メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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 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.
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).
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 | python-executor |
| description | 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. |
Run Python code with one deterministic script:
scripts/run_python.pyUse this skill when the model needs to run a Python snippet or script file.
Inline code:
.venv/bin/python skills/python-executor/scripts/run_python.py \
--code "import platform; print(platform.python_version())" \
--cwd . \
--timeout 600
From a file:
.venv/bin/python skills/python-executor/scripts/run_python.py \
--code-file scripts/task.py \
--arg input.json \
--arg output.json \
--cwd . \
--timeout 600
--code "..." for inline snippets--code-file PATH for existing files--arg VALUE repeated to pass sys.argv[1:]--cwd working directory (default .)--timeout seconds (default 600)--python interpreter path (default current interpreter)Exit code is propagated from the Python process.
--code-file.--cwd explicitly to avoid path confusion.--arg.--base-dir)Pass --base-dir <DIR> to restrict --cwd and --code-file to the given directory:
.venv/bin/python skills/python-executor/scripts/run_python.py \
--base-dir /workspace \
--code-file /workspace/scripts/task.py --cwd /workspace # OK
.venv/bin/python skills/python-executor/scripts/run_python.py \
--base-dir /workspace \
--code-file /etc/exploit.py --cwd /workspace # exit code 2
--code is not restricted (matches Agno PythonTools behaviour).--base-dir is omitted, behaviour is unchanged (no restriction).