New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Input Preparation

by VectorSpaceLab in VectorSpaceLab/AREX-Skill

Build, validate, convert, and troubleshoot AlphaFold 3 input JSON files before prediction runs.

Apache-2.0Auto-check passedResearch & Science

Install Input Preparation

skills CLI
$ npx skills add VectorSpaceLab/AREX-Skill --skill input-preparation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install VectorSpaceLab/AREX-Skill input-preparation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/alphafold3/sub-skills/input-preparation .claude/skills/input-preparation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
input-preparation
GitHub stars
328
Token cost
~619 tokens
SKILL.md length
246 words
Files
4 (incl. scripts, references)
Skills in repo
157
Repo updated
First seen
Licence
Apache-2.0

At a glance

Build, validate, convert, and troubleshoot AlphaFold 3 input JSON files before prediction runs.

  • Works in 5 steps: Draft the input with dialect:… → Keep one prediction job per AlphaFold 3… → Ensure every sequence entity has an… → …
  • Creating fold inputs
  • SKILL.md covers Route here for, Do not handle here, Fast workflow and Key references
  • Runs Python scripts from its folder; calls python

What it does

Input Preparation is an agent skill from VectorSpaceLab/AREX-Skill. Build, validate, convert, and troubleshoot AlphaFold 3 input JSON files before prediction runs. Use when creating fold inputs, validating protein/RNA/DNA/ligand entries, converting AlphaFold Server JSON, adding MSAs/templates/user CCD/bonds, or explaining schema versions.

Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/input-json.md`, `references/troubleshooting.md` and `scripts/validate_fold_input.py`).

It sits in Research & Science, covering Protein structure and design. It works with AlphaFold. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.

When your agent uses it

  • Creating fold inputs
  • Validating protein/RNA/DNA/ligand entries
  • Converting AlphaFold Server JSON
  • Adding MSAs/templates/user CCD/bonds

Example prompts

  • “/input-preparation”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Draft the input with dialect: "alphafold3" and version: 4 unless compatibility with an older saved input is required.
  2. Keep one prediction job per AlphaFold 3 JSON file. Use a top-level list only for AlphaFold Server JSON that will be converted.
  3. Ensure every sequence entity has an uppercase alphabetic id; use a list of IDs only for identical copies.
  4. Prefer explicit path fields for external content: unpairedMsaPath, pairedMsaPath, mmcifPath, and userCCDPath.
  5. Validate before running prediction

What it can do on your machine

Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Input Preparation loads about 619 tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 246 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~619
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its Apache-2.0 licence (© VectorSpaceLab). 246 words, ~619 tokens.

Download SKILL.mdSave it as .claude/skills/input-preparation/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
input-preparation
description
Build, validate, convert, and troubleshoot AlphaFold 3 input JSON files before prediction runs. Use when creating fold inputs, validating protein/RNA/DNA/ligand entries, converting AlphaFold Server JSON, adding MSAs/templates/user CCD/bonds, or explaining schema versions.
disable-model-invocation
true
metadata.disco-role
operating
license
Apache 2.0

AlphaFold 3 Input Preparation

Use this sub-skill when the task is about constructing or checking AlphaFold 3 fold-input JSON, not about running inference or interpreting outputs.

Route here for

  • Creating alphafold3 dialect JSON files with name, modelSeeds, sequences, dialect, and version.
  • Validating protein, RNA, DNA, ligand, ion, MSA, template, userCCD, userCCDPath, and bondedAtomPairs fields.
  • Converting AlphaFold Server-style fold jobs into AlphaFold 3 inputs and explaining conversion limits.
  • Debugging Input.from_json(...) errors before invoking a prediction run.
  • Checking path-relative external files such as unpairedMsaPath, pairedMsaPath, mmcifPath, and userCCDPath.

Do not handle here

  • Runtime database, model, GPU, bucket, or inference flags; route to ../running-predictions/.
  • Confidence JSON, ranking scores, mmCIF output, or result interpretation; route to ../output-interpretation/.
  • Lower-level model runner, data pipeline, or Python API integration beyond input parsing; route to ../python-apis/.

Fast workflow

  1. Draft the input with dialect: "alphafold3" and version: 4 unless compatibility with an older saved input is required.
  2. Keep one prediction job per AlphaFold 3 JSON file. Use a top-level list only for AlphaFold Server JSON that will be converted.
  3. Ensure every sequence entity has an uppercase alphabetic id; use a list of IDs only for identical copies.
  4. Prefer explicit path fields for external content: unpairedMsaPath, pairedMsaPath, mmcifPath, and userCCDPath.
  5. Validate before running prediction:
bash
python sub-skills/input-preparation/scripts/validate_fold_input.py fold_input.json

Key references

  • references/input-json.md covers schema recipes, entity fields, conversion constraints, relative paths, and validation rules.
  • references/troubleshooting.md maps common parser and preparation failures to fixes.
  • scripts/validate_fold_input.py provides a safe local parser check using the installed AlphaFold 3 package.

© VectorSpaceLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/repositories/repo-skills/alphafold3/sub-skills/input-preparation of VectorSpaceLab/AREX-Skill.

  • SKILL.md
  • references/input-json.md
  • references/troubleshooting.md
  • scripts/validate_fold_input.py

Open the folder on GitHubat commit ac3fe1a

Compare with similar skills

Input Preparation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Input Preparation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Input Preparation this skillVectorSpaceLab/AREX-Skill328—~619Automated safety check: PassApache-2.0
Alphafold Database Fetch And Analyzegoogle-deepmind/science-skills3.2k2 repos~1.2kAutomated safety check: PassApache-2.0
Alphafoldadaptyvbio/protein-design-skills1634 repos~1.2kAutomated safety check: PassMIT
Chaiadaptyvbio/protein-design-skills1634 repos~1.5kAutomated safety check: PassMIT
Biopipelineslocbp-uzh/biopipelines109—~2.4kAutomated safety check: PassMIT
Rfdiffusionadaptyvbio/protein-design-skills1634 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • Alphafold Database Fetch And Analyze

    google-deepmind/science-skills

    Retrieve and analyze AlphaFold predicted structures for a protein.

    3.2k GitHub starsUsed in 2 repos~1.2k tokens
    Research & ScienceAuto-check passed

  • Alphafold

    adaptyvbio/protein-design-skills

    Validate protein designs using AlphaFold2 structure prediction.

    163 GitHub starsUsed in 4 repos~1.2k tokens
    Research & ScienceAuto-check passed

  • Chai

    adaptyvbio/protein-design-skills

    Structure prediction using Chai-1, a foundation model for molecular structure.

    163 GitHub starsUsed in 4 repos~1.5k tokens
    Research & ScienceAuto-check passed

  • Biopipelines

    locbp-uzh/biopipelines

    Design and run computational protein and ligand workflows on a GPU: binder and enzyme design, de novo backbone generation, inverse folding and sequence redesign, structure prediction, protein-ligand…

    109 GitHub stars~2.4k tokensUpdated 8 days ago
    Research & ScienceAuto-check passed

  • Rfdiffusion

    adaptyvbio/protein-design-skills

    Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generation.

    163 GitHub starsUsed in 4 repos~2.3k tokens
    Research & ScienceAuto-check passed

  • Bio DB Tools

    DrugClaw/DrugClaw

    Query public biology databases and APIs including UniProt, RCSB PDB, AlphaFold DB, ClinVar, dbSNP, gnomAD, Ensembl, GEO, InterPro, KEGG, OpenTargets, Reactome, and STRING.

    125 GitHub stars~1.4k tokensUpdated 6 mo ago
    Research & ScienceAuto-check passed

More from VectorSpaceLab/AREX-Skill

All 157 skills in this repo

  • Agent Lightning

    VectorSpaceLab/AREX-Skill

    Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…

    328 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Agent Tools

    VectorSpaceLab/AREX-Skill

    A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…

    328 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents And Awel

    VectorSpaceLab/AREX-Skill

    Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.

    328 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents And Middleware

    VectorSpaceLab/AREX-Skill

    Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…

    328 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents Workflows

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.

    328 GitHub stars~500 tokensUpdated 1 mo ago
    Auto-check passed

  • Alphafold3

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.

    328 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Input Preparation

What does Input Preparation do?

Build, validate, convert, and troubleshoot AlphaFold 3 input JSON files before prediction runs. Input Preparation is an agent skill from VectorSpaceLab/AREX-Skill. Build, validate, convert, and troubleshoot AlphaFold 3 input JSON files before prediction runs.

When should I use Input Preparation?

Input Preparation fits situations like: creating fold inputs; validating protein/RNA/DNA/ligand entries; converting AlphaFold Server JSON; adding MSAs/templates/user CCD/bonds.

How do I install Input Preparation in Claude Code?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill input-preparation -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/alphafold3/sub-skills/input-preparation in VectorSpaceLab/AREX-Skill) into .claude/skills/input-preparation in your project. Claude Code loads it when a task matches its description.

How do I install Input Preparation in Codex?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill input-preparation -a codex`. Or copy the skill folder (skills/repositories/repo-skills/alphafold3/sub-skills/input-preparation in VectorSpaceLab/AREX-Skill) into .agents/skills/input-preparation in your project. Codex loads it when a task matches its description.

Can I use Input Preparation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill input-preparation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/input-preparation, .gemini/skills/input-preparation, .github/skills/input-preparation and .opencode/skills/input-preparation in your project.

What does Input Preparation need to run?

Going by SKILL.md and its folder, Input Preparation needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Input Preparation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Input Preparation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Input Preparation use?

Input Preparation is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Input Preparation use?

About 619 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.5k tokens, read only when the agent opens those files.

What are the alternatives to Input Preparation?

Skills that share tags, products or a category with Input Preparation: Alphafold Database Fetch And Analyze (google-deepmind/science-skills, 3.2k stars), Alphafold (adaptyvbio/protein-design-skills, 163 stars), Chai (adaptyvbio/protein-design-skills, 163 stars) and Biopipelines (locbp-uzh/biopipelines, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Input Preparation?

VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 328 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.

Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.