菜单
Use when a tool, command, sandbox, permission, network, dependency, or approval operation fails or repeats the same infrastructure error — classify the failure, cap retries, choose one bounded fallback, and stop before recovery consumes excessive tokens or time.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when starting a new session on a codebase, resuming interrupted work from a previous session, after making an architectural or design decision, or before ending a session or creating a PR — to create, update, or hand off docs/context/ project context files.
Comprehensive guide for dependency injection (DI) in Golang. Covers why DI matters (testability, loose coupling, separation of concerns, lifecycle management), manual constructor injection, and DI library comparison (google/wire, uber-go/dig, uber-go/fx, samber/do). Use this skill when designing service architecture, setting up dependency injection, refactoring tightly coupled code, managing singletons or service factories, or when the user asks about inversion of control, service containers, or wiring dependencies in Go.
Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log aggregation 3rd-party tools. Apply when creating, wrapping, inspecting, or logging errors in Go code.
Provides gRPC usage guidelines, protobuf organization, and production-ready patterns for Golang microservices. Use when implementing, reviewing, or debugging gRPC servers/clients, writing proto files, setting up interceptors, handling gRPC errors with status codes, configuring TLS/mTLS, testing with bufconn, or working with streaming RPCs.
Kotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.
Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.
| name | execution-recovery |
| description | Use when a tool, command, sandbox, permission, network, dependency, or approval operation fails or repeats the same infrastructure error — classify the failure, cap retries, choose one bounded fallback, and stop before recovery consumes excessive tokens or time. |
| metadata | {"source":"born-here","summary":"도구·권한·샌드박스 장애의 재시도 폭주를 차단하고 안전하게 대피"} |
복구 비용이 원래 작업보다 커지는 것을 막는다.
도구·작업·종료 코드·핵심 오류 한 줄을 묶는다. 인자만 바뀌고 핵심 오류가 같으면 동일 실패다.
| 실패 유형 | 동일 방식 재시도 |
|---|---|
| 입력·anchor·문법 오류 | 원인 수정 후 1회 |
| 일시적 timeout·경합 | 1회 |
| 권한·sandbox·정책 거부 | 0회 |
| command not found·의존성 부재 | 0회 |
| 원인 불명 | 진단 1회 후 중단 |
두 번째 동일 실패가 나오면 circuit을 열고 그 도구를 더 호출하지 않는다.
승인 요청과 대피 경로는 같은 목적에 각각 한 번만 허용한다.
bwrap: Failed to make / slave: Permission denied는 sandbox infra failure로 분류한다.
rg -n으로 필요한 범위를 확인한다.nl -ba <file>을 한 번만 요청한다.apply_patch가 같은 오류로 실패하면 scoped escalation으로 좁은 단일 치환 명령을 사용한다.복구 완료, 사용자 승인 필요, 환경 복구 필요, 작업 설계 오류 중 하나로 끝낸다. 영향이 크면 incident에 원인·낭비·방지 규칙·검증을 기록한다.