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.

1.38x

Quality

77%

Does it follow best practices?

Impact

69%

1.38x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/alphafold-database/SKILL.md

Evaluation results

53%

16%

Protein Target Reliability Assessment for Drug Discovery

Biopython structure retrieval and pLDDT confidence analysis

Criteria

Without context

With context

Biopython alphafold_db import

50%

get_predictions usage

download_cif_for usage

mmCIF format preference

100%

confidenceScore key

100%

pLDDT very high threshold

100%

pLDDT high threshold

100%

pLDDT low threshold

100%

B-factor pLDDT extraction

50%

uv pip install

100%

Confidence URL pattern

Version v4 in URLs

90%

23%

Domain Architecture Confidence Analysis for Protein Engineering

REST API access, AlphaFold ID format, and PAE matrix analysis

Criteria

Without context

With context

REST API endpoint

100%

entryId extraction

100%

AlphaFold ID format

100%

PAE URL pattern

77%

66%

PAE distance key

100%

PAE confident threshold

100%

PAE uncertain threshold

100%

viridis_r colormap

100%

PAE vmin/vmax range

100%

High-resolution save

100%

Version v4 suffix

75%

62%

PAE colorbar label

42%

65%

18%

High-Throughput Structural Confidence Profiling for Model Organism Proteins

Batch processing with rate limiting and local caching

Criteria

Without context

With context

Biopython batch retrieval

Rate limit: max concurrent

22%

55%

Rate limit: delay between requests

44%

Local file caching

100%

subprocess list form

100%

No shell=True

100%

uv pip install

50%

confidenceScore key

100%

pLDDT threshold classification

100%

Error handling per protein

100%

Version v4 in URLs

37%

Results summary output

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: 71add64

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Protein Target Reliability Assessment for Drug Discovery Domain Architecture Confidence Analysis for Protein Engineering High-Throughput Structural Confidence Profiling for Model Organism Proteins

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.