메뉴
Disaster response and systems recovery: controlled execution paths, backup-first discipline, build/runtime probes, and checkpoint-based rollback. Use for debugging crashes, data recovery, failover scenarios, or infrastructure repair.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | systems-recovery |
| description | Disaster response and systems recovery: controlled execution paths, backup-first discipline, build/runtime probes, and checkpoint-based rollback. Use for debugging crashes, data recovery, failover scenarios, or infrastructure repair. |
Leading word: checkpoint — before every state-changing operation, create a point you can return to. Recovery is a series of checkpoints, not a single rollback.
# rsync — file-level backups
# dmesg/journalctl — system logs
# strace/lsof — process diagnostics
Detailed probing patterns: references/probe-strategies.md
SKILL systems-recovery
INPUTS:
failureType: string // crash, data_loss, build_fail, runtime_error
targetSystem: string // Service, application, or path affected
backupPath?: string // Optional path to known-good backup
OUTPUTS:
recoveryPlan: array // Ordered recovery steps
rootCause: string // Identified root cause
recoveryStatus: object // Status per step with rollback info
PRECONDITIONS:
- Backup verified restorable before any modification
- Build system integrity confirmed (compiler, deps, disk)
- Runtime probes collected before diagnosis
POSTCONDITIONS:
- All state changes logged for rollback
- Recovery checkpoints before each state change
- If recovery fails → rollback to last checkpoint
- Root cause documented for future prevention
ERROR_HANDLING:
- Backup not restorable → halt and alert
- Build system missing or corrupted → repair before recovery
- Runtime probe fails → fall back to log analysis
- Recovery step fails → rollback to last checkpoint
Smart commit with Conventional Commits: groups logical changes, infers type + scope from file paths, and generates messages in `<type>(<scope>): <description>` format.
Iterative quality gate hardening loop — run the gate, parse failures, fix each failing category with a fresh-context delegate, re-run until all gates pass or diminishing returns are hit.
Relentless quality loop: alternate between a fresh-context implementer and a fresh-context reviewer until only diminishing-return issues remain. The reviewer is advisory-only (no state changes). The implementer starts fresh each cycle, unanchored from prior attempts. Terminates when max severity ≤ 3 for two consecutive cycles or the severity trend is flat.
Compact the current conversation into a handoff document for a fresh agent to pick up next session. Includes current phase, workspace state, memory state, and suggested skills.
Investigate a question against primary sources (official docs, arXiv papers, Semantic Scholar, source code, specs, first-party APIs) using the web_search tool. Writes structured findings as a Markdown file. Use when the user wants a topic researched, docs gathered, API facts investigated, or reading legwork delegated. Maps to P1 Explore phase.
Meta-cognitive improvement loop: reflect on errors, learn patterns, codify guardrails. The skill that rewrites skills. Always loaded.