genomic-intelligence

Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer activity, chromatin state, sequence-to-expression (log TPM), and de-novo gene annotation, plus a composite find-genes-then-predict-expression workflow. Use when the user has a gene symbol, a genomic region, or a DNA/FASTA sequence and wants any of these predictions, mentions Genomic Intelligence, genomicintelligence.ai, api.genomicintelligence.ai, or mcp.genomicintelligence.ai.

Quality

85%

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

The canonical home for this skill is genomic-intelligence in K-Dense-AI/scientific-agent-skills

Quality

Content

78%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.

A thorough, actionable skill body with executable REST and MCP examples and well-structured one-level-deep references. The main weakness is conciseness: the strict expression/tss_index contract is repeated across multiple sections and inline version stamps, which inflates tokens without adding proportional clarity.

Suggestions

Consolidate the expression/tss_index rules into a single section; the table row, prose block, and blockquote all restate the same 9,198 bp / tss_index constraints — keep one authoritative statement and cross-reference it.

Move the OpenAPI version stamps (2026.08.20.7, 2026.09.10.1) into a single 'Contract version' line or a references file so the body stays version-neutral and easier to maintain.

Promote the async and composite steps into a short numbered checklist with explicit validation gates (e.g. 'assert scored_window == [.., 9198] before trusting the result') so checkpoints are visible at a glance.

Dimension	Reasoning	Score
Conciseness	The body is dense and high-signal but the expression/tss_index rules are restated across the task table, a dedicated prose section, a blockquote, and code comments, and inline version stamps (2026.08.20.7, 2026.09.10.1) add time-sensitive detail that could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready Python (a complete predict() helper with auth/headers, an async polling loop) and concrete MCP tool-call signatures cover the common promoter and expression cases end to end.	5 / 5
Workflow Clarity	Acquire-then-predict and submit-then-poll sequences are clear with explicit validation (assert on meta.task_specific_counts.scored_window, genes_predicted + genes_skipped == genes_found) and error-recovery guidance (429 backoff, 413 retry as async), but checkpoints are woven through prose rather than presented as a crisp gated checklist.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with clearly signaled, one-level-deep references to four real bundle files (tasks.md, api-and-auth.md, mcp.md, sequence-acquisition.md), each mapped to a topic; navigation is easy and no nesting goes deeper than one level.	5 / 5
	Total	17 / 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 states concrete capabilities, names the access paths, and gives explicit 'Use when...' trigger guidance tied to user inputs and brand mentions. Slight room to surface a few more natural synonyms directly in the prose rather than only in metadata keywords.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'promoter regions, splice donor/acceptor sites, enhancer activity, chromatin state, sequence-to-expression (log TPM), and de-novo gene annotation, plus a composite find-genes-then-predict-expression workflow' — covering the full capability surface comprehensively.	5 / 5
Completeness	Explicitly answers both what ('Predict regulatory features, gene structure, and expression directly from DNA sequence...') and when ('Use when the user has a gene symbol, a genomic region, or a DNA/FASTA sequence and wants any of these predictions, mentions Genomic Intelligence...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage including 'gene symbol', 'genomic region', 'DNA/FASTA sequence', and the six task names plus brand/URL triggers, though a few common user phrasings (e.g. 'DNA sequence prediction', 'regulatory genomics') live only in metadata, not the description itself.	4 / 5
Distinctiveness Conflict Risk	Clear niche (hosted transformer DNA language models over REST/MCP) anchored to brand-specific triggers (Genomic Intelligence, genomicintelligence.ai, mcp.genomicintelligence.ai), 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_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/genomic-intelligence/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.