How do I install the Alphafold Database skill?

Run npx skillmds@latest add ai4protein/alphafold-database in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Alphafold Database safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Alphafold Database?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Alphafold Database free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Unknown.

Who published Alphafold Database?

ai4protein (@ai4protein) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Alphafold Database by ai4protein — Agent Skill

Name: Alphafold Database
Author: ai4protein

Alphafold Database

AlphaFold DB structures and confidence analytics via VenusFactory tools. Use when the user needs predicted structures by UniProt ID, pLDDT/PAE analysis, or PDB/mmCIF download. Do NOT use for experimental PDB (rcsb_database), local ESMFold without UniProt (predict_structure_esmfold / protein_structure_pipeline), or sequence annotation (uniprot_database).

ai4protein 9c5a157 3 files · 34.3 KB Updated Sep 17, 2026

File contents

AlphaFold Database

Overview

Download AlphaFold predictions to disk and analyze confidence locally. Default model version is v6. Large coordinate files must stay on disk — never paste PDB into chat.

VenusFactory execution

Call hub tools by exact name. Extended Biopython/GCP examples: read_skill(..., relative_path="references/legacy_guide.md") or references/api_reference.md.

Project Tools (VenusFactory2)

Tool	Args	Returns	Description
download_alphafold_structure_by_uniprot_id	`uniprot_id`, `out_dir`, `format` (`pdb`\|`cif`, default pdb), `version` (default `v6`), `fragment`	rich JSON `status` + `file_info`	Structure file
download_alphafold_metadata_by_uniprot_id	`uniprot_id`, `out_dir`	rich JSON + metadata JSON path	Prediction metadata
analyze_alphafold_plddt_by_metadata_file	`metadata_path`	pLDDT fractions + verdict	Local analysis
analyze_alphafold_pae_by_pae_file	`pae_path`, optional cutoffs	domains + PAE stats	Local analysis

There is no dedicated PAE download @tool. Obtain PAE via metadata paeDocUrl + agent_generated_code, then analyze.

Recommended workflow

download_alphafold_metadata_by_uniprot_id → analyze_alphafold_plddt_by_metadata_file
download_alphafold_structure_by_uniprot_id for coordinates
Optional PAE download → analyze_alphafold_pae_by_pae_file
Optional render_protein_structure / figure step for pLDDT plot

When NOT to use

Experimental structure → rcsb_database
No UniProt, only raw sequence → predict_structure_esmfold
Full engineering pipeline → protein_structure_pipeline

Common mistakes

Assuming return shape is {success, file_path} — use status + file_info.file_path
Using v4 URLs while tools default to v6
Feeding structure PDB into the pLDDT analyzer (needs metadata JSON)
Dumping coordinates into the conversation

References

references/api_reference.md — REST/URL details
references/legacy_guide.md — archived tutorials (Biopython, GCP bulk)

---name: alphafold-databasedescription: AlphaFold DB structures and confidence analytics via VenusFactory tools. Use when the user needs predicted structures by UniProt ID, pLDDT/PAE analysis, or PDB/mmCIF download. Do NOT use for experimental PDB (rcsb_database), local ESMFold without UniProt (predict_structure_esmfold / protein_structure_pipeline), or sequence annotation (uniprot_database).license: Unknown---# AlphaFold Database## OverviewDownload AlphaFold predictions to disk and analyze confidence locally. Default model version is **v6**. Large coordinate files must stay on disk — never paste PDB into chat.## VenusFactory executionCall hub tools by exact name. Extended Biopython/GCP examples: `read_skill(..., relative_path="references/legacy_guide.md")` or `references/api_reference.md`.## Project Tools (VenusFactory2)| Tool | Args | Returns | Description ||------|------|---------|-------------|| **download_alphafold_structure_by_uniprot_id** | `uniprot_id`, `out_dir`, `format` (`pdb`\|`cif`, default pdb), `version` (default `v6`), `fragment` | rich JSON `status` + `file_info` | Structure file || **download_alphafold_metadata_by_uniprot_id** | `uniprot_id`, `out_dir` | rich JSON + metadata JSON path | Prediction metadata || **analyze_alphafold_plddt_by_metadata_file** | `metadata_path` | pLDDT fractions + verdict | Local analysis || **analyze_alphafold_pae_by_pae_file** | `pae_path`, optional cutoffs | domains + PAE stats | Local analysis |There is **no** dedicated PAE download `@tool`. Obtain PAE via metadata `paeDocUrl` + `agent_generated_code`, then analyze.## Recommended workflow1. `download_alphafold_metadata_by_uniprot_id` → `analyze_alphafold_plddt_by_metadata_file`2. `download_alphafold_structure_by_uniprot_id` for coordinates3. Optional PAE download → `analyze_alphafold_pae_by_pae_file`4. Optional `render_protein_structure` / figure step for pLDDT plot## When NOT to use- Experimental structure → `rcsb_database`- No UniProt, only raw sequence → `predict_structure_esmfold`- Full engineering pipeline → `protein_structure_pipeline`## Common mistakes- Assuming return shape is `{success, file_path}` — use `status` + `file_info.file_path`- Using v4 URLs while tools default to **v6**- Feeding structure PDB into the pLDDT analyzer (needs **metadata JSON**)- Dumping coordinates into the conversation## References- `references/api_reference.md` — REST/URL details- `references/legacy_guide.md` — archived tutorials (Biopython, GCP bulk)

Frequently asked questions