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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bio/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 body is highly actionable with comprehensive executable examples, but it is verbose with duplicated content, lacks systematic workflow validation/feedback loops, and references a bundle file that is not present. Tightening redundancy and either bundling or removing the dangling reference would improve it.

Suggestions

De-duplicate the pLDDT/PAE threshold explanations into a single "Confidence Interpretation" section and trim the overlapping "Common Use Cases" to reduce token cost.

Either create references/api_reference.md and move the bulk API details there, or remove the reference pointer so inline content is the single source of truth.

Add explicit validation checkpoints (e.g., verify downloaded files are non-empty / parseable before downstream analysis) to batch and bulk-download workflows.

Dimension	Reasoning	Score
Conciseness	Content is mostly executable code, but it is padded: pLDDT/PAE thresholds are explained twice (section 3 and "Confidence Interpretation Guidelines"), "Common Use Cases" overlaps "When to Use", and the promotional K-Dense Web section adds noise; not level 1 because the bulk is actionable rather than conceptual fluff, not level 3 due to the redundancy.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code across Biopython, REST, Google Cloud, BigQuery, and structure parsing with concrete URLs and examples; matches the level-3 anchor and clearly above the pseudocode level 2.	3 / 3
Workflow Clarity	Capabilities are sequenced into numbered sections with some validation (isinstance taxonomy check, batch try/except), but it reads as a capability catalog rather than a guided workflow with systematic validation checkpoints and feedback loops; not level 1 because steps and some validation exist, not level 3 because no validate->fix->retry cycle is provided for batch/destructive operations.	2 / 3
Progressive Disclosure	The Resources section clearly signals references/api_reference.md and describes its contents, but no bundle file actually exists and substantial API-reference material remains inline in the body; not level 3 because referenced content is unbundled and the body is monolithic, not level 1 because a one-level reference is signaled.	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-triggered, and clearly distinguishable, but it omits an explicit "Use when..." trigger clause, capping completeness at 2. Adding explicit trigger guidance would raise the completeness dimension.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user needs AI-predicted protein structures, AlphaFold predictions, or per-residue confidence (pLDDT/PAE) analysis."

Consider adding common phrasings users say ("AlphaFold structure", "protein structure prediction") to further reinforce the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Retrieve structures by UniProt ID", "download PDB/mmCIF files", "analyze confidence metrics (pLDDT, PAE)" — matching the level-3 anchor for several specific actions; not level 2 because the actions are concrete rather than a single named domain.	3 / 3
Completeness	Clearly states what the skill does but provides no explicit "Use when..." trigger clause; "for drug discovery and structural biology" only implies when, so per the guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Includes natural terms a user would actually say — AlphaFold, protein structures, UniProt ID, PDB/mmCIF, pLDDT, PAE, drug discovery — giving good coverage; not level 2 because both common and domain-specific variations are present.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (AlphaFold DB protein-structure predictions) with distinct triggers unlikely to fire for unrelated skills; not level 2 because the AlphaFold-specific identifiers make overlap minimal.	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 (513 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/alphafold-database/SKILL.md
Commit: df37802

Reviewed: about 2 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.