← ClaudeAtlas

compilelisted

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 a compiled skill (the default) or runtime code for DBOS (Python or TypeScript), Temporal, Cloudflare Workflows, Inngest, or a plain Python script.
trevhud/rote · ★ 8 · AI & Automation · score 71
Install: claude install-skill trevhud/rote
# 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. <!-- rote:worth --> ### Is it worth compiling? Compiling to the skill runtime pays off when most of the skill's work is fixed steps: tool calls, lookups, filtering, arithmetic, formatting. The compiled skill does those in code and stops for you only where the skill needs judgment. Each stop is a round trip that re-reads the conversation, so a skill that is mostly judgment (search, read, then write an answer) runs slower and costs more compiled. Measured: Atlassian's search-company-knowledge took 4x longer at 3x the cost, while expense-audit ran 3.6x faster at 62% less. Read the SKILL.md before compiling, and count the steps that need judgment: choosing, ranking, summarizing, writing prose. If a run needs more than two, tell the us