lda-wf/skills/wf-cli/SKILL.md

name, description

name	description
wf-cli	Use when authoring, validating, deploying, running, or debugging workflows through the repo-local `wf` CLI.

wf CLI

Use the wf CLI when an agent needs a shell-friendly workflow lifecycle:

1. Discover capabilities.
2. Create or patch a draft workspace.
3. Validate the draft.
4. Save an artifact.
5. Save and validate a deployment.
6. Run the deployment.
7. Read bounded trace slices only when debugging.

Canonical docs:

• docs/wf_cli.md
• docs/workflow_capabilities.md
• docs/workflow_drafts.md
• docs/workflow_artifacts.md
• docs/durable_run_operations.md

Core Commands

wf cap list --format ids
wf cap inspect <capability>
wf cap call <capability> --input '{"field":"value"}'

wf draft create-from-capability <workspace_id> <capability>
wf draft inspect <workspace_id> --include-draft
wf draft patch <workspace_id> --revision <n> --input-file patch.json
wf draft validate <workspace_id>
wf draft save <workspace_id> --artifact <artifact_id> --version <n> --title <title>

wf deploy save <deployment_id> --artifact <artifact_id> --version <n> --binding <logical>=<concrete>
wf deploy validate <deployment_id>
wf run start <deployment_id> --input-file input.json
wf run trace <run_id> --from 0 --limit 25

Rules

• Prefer --input-file for large JSON.
• Prefer --format ids or --format compact for discovery.
• Use wf cap call as a cheap smoke test before creating a draft.
• Do not request unbounded traces.
• Do not treat wrapper hints as semantic guarantees.
• If validation fails, run wf explain <code> or wf explain --input-file <validation-output.json>.
• Do not use planning-session specs or implementation plans as user-facing runtime guidance.