dotfiles

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.

Check Claude/Codex/OMX context, cache, headroom, and handover pressure; advise continue, compact, clear, or hand off.

Verify dotfiles install scripts, plugin manifests, hooks, TOML/JSON/plist config, and CI-style smoke checks.

Hand off current work to fresh Claude/Codex/OMX sessions or visible cmux/purplemux display backends with durable artifacts, ACK/READY checks, optional source-tab closure, and fail-closed recovery.

Serve local files, HTML reports, static directories, dashboards, or build artifacts through verified private/tailnet browser URLs. Use when asked to serve, preview, expose, share, or make generated local web output accessible, including 서버 켜줘, 접속 가능하게 해줘, 웹에서 볼 수 있게 해줘, or HTML 보여줘. Do not use to browse source code or open an existing git worktree in code-server.

Use when about to commit to a plan, rollout, migration, release, hire, or any decision that is costly or hard to reverse — run this before you start, not after. Triggers: 'premortem this', 'what could kill this', 'stress test this plan', 'what am I missing', 'poke holes in this', 'where will this break', '실패 시나리오', '뭐가 잘못될 수 있어', '이 계획 망할 이유'.

Analyze historical local Codex, Claude, or OMX JSONL session logs for repeated user corrections, re-requests, execution preferences, and agent failure patterns, then turn cross-session evidence into concise anti-repeat rules. Use for historical session-feedback audit, JSONL analysis, repeated corrections, recurring instructions, 매번 요청, 반복 안 되게, 재발 방지, or requests to learn durable guidance from past agent conversations. Do not use for current-document cleanup or writing review. Built-in Korean and English pattern packs are extensible with custom JSON patterns; this is not a Korean-only writing skill.

Track provenance for imported skills, agents, hooks, prompts, plugins, scripts, and third-party workflow assets.

Use when a prior AI answer, supplied text, report, or explicit claim needs fact-checking before you trust or publish it — especially numbers, file/command references, or causal/security statements headed into a README, PR, docs, report, or decision. Triggers include 'fact-check this answer', 'is this claim accurate', 'check this report for hallucinations', '이 답변 검증해줘', '이 주장 맞아', or '환각 확인'. Do not use for ordinary code test execution or general repository verification.

Inspect work-scope safety reminders for company/work dirs, sensitive URLs, internal data routing, and hook overlays.

Build a browser VS Code (code-server) link for a git worktree or all worktrees of a repo. Use when the user asks to view, review, or open worktree source code in browser VS Code. Do not use to serve reports or build artifacts, and do not start a new preview server.

Use when investigating bugs, regressions, flaky or intermittent failures, unexpected UI/runtime behavior, incidents, or a fix that didn't work — especially when the symptom and the cause aren't obviously linked, or repeated guesses keep missing. Triggers: 'debug this', 'why is this failing', 'find the root cause', 'this fix didn't work', '디버깅', '원인 찾아줘', '왜 안돼'.