From 26c04a70922aa0a9ce21bd8e1bab0b32fedc8b30 Mon Sep 17 00:00:00 2001 From: Amolith Date: Mon, 23 Mar 2026 09:27:38 -0600 Subject: [PATCH] docs(rumilo): clarify sequential query necessity Explicitly note that rumilo is amnesic and each invocation starts fresh, so later queries that depend on earlier answers must include that context. Also mention parallel execution for independent queries. --- skills/researching-with-rumilo/SKILL.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/skills/researching-with-rumilo/SKILL.md b/skills/researching-with-rumilo/SKILL.md index 7d4fa4abff574ef4f07d89383071a1baf6ed0c0a..274fbbbd8d90c2dae546964f1ee6c5f6ad782ec0 100644 --- a/skills/researching-with-rumilo/SKILL.md +++ b/skills/researching-with-rumilo/SKILL.md @@ -61,7 +61,8 @@ Rumilo works best with focused queries. Think about **scope** and **coupling** w - **Tightly coupled, narrow scope** — multiple simple questions in one call is fine when they're about the same small surface area (a single file, one struct, one API endpoint). - **Broad scope or loose coupling** — one question per invocation. If answering requires exploring many files or pages, keep it to a single clear question so the agent can focus. - **Write natural questions, not keyword lists.** Rumilo is an LLM, not a search index. -- **Sequence calls when later questions depend on earlier answers.** Get the overview first, then drill in. +- **Sequence calls when later questions depend on earlier answers.** Get the overview first, then drill in. Rumilo is amnesic — each invocation starts fresh. If a later query depends on an earlier answer (repo URL, version number, file paths), you must include that context explicitly in the prompt. +- **Run independent queries in parallel** (e.g. via separate tmux windows or backgrounded commands), but keep dependent queries sequential. ### Bad