protein-sequence-similarity-search

Searches for homologous protein sequences using MMseqs2 (fast, default) or BLAST (comprehensive, fallback). Trigger this whenever the user provides a protein sequence or FASTA file and asks to find homologues, sequence matches, or wants to infer protein function based on sequence similarity, but not when the user wants to infer protein function based on structural similarity.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%Weight 40%Scale 1-3

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

The body delivers a clean, executable workflow with explicit validation checkpoints and well-organized one-level-deep references to real bundle scripts. The inline BLAST database table is justified as the per-run validation allowlist rather than misplaced reference content.

Dimension	Reasoning	Score
Conciseness	The body is lean and task-focused with executable commands, code blocks, and metric definitions, with no basic-concept padding; the long BLAST database listing is necessary allowlist data rather than filler.	3 / 3
Actionability	Provides fully executable `uv run scripts/mmseqs2_search.py` and `uniprot_blast.py` invocations with concrete flags, file-name conventions, and exit-code-driven fallback, all copy-paste ready.	3 / 3
Workflow Clarity	Path A / Path B / Common Steps are clearly sequenced with explicit validation checkpoints (exit code 2 fallback, strict BLAST database-code validation with 'do not proceed'), plus error/no-hits recovery guidance.	3 / 3
Progressive Disclosure	SKILL.md acts as an overview pointing to two real one-level-deep script bundles (scripts/mmseqs2_search.py, scripts/uniprot_blast.py, both present), with clearly signaled invocation rather than monolithic inline implementation.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 is third-person, concise, and covers specific capabilities, natural trigger terms, both what-and-when, and a clear distinctiveness boundary. It follows the strong example pattern with an explicit trigger clause and a negative-scope disambiguator.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Searches for homologous protein sequences using MMseqs2 (fast, default) or BLAST (comprehensive, fallback)') with named tools and the infer-function-by-similarity action, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (search homologues via MMseqs2/BLAST) and when ('Trigger this whenever the user provides a protein sequence or FASTA file and asks to find homologues...'), plus a negative-scope clause, matching the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Natural user-facing terms appear throughout ('protein sequence', 'FASTA file', 'find homologues', 'sequence matches'), covering the phrasings a user would actually say when requesting this skill.	3 / 3
Distinctiveness Conflict Risk	A clear protein-sequence-similarity niche with distinct triggers, plus an explicit exclusion ('but not when the user wants to infer protein function based on structural similarity') that reduces conflict with a structural-similarity skill.	3 / 3
	Total	12 / 12 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_similarity_search/SKILL.md
Commit: 0b42509

Reviewed: 8 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.