CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 is actionable and well-sequenced at the top level, anchored by an executable wrapper script. It is held back by verbose interpretive prose, validation steps that are delegated to the script rather than surfaced as explicit checkpoints, and an orphaned citation.bib reference file that is never linked from the body.

Suggestions

Tighten the 'Interpret and Report Results' metric explanations to just the formula and the one-line use-case trigger, dropping the pedagogical justification of gap behavior that Claude already knows.

Add an explicit verification checkpoint after the alignment step (e.g. 'Confirm the output file is non-empty and contains the expected number of aligned sequences before interpreting') and a short error-recovery note for job failures.

Link references/citation.bib from the body (e.g. in the References section) or move the detailed metric/feature-mapping guidance into a separate reference file referenced one level deep, so the overview stays lean.

DimensionReasoningScore

Conciseness

The 'Interpret and Report Results' section explains identity-metric mechanics at length (e.g. 'This is the most conservative metric; it penalizes for all gaps (indels) introduced by any sequence in the MSA') — domain knowledge a competent Claude largely already has, so the prose could be tightened while keeping the denominator-choice guidance.

2 / 3

Actionability

Provides a fully executable command ('uv run scripts/msa_align.py <INPUT_FASTA> -o <OUTPUT_FILE>'), a concrete FASTA example, and explicit flags ('Always specify the output file with -o or --output'), making the core task copy-paste ready.

3 / 3

Workflow Clarity

Steps are clearly sequenced (prepare input → execute → interpret), but validation checkpoints are implicit — input/size/count checks live inside the script and the body has no 'verify the output alignment before interpreting' step or error-recovery loop, fitting the 'sequence present but checkpoints missing or implicit' anchor.

2 / 3

Progressive Disclosure

The script is clearly signaled and present, but references/citation.bib exists in the bundle without being referenced or linked from the body, and the lengthy metric/feature-mapping guidance is inline rather than split into a one-level-deep reference — matching 'references present but not clearly signaled; content that should be separate is inline'.

2 / 3

Total

9

/

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.

A strong, well-structured description: it states a concrete capability, gives an explicit 'Use when' trigger, and carves out a distinct niche with clear negative boundaries against overlapping tools. Trigger terms are natural and the capacity limits add useful specificity without padding.

DimensionReasoningScore

Specificity

Names the concrete action (protein MSA via EBI Clustal Omega) and multiple specific purposes — 'assess similarity, domain conservation, or key residue conservation' — plus explicit capacity constraints (4000 sequences, 4 MB), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Performs multiple sequence alignment of proteins with EBI Clustal Omega') and when ('Use when you need to align multiple sequences...'), with an explicit 'Do not use' exclusion clause, so both halves are present and explicit.

3 / 3

Trigger Term Quality

Uses natural bioinformatics terms a user would say — 'align multiple sequences', 'similarity', 'domain conservation', 'homologous proteins', 'BLAST', 'MMseqs2' — giving good coverage of natural trigger phrasing.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (protein MSA) and actively disambiguates from adjacent tools — routing homology search to MMseqs2/BLAST and structural alignment to Foldseek/PyMOL — making a wrong-skill trigger unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
google-deepmind/science-skills
Reviewed

Table of Contents

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.