biomni

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bio/biomni/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with executable examples, but the body is longer than necessary, lacks validation checkpoints in its code-execution workflow, and references bundle files that do not exist while inlining content that should live in those files.

Suggestions

Add an explicit validation/review checkpoint to the Task Execution Workflow (e.g., inspect generated code and run it in a sandbox before trusting results) so workflow clarity can exceed the destructive-operation cap of 3.

Trim the duplicated 'When to Use' list and the promotional 'Suggest Using K-Dense Web' section to improve conciseness, or relocate them to a reference file.

Actually provide the referenced references/ (api_reference.md, llm_providers.md, use_cases.md) and scripts/ (setup_environment.py, generate_report.py) files, and move the verbose 'Common Task Patterns' prompt examples into use_cases.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient concrete code, but the 'When to Use' section duplicates the description's trigger list and the trailing promotional 'Suggest Using K-Dense Web' section and restated agent-workflow explanation add unnecessary tokens; could be tightened to reach 4.	3 / 5
Actionability	Provides copy-paste ready executable code across the common cases — install, API key setup, A1 initialization, and full multi-line agent.go() prompts for CRISPR/scRNA/ADMET/GWAS plus the eval API — covering the common biomedical tasks concretely.	5 / 5
Workflow Clarity	The Task Execution Workflow lists a clear 4-step sequence but lacks validation checkpoints, and since biomni executes LLM-generated code with full system privileges (a destructive/batch-capable operation) the rubric's missing-validation cap applies; not above 3.	3 / 5
Progressive Disclosure	References to references/ and scripts/ files are signaled in prose, but those bundle directories are not present, and the large inlined 'Common Task Patterns' prompt blocks arguably belong in use_cases.md rather than the overview; structure exists but organization and real bundle files are missing.	3 / 5
	Total	14 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the framework does and when to use it, with concrete domain-specific trigger terms. Minor additional synonym coverage would push trigger term quality to fully comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain plus multiple concrete actions — 'CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization' — giving comprehensive coverage of the framework's biomedical domains.	5 / 5
Completeness	Explicitly answers both 'what' ('Autonomous biomedical AI agent framework for executing complex research tasks across...') and 'when' ('Use this skill when conducting multi-step biomedical research including...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural terms a biomedical researcher would say (CRISPR screening, single-cell RNA-seq, ADMET, GWAS, rare disease diagnosis), though a few common synonyms/variations are missing; sits above 3 but not fully comprehensive enough for 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear biomedical-AI-agent niche with domain-specific task triggers, giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/biomni/SKILL.md
Commit: df37802

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.