원클릭으로
hi-fix
ALWAYS activate before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
ALWAYS activate before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.
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
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
ALWAYS activate before implementing ANY feature, plan, or fix.
Debug systematically with root cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, call stack tracing, multi-layer validation, log analysis, CI/CD failures, database diagnostics, system investigation.
Unified knowledge retrieval skill. Build traceable answers from git, MCP, and memory files.
Plan implementations, design architectures, create technical roadmaps with detailed phases.
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
| name | hi:fix |
| description | ALWAYS activate before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem. |
| argument-hint | [issue] [--standard|--deep|--parallel|--review] — default: Quick mode |
| metadata | {"author":"baka3k","version":"2.0.0"} |
| Flag | When |
|---|---|
| default | Quick: 1 file, type/lint, lỗi rõ ràng |
| --standard | Standard: 2-5 files, cần debug đầy đủ |
| --deep | Deep: 5+ files, architecture impact |
| --parallel | 2+ independent issues |
| --review | Human-in-the-loop at each step |
[Scout] -> [Diagnose] -> [Fix] -> [Verify+Prevent] -> [Finalize]
Locate affected files và đọc lỗi. 1 agent là đủ. Standard/Deep: activate hi:scout hoặc 2-3 parallel agents.
Capture pre-fix state: exact error, stack traces, logs. Trace backward: symptom -> immediate cause -> contributing factor -> ROOT CAUSE. Nếu khó: activate hi:debug. Nếu 2+ hypotheses fail -> activate hi:problem-solving.
Fix ROOT CAUSE. Minimal changes. Follow existing patterns.
Quick: typecheck + lint (mặc định) Standard: + build + test Deep: comprehensive (edge cases, security, perf)
Quick: report ngắn -> ask commit (skip docs, skip review) Standard/Deep: report -> review (nếu --review) -> docs -> commit
Scout (locate only) -> Diagnose (read error) -> Fix -> Verify (typecheck+lint) -> Done
Full Scout -> Full Diagnose (gọi hi:debug nếu cần) -> Fix -> Verify (typecheck+lint+build+test) -> Review (nếu --review) -> Finalize
Parallel Scout + Diagnose + Research -> Fix -> Comprehensive Verify -> Review -> Finalize
Separate task tree per issue. Spawn fullstack-developer per issue.