compile

name

compile

description

Compile an Anthropic-style skill — a directory with a SKILL.md and optional references/ — into a deterministic, runnable workflow via the rote CLI. Use when the user says "compile this skill", "graduate this skill" (the retired name for the same operation), "make this skill deterministic", "make this skill faster/cheaper", "turn this skill into a workflow", "turn this skill into code", "harden this skill for production", or complains that a skill is slow, expensive, or unreliable as a background job. Output: a pipeline.yaml IR, extracted code modules, typed LLM-judge signatures, and runtime code for Temporal, Cloudflare Workflows, or DBOS.

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