メニュー
Check Claude/Codex/OMX context, cache, headroom, and handover pressure; advise continue, compact, clear, or hand off.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Review and edit Korean technical docs, READMEs, UI copy, and prompts when terminology sounds machine-translated or a canonical English term was unnecessarily translated. Classify each disputed term as canonical English to preserve, established Korean to keep, or an awkward calque to rewrite naturally. Also strips surface AI-tell symbols from Korean prose — em/en dashes and spaced --, arrows (→), curly/smart quotes, ellipsis (…), and middle-dot (·) bullets or noun enumerations. Use for 기술 용어, 번역투, 직역, 영어로 써야 할 표현, 원어 유지, 한글화가 어색함, 용어 통일, 화살표 제거, em대시 없애, 가운뎃점 없애, AI 티 기호, AI slop 기호, Korean technical writing, or terminology review. Do not use as a general spelling or tone checker.
Auto-research and improve a repo's skills, hooks, and scripts: external real-world web research + internal audit + Codex cross-model verification, behind a propose then approve then apply gate with freeze-on-success and auto-revert. Use when asked to improve, audit, harden, or research-improve skills/hooks/scripts in the current repo.
Use public web, GitHub, social/community, video, RSS, and career search surfaces from the CLI/MCP when local repo evidence is not enough. Routes to public-only research tools while avoiding internal/company URLs and secret-bearing pages.
Clean up runaway/orphaned agent processes: stuck zip/tail/python/node, high CPU, dead Claude/Codex/OMX sessions.
Audit installed Claude/Codex agents, skills, commands, metadata-level reference counts, and source-level token pressure to decide what to prune, keep, or route. This inventory skill does not mine historical correction content or decide the current session's handoff state.
Diagnose codegraph/serena MCP setup, Codex config, and per-repo indexes when code intelligence is broken or stale.
| name | context-check |
| description | Check Claude/Codex/OMX context, cache, headroom, and handover pressure; advise continue, compact, clear, or hand off. |
Use this skill as an advisory gate for the current session. It should not audit historical feedback or mutate session state by itself.
SKILL_DIR to the absolute directory containing this SKILL.md (use the
path supplied by the skill loader), then run the bundled helper from any cwd:
SKILL_DIR="/absolute/path/to/context-check"
python3 "$SKILL_DIR/scripts/context_check.py" diagnose --cwd "$PWD"
/compact when the same task must continue and important context would be lost by clearing./clear when the task is disposable, done, or a fresh branch would be cleaner than preserving history.$handover only when a fresh agent surface is valuable: Claude ↔ OMX/Codex transfer, tab/session closure, stuck/poisoned context, or long-running cmux handoff./clear, /compact, or $handover from the hook; surface the recommendation and let the active agent/user apply it.claudeh/codexh/omxh or default shell wrappers):
treat Headroom as the primary token/cache mitigation layer.--include-ccusage).~/.claude/hooks/context-check.sh and the local-skills@dotfiles-local plugin exposes this skill.scripts/skills.sh codex symlinks this skill into ~/.codex/skills/context-check; use $context-check or run the script directly.