菜单
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.
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.
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 | shell-executor |
| description | 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. |
Run shell commands with one deterministic script:
scripts/run_shell.pyUse this skill when you need CLI operations and want a standardized skill interface.
.venv/bin/python skills/shell-executor/scripts/run_shell.py \
--cmd "pwd && ls -la" \
--cwd . \
--timeout 600
--cmd: shell command string--cwd: working directory (default .)--timeout: seconds before termination (default 600)--shell: shell executable (default $SHELL or /bin/bash)Exit code is propagated from the executed command.
--cmd argument.--cwd explicitly for reproducibility.--timeout for long tasks (tests, builds, downloads).--base-dir)Pass --base-dir <DIR> to restrict --cwd to the given directory:
.venv/bin/python skills/shell-executor/scripts/run_shell.py \
--base-dir /workspace \
--cmd "ls -la" --cwd /workspace # OK
.venv/bin/python skills/shell-executor/scripts/run_shell.py \
--base-dir /workspace \
--cmd "ls -la" --cwd /etc # exit code 2
--cmd) is not restricted (matches Agno ShellTools behaviour).--base-dir is omitted, behaviour is unchanged (no restriction).