executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
cli-sdk-workflowsOperate on Transformer Lab Typer CLI, Textual job monitor, CLI config/auth/profiles, asset transfer helpers, Python SDK facade/resources/storage, and tfl-remote-trap workflows.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when a task touches Transformer Lab's Python CLI package, the interactive job monitor TUI, CLI authentication/profile/config state, asset upload/download helpers, the Python SDK facade/resource/storage layers, or the remote task wrapper used by launched jobs.
tfl-remote-trap: read SDK reference.../backend-api-services/SKILL.md.../task-execution-compute/SKILL.md.../frontend-web-app/SKILL.md.--format, --profile, and root --no-interactive must appear immediately after lab and before a command group.lab.init() before logging, progress, or save helpers, and pass final scores as dictionaries, not scalars.transformerlab-cli 0.0.68.transformerlab 0.1.46.Lab.init(self, experiment_id: str | None = None, config: Optional[Dict[str, Any]] = None) and Lab.finish(self, message: str = "Job completed successfully", score: Optional[Dict[str, Any]] = None, additional_output_path: Optional[str] = None, plot_data_path: Optional[str] = None).typer.testing.CliRunner with mocked API calls; SDK tests use pytest around isolated workspace/storage state.