菜单
Convert CSV tables into valid AlphaFold3 input JSONs. Use this skill when you need to batch-generate AF3 JSONs from tabular inputs and run in MSA-free mode (protein uses empty unpairedMsa/pairedMsa, RNA uses empty unpairedMsa).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Perform normalized filesystem operations (list, read, write, append, mkdir, stat, copy, move, delete, search, replace) through a single skill script. Use when tasks require deterministic file manipulation through get_skill_script instead of built-in FileTools.
Execute Python snippets or Python files through a normalized skill entrypoint with explicit cwd, timeout, and argv. Use when tasks require ad-hoc Python execution and you want skill-based execution instead of built-in PythonTools.
Execute shell commands through a normalized skill entrypoint with explicit cwd and timeout. Use when tasks require command-line operations (tests, build, git, search, file inspection) and you want script-based execution via get_skill_script instead of built-in ShellTools.
Convert AlphaFold3 official inference JSON into Protenix, Boltz, or OpenFold3 inputs with schema validation. Use when an existing AF3 JSON must be reused by another folding stack, including batch conversion, target auto-detection from output filename, and best-effort mapping of AF3 `bondedAtomPairs`, MSA fields, templates, and ligand CCD/smiles data.
Extract deduplicated protein, DNA, and RNA sequences from AF3 or Protenix inference JSON files into per-entity-type FASTA files keyed by SHA-256 hash. Use as the first stage of the MSA pipeline before `af3-msa-search` and `af3-msa-injector`.
Inject cleaned ColabFold MSA artifacts from `af3-msa-search` into MSA-free AF3 or Protenix inference JSON files to produce complete inputs for downstream inference. Use when AF3 JSON contains empty `unpairedMsa`/`pairedMsa` fields or Protenix JSON lacks `unpairedMsaPath`/`pairedMsaPath`, including single-file and batch directory processing.
| name | af3-json-factory |
| description | Convert CSV tables into valid AlphaFold3 input JSONs. Use this skill when you need to batch-generate AF3 JSONs from tabular inputs and run in MSA-free mode (protein uses empty unpairedMsa/pairedMsa, RNA uses empty unpairedMsa). |
Generate one AlphaFold3 input JSON per table row.
Run commands from repository root and prefer .venv/bin/python.
Use this skill in two modes:
type_k/seq_k columns directly.--schema when column names are custom or layouts are complex.Reference: references/AlphaFold3_input.md (AF3 input spec).
dialect, version, modelSeeds, name, sequences).unpairedMsa: "", pairedMsa: "", templates: []unpairedMsa: ""--version 3 and --seeds 1 (single seed unless explicitly overridden).A-Z, AA, ...).id as a list (for example ["A","B","C"]) instead of duplicating the same sequence entity.Use when your table has type_1/seq_1, type_2/seq_2, ...
Supported type_k:
protein, rna, dna, ligand_ccd, ligand_smilesRecommended optional columns:
job_id (or pass --id-col)id_k (explicit AF3 entity id like A, B, L, or JSON list like ["A","B","C"] for homomer copies), otherwise ids are auto-assigned.type_k/seq_k indices must be contiguous (1,2,3,...) with no gaps.A/C/G/U/N (T is rejected)A/C/G/T/NRun:
.venv/bin/python skills/af3-json-factory/scripts/csv_to_af3_json.py --help
.venv/bin/python skills/af3-json-factory/scripts/csv_to_af3_json.py \
--table inputs.csv \
--out-dir runs/$(date +%Y%m%d_%H%M%S)/inputs/json \
--id-col job_id \
--seeds 1
Use when your table DOES NOT match type_k/seq_k, or you need custom column names.
Copy assets/schema.example.json.
assets/schema.example.csv.Edit entities[]:
kindid or id_col (or omit both for auto-ID)id supports a single string ("A") or a list (["A","B","C"]) for homomer copiessequence_col / smiles_col / ccd_coloptional: true to skip this entity when the row value is emptyRun with --schema:
.venv/bin/python skills/af3-json-factory/scripts/csv_to_af3_json.py \
--table complex.csv \
--schema my_schema.json \
--out-dir runs/$(date +%Y%m%d_%H%M%S)/inputs/json \
--id-col job_id \
--seeds 1,2
If the schema cannot express your input, then edit scripts/csv_to_af3_json.py, using references/AlphaFold3_input.md as the ground-truth spec.
--on-error skip to keep going; bad rows are recorded in the manifest.job_id values are rejected to prevent silent JSON overwrite.*.json under --out-dirmanifest.jsonl under --out-dir with status=ok|error and error details.job_id (including collisions with existing files in --out-dir).manifest.jsonl has no status=error rows.unpairedMsa only,id_k/schema id.optional: true.