Reload saved working state from .amber/ (STATE.md, FOCUS.md, checkpoint.md) and continue the previous task. Use when the user says resume/continue where we left off, or at the start of a session in a project that has an .amber directory.
Scanned 9/7/2026
Install to Claude Code
npx -y skills add yanfeid/claude-amber --skill resume --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Resume?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/yanfeid-resume)More formats (shields.io, HTML) on the badges page.
---
description: Reload saved working state from .amber/ (STATE.md, FOCUS.md, checkpoint.md) and continue the previous task. Use when the user says resume/continue where we left off, or at the start of a session in a project that has an .amber directory.
---
# /amber:resume — pick up where you left off
1. Read, in this order, whichever exist:
- `.amber/STATE.md` — model-written working state (authoritative)
- `.amber/FOCUS.md` — active focus contract (still binding unless the user changes the task)
- `.amber/checkpoint.md` — machine-captured facts (recent goals, files touched)
2. If none exist, say so and ask what to work on. Do not invent prior state.
3. Cross-check the state against reality before acting: the files listed — do they still exist, do they contain what the state claims? Git may have moved on since the checkpoint. If reality contradicts the state, trust reality and say what changed.
4. Give the user a 3–5 sentence re-grounding: what the task is, where it stood, and the single next step you propose. Then, unless they redirect you, execute that next step.
5. If `.amber/STATE.md` says "Next steps", do not re-plan from scratch — continue the plan.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.