bioinformatics

Gateway to 400+ genomics and computational biology skills.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/research/bioinformatics/SKILL.md

Quality

Content

50%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.

The skill is a well-structured, actionable gateway with concrete clone/read commands and clear sourcing, but it is held back by a very long inlined index that inflates token cost and by fetch/clone workflows that lack explicit validation checkpoints.

Suggestions

Move the full per-domain skill index into a separate reference file (e.g., references/SKILL_INDEX.md) and keep only a condensed summary plus a link in SKILL.md to improve conciseness and progressive disclosure.

Add validation checkpoints to the fetch workflow — e.g., verify the clone succeeded (`git clone ... && test -d`) and confirm prerequisites/installed tools before invoking a fetched ClawBio pipeline.

Trim redundant restatements (e.g., the 'NOT in Hermes SKILL.md format' caveat appears in both 'How to fetch' step 4 and 'Pitfalls'); consolidate to cut tokens.

Dimension	Reasoning	Score
Conciseness	The body inlines a ~200-line enumerated skill index listing hundreds of skill names across every domain; this large catalog duplicates information that lives in the linked repos and competes with the context window, matching the noticeably-verbose/padded anchor.	2 / 5
Actionability	It provides concrete, copy-pasteable commands (shallow clone URLs, cat paths to specific SKILL.md/README files, pip/R/apt/conda install blocks), with only minor gaps such as no example of actually selecting and running a fetched ClawBio skill end-to-end.	4 / 5
Workflow Clarity	The four-step fetch-and-use sequence is clearly numbered, but it involves batch/external operations (cloning repos, running third-party pipelines) with no validation checkpoints (e.g., verify the clone succeeded, confirm prerequisites before running), capping it at 3 per the destructive/batch rule.	3 / 5
Progressive Disclosure	It correctly acts as a gateway pointing one level deep to two external repos, but the huge inlined skill index is content that arguably belongs in a separate reference file, and the references are external URLs rather than well-signaled local bundle files.	3 / 5
	Total	12 / 20 Passed

Description

61%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.

The description clearly identifies a distinctive bioinformatics niche with strong trigger-term coverage, but it stays at a high-level gateway framing rather than enumerating concrete actions, and the explicit 'Use when...' guidance is in the body rather than the description field itself.

Suggestions

Add an explicit 'Use when...' clause inside the description field (e.g., 'Use when asked about genomics, variant calling, or single-cell analysis') so the trigger guidance is self-contained.

Replace the single gateway action with 2-3 concrete capabilities (e.g., 'Indexes and fetches on-demand reference guides and runnable analysis pipelines for genomics tasks').

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action ('Gateway to 400+ ... skills' / 'fetches what you need'), but the action is a single generic indexing gesture rather than a list of concrete capabilities, matching the anchor for domain-plus-1-2-actions-not-comprehensive.	3 / 5
Completeness	The 'what' ('Gateway to 400+ ... skills') is stated but the description field itself lacks an explicit 'Use when...' trigger clause; that guidance lives in the body instead, so per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	It surfaces many natural user-facing terms — 'bioinformatics, genomics, sequencing, variant calling, gene expression, single-cell analysis, protein structure, pharmacogenomics, metagenomics, phylogenetics' — giving good keyword coverage, though a few common synonyms or file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	The bioinformatics/computational-biology niche is highly specific and unlikely to conflict with unrelated skills, with only minor overlap risk against a generic 'biology' or 'data-analysis' skill.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
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	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/research/bioinformatics/SKILL.md
Commit: 48f69e5

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.