alphafold-database-fetch-and-analyze

Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.

Quality

90%

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

88%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 well-structured, actionable skill body with executable commands and explicit validation/warning checkpoints throughout the workflow. Minor conciseness trims and an explicit pointer to references/citation.bib would polish it further.

Suggestions

Trim the per-script descriptive sentences that restate script output (e.g. 'Reads pLDDT confidence metrics... prints a heuristic confidence assessment') to tighten the body.

Add a brief pointer to references/citation.bib (e.g. in Prerequisites or a Citations section) so the bundled reference file is discoverable from the body.

Consider noting the rate-limit value or behavior inline so users know what 'graceful' enforcement means without reading the script.

Dimension	Reasoning	Score
Conciseness	Lean and mostly efficient — executable examples and rules without teaching basic concepts — though a few descriptive sentences restating what each script reads/prints slightly overlap the script's own output and could be trimmed.	4 / 5
Actionability	Copy-paste-ready bash commands with concrete UniProt IDs and explicit -o path guidance ('uv run scripts/fetch_structure.py P00520 -o /path/to/output/'), covering the common fetch and analyze cases with specific flags.	5 / 5
Workflow Clarity	Clear prerequisite → fetch → analyze-pLDDT → analyze-PAE → synthesize sequence with explicit mandatory checkpoints: '[!] WARNING' lines, isoform/large-protein (>2700 AAs) checks, and a prominent disorder warning that gates downstream analysis.	5 / 5
Progressive Disclosure	Well-organized sections with scripts referenced by one-level-deep paths (scripts/fetch_structure.py, etc.) backed by real bundle files; references/citation.bib is not explicitly linked from the body, a minor organization gap.	4 / 5
	Total	18 / 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 precise, well-scoped description that states concrete capabilities, an explicit trigger, and a clear negative-trigger guardrail. Minor keyword synonym coverage (.cif, PAE) could be added but the core trigger guidance is excellent.

Suggestions

Consider mentioning 'PAE matrix' or '.cif' as additional natural trigger terms to broaden keyword coverage.

Optionally note the AlphaFold Database / EBI source explicitly in the description to aid discovery phrasing.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Retrieve and analyze AlphaFold predicted structures', 'structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment' — covering fetch plus several analysis modes comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (retrieve and analyze AlphaFold structures) and 'when' (Use when the user provides a specific UniProt Accession ID and wants pLDDT/domain/disorder), with a concrete negative trigger for missing input.	5 / 5
Trigger Term Quality	Strong natural terms ('UniProt Accession ID', 'pLDDT', 'domain boundary analysis', 'disorder assessment') that users of this skill would say, though a few synonyms/file extensions (.cif, PAE matrix, AlphaFold DB) are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (AlphaFold DB fetch + structural analysis by UniProt ID) reinforced by an explicit 'Do not use if... — ask for a UniProt ID first' guardrail, minimizing overlap with Foldseek/PDB/custom-prediction 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/alphafold_database_fetch_and_analyze/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.