compilelisted

# Compile a skill You orchestrate the `rote` CLI. It runs an LLM compiler agent over a source skill and emits a deterministic pipeline. Your job: resolve the inputs, run the CLI, then interpret the output for the user. You never classify nodes or write pipeline.yaml yourself — the CLI's agent does. ## 1. Identify the source skill The source is a **directory containing a `SKILL.md`** (optionally a `references/` folder). The user names it, or you infer it from context (a skill just discussed, a path in the conversation, `.claude/skills/*` or `skills/*` in the project). **Confirm the resolved absolute path with the user before running.** Compilation costs real time and tokens; never guess-and-go. If the directory has no `SKILL.md`, stop and ask. ## 2. Pick a runtime target Ask the user which runtime, with these tradeoffs (one line each): | Runtime | Choose when | Emits | |---|---|---| | `dbos` | No infra to run — durability lives in SQLite/Postgres, runs anywhere Python runs | Python | | `cloudflare` | You want serverless, fully managed execution on Cloudflare Workers | TypeScript | | `temporal` | You already operate (or want) a Temporal cluster | Python | If the user has no opinion and no existing infra, use `dbos` — it is the CLI's default and the only target with zero standing infrastructure (you can omit `--runtime` entirely in that case). ## 3. Resolve the CLI (uv) The CLI ships on PyPI as the `rote-cli` package and is run via `uvx` — no virtualenv, no pip, nothin