エンジニアリング
Bots decide; scripts repeat; verifier checks — stop burning tokens on rehearsal
Routines re-reason the same commands and burn tokens every wake.
困っていたこと
@Solomonrojie shares a SpaceXAI-style split: lead Bot decides and handles exceptions; scripts collect/transform/check; a verifier checks the deliverable. Judgment only at plan→execute, unclear failures, and before external actions. Author-quoted refactor prompt keeps BRIEF.md, file logs, and approval before send/publish/delete. Not affiliated with xAI.
インストールまたは作成するもの
Paste refactor prompt → review proposed split → scripts + BRIEF.md + verifier → approve before routine.
ボット
Lead bot
Defines the task, approves approach, handles exceptions.
Verifier bot
Checks deliverable against brief and test results.
プラグイン
初日から入れるものはありません。初回の手順に従ってください。
ルーティン
初回の実行では使いません。まず手動で1回通して確認してください。
プロンプト
Refactor workflow: bots decide, scripts repeat (author-quoted)
Quoted from @Solomonrojie — as published. Do not invent a second system prompt.
Refactor this recurring workflow so scripts handle repeatable operations and Bots handle decisions: 1. Inspect the current process. Identify deterministic steps, judgment calls, required access, and the finished result. Show me the proposed split before changing anything. 2. Create BRIEF.md with the goal, inputs, acceptance checks, and approval boundaries. Turn stable operations into reusable scripts. Save detailed logs to files and return concise summaries. 3. Where I control the executor, propose filesystem and network restrictions for commands and self-hosted MCP servers. Test an allowed action and a deliberately blocked action. Report anything the environment cannot enforce. 4. Use a separate verifier when an independent check is useful. Give it the brief and evidence. Preserve successful steps, stop after two failed repair attempts, and report what remains unresolved. Show me the changes and one completed test run before enabling a routine.
初回実行
- 1Read https://x.com/Solomonrojie/status/2114128321449693673 (credit @Solomonrojie).
- 2Pick one recurring workflow that re-explains the same steps every run.
- 3Paste the author-quoted refactor prompt.
- 4Review the proposed bot/script split and BRIEF.md before any change.
- 5Require one completed test run — then your yes — before scheduling a routine.
承認フェンス
Show proposed split and one test run before enabling a routine; approve send/publish/delete/production changes.
調整ポイント
Steal the split: bots for decisions, scripts for repetition, you for consequential actions.
出典
Solomon Rojie @Solomonrojie · 元の投稿
xAI とは提携していません。このプロンプトは当サイトが書いたものではありません。第三者テンプレートの規約も適用されます。
Pro パック
アイデアだけでなく、完全な構成が必要ですか？
Pro パックには、人気ユースケースのジョブ本文、プロンプト、スケジュール、落とし穴が入っています。