protein-sequence-msa

Performs multiple sequence alignment of proteins with EBI Clustal Omega. Use when you need to align multiple sequences to assess similarity, domain conservation, or key residue conservation. Supports up to 4000 sequences and a maximum file size of 4 MB. Do not use to search for homologous proteins in a database (use MMseqs2, BLAST), align non-protein sequences (DNA, RNA), perform structural alignment (use Foldseek, PyMOL), or if you only have a single sequence.

Quality

80%

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

Quality

Content

68%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 body is well-organized and actionable with a concrete execution path, but it lacks an explicit validation step confirming the remote alignment ran successfully, which caps workflow clarity. Progressive disclosure is good though an unused bundle file is not navigated to.

Suggestions

Add an explicit validation checkpoint after running the alignment (e.g., verify the output file exists, is non-empty, and contains expected alignment rows before interpreting), with a retry/error path if the EBI job fails or is still queued.

Link references/citation.bib from the body (e.g., a 'Citations' line under References) so the bundled file is discoverable and navigation is one level deep.

Consider moving the detailed identity-metric formulas into a separate reference file with a brief inline summary, to reduce body length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly lean with an executable command and a compact FASTA example, and it assumes Claude's intelligence rather than explaining what MSA is; only minor tightening possible, so it sits just below the 5 'every token earns its place' anchor.	4 / 5
Actionability	Provides a concrete copy-paste command ('uv run scripts/msa_align.py <INPUT_FASTA> -o <OUTPUT_FILE>') and a real FASTA example, but the interpretation/metrics section is guidance rather than executable code, leaving minor gaps versus the 5 anchor.	4 / 5
Workflow Clarity	Steps are clearly numbered (Prepare Input -> Execute Alignment -> Interpret and Report) but there is no explicit validation checkpoint that the remote alignment job succeeded or completed; for a remote batch API this absence caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Clean sectioned overview (Prerequisites, Core Rules, Goal, Instructions, References) pointing to a real script (scripts/msa_align.py), but references/citation.bib is never linked from the body and interpretation detail is inlined rather than split, leaving minor organization gaps.	4 / 5
	Total	15 / 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.

This is a strong, well-targeted description: concrete actions, explicit triggers, and clear negative-boundary guidance that distinguishes it from neighbor skills. The only minor gap is trigger-term synonyms and file extensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('assess similarity, domain conservation, or key residue conservation') and names the concrete tool (EBI Clustal Omega) plus hard limits (4000 sequences, 4 MB), giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly states both what ('Performs multiple sequence alignment of proteins with EBI Clustal Omega') and when ('Use when you need to align multiple sequences to assess similarity...'), with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('align multiple sequences', 'similarity', 'domain conservation', 'key residue conservation'), but misses common synonyms/extensions like 'homologs', 'MSA', or FASTA/.faa file extensions that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (protein MSA via Clustal Omega) reinforced by explicit 'Do not use to...' exclusions (MMseqs2/BLAST for homolog search, DNA/RNA, structural alignment, single sequence) minimizes conflict with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/protein_sequence_msa/SKILL.md
Commit: 6883275

Reviewed: 4 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.