alphafold-database

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/alphafold-database/SKILL.md

Quality

Content

65%

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

The skill is highly actionable with executable code throughout, but it suffers from verbosity (redundant confidence and version sections) and a flat structure that over-inlines content a dedicated reference already provides, leaving workflow and disclosure at 2.

Suggestions

De-duplicate pLDDT/PAE threshold explanations — keep them in one place (e.g. 'Confidence Interpretation Guidelines') and reference it from section 3.

Move the bulk of REST/BigQuery/gsutil snippets into references/api_reference.md and keep SKILL.md to one concise quick-start example per capability.

Add explicit validation checkpoints for batch/bulk operations (e.g. check HTTP status, verify file integrity after gsutil cp) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and code-driven, but it pads the context with redundant material — pLDDT thresholds are explained in section 3 and again under 'Confidence Interpretation Guidelines', and version notes repeat across 'Key Concepts', 'Important Notes', and 'Additional Resources'.	2 / 3
Actionability	Every capability is backed by complete, executable Python/Bash snippets (Biopython retrieval, REST downloads, BigQuery queries, gsutil commands) that are copy-paste ready.	3 / 3
Workflow Clarity	The numbered capabilities are parallel tasks rather than a sequenced pipeline, and although batch processing has a try/except, there are no explicit validation checkpoints (e.g. verifying downloads or checking HTTP status) for the bulk/batch operations the rubric flags as needing feedback loops.	2 / 3
Progressive Disclosure	A one-level reference (references/api_reference.md) is correctly signaled, but a large amount of inline detail — full REST/BigQuery/gsutil examples and a duplicated API surface — duplicates material that the reference already covers and could be split out.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, well-populated with natural trigger terms, and distinct, but it omits an explicit 'Use when...' guidance clause, capping completeness at 2.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when retrieving AI-predicted protein structures, downloading PDB/mmCIF files, or analyzing pLDDT/PAE confidence metrics.'

Trim the trailing 'for drug discovery and structural biology' which reads more as marketing framing than a trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE)' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but lacks any explicit 'Use when...' trigger clause; per the rubric a missing use-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Covers natural user-facing terms ('protein structures', 'UniProt ID', 'PDB/mmCIF', 'pLDDT', 'PAE', 'drug discovery') that a user would actually say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The AlphaFold-specific identifiers (UniProt ID, pLDDT, PAE, mmCIF) give it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (519 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/alphafold-database/SKILL.md
Commit: 52845c3

Reviewed: about 11 hours 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.