메뉴
Use when work may touch a codebase, long session, large files, unknown repo structure, or model context is limited. Finds relevant context first, avoids broad dumps, keeps a compact working map, and recommends compact/fresh-session points.
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
Use when setting up or repairing repo agent instructions for Claude Code, Codex, or both. Proposes durable AGENTS.md, CLAUDE.md, and project memory changes before writing unless setup was explicitly requested.
Use for backend routes, API design, validation, database interactions, auth boundaries, response shapes, typed clients, error models, and integration-safe changes.
Use for slow pages, large bundles, slow APIs, database performance, caching, rendering jank, long sessions, and production-readiness polish.
Use for high-end UI, SaaS dashboards, landing pages, product websites, mobile responsive UI, visual redesign, UI polish, empty/loading/error states, motion, typography, and design quality rescue.
Use for long-running projects, context compaction, resume/handoff work, multi-session builds, or when the user asks to preserve project state. Proposes small verified memory docs before creating them unless setup was explicitly requested.
Use automatically for Claude Code work involving files, tools, bash, edits, tests, long commands, failed tool calls, or unfamiliar repos. Improves tool choice, prevents loops, and keeps work high-quality without adding broad context.
| name | Context Intelligence |
| description | Use when work may touch a codebase, long session, large files, unknown repo structure, or model context is limited. Finds relevant context first, avoids broad dumps, keeps a compact working map, and recommends compact/fresh-session points. |
| allowed-tools | Read, Bash |
Use this skill before large implementation, debugging, refactors, or unfamiliar repos.
AGENTS.md, CLAUDE.md, or docs/agent-memory/INDEX.md exists, read only the relevant boot/memory files first, then verify claims against code.Bash with rg, rg --files, or find to find candidate files. Read only likely relevant files./compact with a concrete focus.Return concise context map:
GoalLikely FilesRiskPlanNeed Read NextDo not read huge logs or generated files unless user asks. Summarize long outputs.