القائمة
Resume execution from a previous session — reads checkpoint state and continues where the last session left off.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | resume |
| description | Resume execution from a previous session — reads checkpoint state and continues where the last session left off. |
| user-invocable | true |
Resume work from a previous session's checkpoint.
Find resume state: Check for resume files in this order:
a. Omega memory: call omega_resume_task() if available
b. Local resume file: ~/.next-level/sessions/*/resume.md (most recent)
c. Continuation file: ~/.next-level/sessions/*/continuation.md (most recent)
Load context: Read the resume/continuation file. It contains:
Verify state: Before resuming:
gh issue list --state closed --json number | jq -r '[.[].number]' and verify the issue numbers from the resume file appear in the outputResume execution:
/next-level:execute to continue the epic from the right pointClean up: Delete the resume/continuation file only after the resumed task completes successfully (not immediately on resume — keep as fallback if the resumed task fails)
The resume file (resume.md) is written by /next-level:execute when context runs low:
# Resume: <project-name> / <epic-name>
## Completed Tasks
- #12: Setup configuration system ✓
- #13: Dependency detection engine ✓
- #14: Setup skill ✓
## Current Task
- #15: Doctor skill — IN PROGRESS (step 2/4: "Check 2: Dependencies")
## Next Tasks
- #16: SessionStart hook
- #17: File checker dispatcher
## Key Decisions
- Chose ruff over black for Python (faster, single tool)
- Using jq for JSON parsing in bash hooks
## Context When Saved
- 87% at checkpoint
- Session: abc123
No resume state found. Nothing to resume.
Options:
- /next-level:spec "task" — start a new spec
- /next-level:project "description" — plan a new project
- /next-level:context-status — check session state
If the resume file is older than 24 hours, or if significant code changes have been made since:
Primary review entrypoint for plans, diffs, commits, subagent results, and pre-submit checks. Selects quick, standard, or deep mode by scale and risk.
Planner-led repo improvement loops with subagents, review gates, Mermaid DAGs, and workflow-aware commits. Use for improve, refactor, audit, or continue-loop requests.
Triage and apply code review feedback with technical verification. Use when a human, reviewer subagent, CI, or adversarial reviewer returns findings or requested changes.
Heavy review mode normally invoked by request-code-review for risky checkpoints, pre-submit stacks, OpenSpec/cflx acceptance, security-sensitive work, or explicit deep review, audit, or red-team requests.
Post-implementation cleanup for recent changes using parallel reuse, quality, and efficiency reviewers. Use after building a feature or fix, before commit, PR, or submit.
End-of-workflow learning loop for skill-guided work. Use at session/checkpoint closeout to classify GitHub/CodeRabbit/human/CI findings, log missed-review patterns, and propose skill improvements only when evidence justifies them.