries: - notebooks, code, scripts, and workflow files - environment files, package versions, and runtime logs - figures, tables, and manuscript drafts - data provenance, accession lists, database versions, and citations - benchmark results, hardware notes, and task constraints 4. Choose the closest task profile from [`references/task_profiles.md`](references/task_profiles.md) and load the matching weights from [`assets/default_weight_profiles.yaml`](assets/default_weight_profiles.yaml). Use the primary scientific profile first for composite tasks, then add manuscript comments as a secondary layer. …
Read the whole file at its exact version.
How to install
mdr add fmschulz/omics-skills/ai-scientist-evaluator@sha256:51692c5f8d4f2893The line at the top of this page pins the label git:20261001.bf5afd6, 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_zhpdh3q4bjarjq7w)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 11, 2026 and Oct 1, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261001.bf5afd6 latest | 2026-10-01 | bf5afd6 | 9,366 B | A | view · diff |
| git:20260905.3e49039 | 2026-09-05 | 3e49039 | 9,796 B | A | view · diff |
| git:20260825.bd47e68 | 2026-08-25 | bd47e68 | 9,808 B | A | view · diff |
| git:20260807.4acaed9 | 2026-08-07 | 4acaed9 | 9,743 B | A | view · diff |
| git:20260712.3675171 | 2026-07-12 | 3675171 | 9,633 B | A | view · diff |
| git:20260711.5ae6f6f | 2026-07-11 | 5ae6f6f | 9,405 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 (9366 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
fmschulz/omics-skills · 11 stars · license MIT · pushed 2026-10-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zhpdh3q4bjarjq7w GET https://markdownregistry.com/api/v1/resolve?ref=fmschulz/omics-skills/ai-scientist-evaluator GET https://markdownregistry.com/api/v1/blob/51692c5f8d4f289320afe0842b7e3480dbee2eaa4246d3b22ce60289cfe2c451
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.