Skip to main content

zero-sleep

Holds the thread across a big multi-step build without losing the plot — long-haul endurance and context-keeping; invoke via /zero-sleep when a task spans many steps and hours and you need consistency from start to finish.

ソース情報

リポジトリ
Jakeschincariol/unhinged-claude-skills
ソースの最終更新活動
2026年6月27日 19:35
検出された SKILL.md の言語
英語
スター
14
フォーク
1

インストール方法

デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。

ソースファイルを確認

インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。

SKILL.md を表示中

SKILL.md
ソースの指示 · 読み取り専用プレビュー
name
zero-sleep
description
Holds the thread across a big multi-step build without losing the plot — long-haul endurance and context-keeping; invoke via /zero-sleep when a task spans many steps and hours and you need consistency from start to finish.
# Zero Sleep The marathon, not the sprint. This mode is built for long, sprawling builds where the real risk isn't any single step — it's forgetting what you decided three hours ago. It keeps the thread, the goals, and the constraints locked in from step one to step done. ## When to use - A large, multi-step build that spans many actions or a long session. - The danger is drift: losing track of earlier decisions, goals, or constraints. ## Behavior 1. Establish and write down the north-star goal, key constraints, and decisions at the start as an anchor. 2. Maintain a living progress ledger: what's done, what's in flight, what's next. 3. Re-read the anchor and ledger before each major step to avoid drifting from the original plan. 4. Keep decisions consistent — when a new step touches an earlier choice, honor it or explicitly revise it on the record. 5. Checkpoint state at natural boundaries so the work can be resumed without re-deriving everything. 6. Watch for contradiction: flag when a new step conflicts with something decided earlier. 7. Periodically summarize progress against the goal so the big picture stays in view. ## Output Steady end-to-end progress on the build, a maintained progress ledger and decision anchor, and periodic check-ins confirming the work still matches the original goal.
GitHubで見る