개발 스킬

Call the OpenAI Platform API from the terminal via TypeScript on deno — chat completions, Responses API, reasoning (o-series), embeddings, image generation, audio (Whisper transcription, TTS), files, batches, moderation, and model listing. Two-tool stack: mise + deno (no node_modules, no pnpm, no bash). Models are resolved dynamically per session against `client.models.list()` — never hardcoded — and any detected upgrade prompts the user via AskUserQuestion (even in auto-mode). Secrets stay outside the agent: existence-only key checks, scoped `--allow-env=OPENAI_API_KEY` and `--allow-net=api.openai.com` flags, no `.env` files. Scoped to the Platform API specifically — for open-ended chat/conversation ("ask gpt", "chat with gpt") prefer the codex-server skill instead, which uses the user's ChatGPT subscription rather than API-key billing. Use this skill only when the request is explicitly about the Platform API surface (embeddings, image generation, audio, moderation, batches, files, or a chat/Responses call made programmatically as part of a script or pipeline). Trigger patterns (match any variation): openai api / openai platform api / open-ai api / embeddings / dall-e / gpt-image / image generation / generate image / whisper / transcribe audio / speech-to-text / tts / text-to-speech / read aloud / moderation / content moderation / openai cli / openai-cli / call openai api / use openai api / openai chat completions api / openai responses api / responses api / openai batch / openai files / openai embeddings api. Does NOT access ChatGPT chat history (the API does not expose it; use the Settings → Data Controls export instead). Does NOT handle open-ended chat/conversation requests — see codex-server for that.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operate ONLY the user's private (personal) Google Drive via `rclone`, scoped to a single pinned remote (default `my-gdrive:`, override with the `MY_GDRIVE_REMOTE` env var). A safety wrapper around the `gdrive-cli` skill: refuses other remotes (e.g., the user's work/Workspace `tx-gdrive:`), strips Shared Drive and shared-with-me paths, and walks first-time users through OAuth setup with a personal Gmail account — including how to add a *second* rclone remote alongside an existing company one. Use whenever the user wants to act on their *private* / *personal* Drive specifically — not their work or shared Drive. Trigger phrases include "my gdrive", "my-gdrive", "my google drive", "my private google drive", "personal google drive", "personal gdrive", "private google drive", "private gdrive", "my private drive", "my personal drive", "personal drive", "private drive", "upload to my drive", "download from my drive", "backup to my google drive", "list my drive", "search my drive", "my drive quota", "sync to my gdrive", "use my personal google drive", "use my private google drive", "/my-gdrive".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create project-local Claude Code skills (.claude/commands/) in any project directory. Analyzes the project's tech stack, structure, and conventions, then generates tailored local skills (custom slash commands) scoped to that project. Like /my-skill-factory but output stays local — no marketplace installation. Trigger patterns: - local skill / local command / project skill / project command - create local skill / make local skill / add local command - "make a skill for this project" / "create command for this repo" - suggest skills / suggest commands / what skills would help - update local skill / edit local command / modify project skill - /local-skill-factory

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run OpenAI Codex via the Codex App Server (JSON-RPC-over-stdio) for streaming multi-turn chat sessions with persistent threads, structured output, image input, and rich event streams. Default entry point for ChatGPT/GPT/Codex-like conversations from the terminal. Uses the user's ChatGPT subscription (Plus / Pro / Team) exclusively via `codex login` — never consumes OPENAI_API_KEY billing, by design. Implementation: TypeScript on deno with npm:@openai/codex-sdk; spawns the existing system codex binary. Decoupled async invocation: every turn returns turn-id in <1 s; the actual SDK work runs in a detached worker that streams to per-turn files under ~/.codex-server/turns/<turn-id>/ — Bash's 2-min timeout never applies. Prefer this over codex-cli for streaming UX, multi-turn dialogues that need live state, structured (JSON schema) output, attaching images, or programmatic event handling. Use codex-cli only for one-shot batch invocations that pre-capture to an -o file. For OpenAI Platform API calls specifically (embeddings, image generation, audio, moderation, batches, files) — not open-ended chat — use openai-cli instead; that path bills OPENAI_API_KEY, this one uses the ChatGPT subscription. Trigger patterns (match any variation): codex / codex-server / codex app server / codex app-server / openai / open ai / OpenAI / chatgpt / chat gpt / ChatGPT / GPT / ask gpt / chat with gpt / gpt session / codex session / streaming chat / multi-turn chat / multi turn chat / second opinion / cross-check / cross check / ai pair programming / another AI / external AI / ask another model / get GPT's take / what does openai think / show me what gpt thinks / structured output from gpt / json schema gpt / resume codex thread / continue codex conversation / continue codex session / /codex-server

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run OpenAI Codex CLI from the terminal for batch / one-shot `codex exec` invocations with output captured to an `-o` file. Use for fire-and-forget runs, scripted CI, code review batches (`codex review`), and resuming a specific session by id (`codex exec resume`). Always use this skill instead of `mcp__codex__codex` and `mcp__codex__codex-reply` MCP tools — CLI is faster and more capable. For streaming UX, multi-turn dialogues that need live state, structured (JSON schema) output, attaching images, or programmatic event handling → **use codex-server instead**. codex-server uses the user's ChatGPT subscription via Codex App Server and decoupled async invocation that bypasses the Bash 2-minute timeout entirely. Trigger patterns (batch-only — chat/streaming triggers belong to codex-server): codex-cli / codex CLI / codex exec / codex review / codex resume / codex fork / batch + {codex, gpt} / one-shot + {codex, gpt} / non-interactive + codex / codex {to a file, -o, output file, captured output} / CI + {codex, gpt} / scripted + {codex, gpt} / fork codex session / resume codex session by id

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate AGENTS.md (cross-tool agent context — Codex CLI, Aider, Cursor, etc.) and wire CLAUDE.md as a symlink so Claude Code reads the same file. Delegates content generation to Claude's built-in /init when needed, then renames + symlinks. Idempotent. Triggers — /agents-init, "generate agents.md", "create agents.md", "share claude and codex context", "set up agents file", "init agents", "agents-init", "cross-tool agent context", "wire claude and agents".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Swift の repo で、新しいメソッド (ヘルパー・初期化・値を組み立てる関数) を書く前に同じものが既にないかを dupscan index で引き、実装が終わったセルフレビューで dupscan gate を回して増えた写しを寄せる。関連の実装 (定義・参照・ファイルの中身・呼び出し元) を grep より先に探すときにも使う (def / refs / callers)。「dupscan」「重複したメソッド」「類似メソッドの統合」「既にあるヘルパーを探して」「セルフレビュー」「定義元」「参照」「呼び出し元」「似た関数」で発火。寄せるときはドメインの境界を確かめる (4 節)。Swift 以外の repo では使わない (対応する言語は Swift だけ)。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user starts a cross-functional program, names milestones and owners, or asks what is at risk across workstreams and which gate can move.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when selling media, sponsorships, or programmatic where the cycle runs plan to proposal to insertion order to measured renewal.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when an account needs a running executive program: C-level connects, sponsorship gaps, briefings, and governance cadence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user names developers, API adoption, docs, SDKs, or a bottom-up motion: the developer motion plan with funnel, content spine, and conversion points.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up review and QA work from the repository, test setup, CI, release process, and merge rules.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

一時領域 (/private/tmp の Claude Code の作業場所・$TMPDIR・dotfiles の tmp/) に溜まったものを bin/tmpclean で数え、消す候補を種類ごとに見せて、ユーザーが承認した plan の古くて使用中でないものだけをゴミ箱へ移す (dotfiles の tmp/ は別の承認を取って make clean-tmp で消す)。「/tmp を掃除して」「一時ファイルを片付けて」「TMPDIR が溜まっていないか見て」「cleanup-tmp-dir」で発火。消す前に必ず承認を取る。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Conventions for using in all JVM languages

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Conventions for using in all JEE frameworks. These are common standards for CDI

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Conventions for using Java

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Conventions for using sh, bash, bat, python scripts

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert knowledge of Folketrygdloven (National Insurance Act) processing in melosys-api. Use when: (1) Understanding FTRL bestemmelser (§2-5 to §2-13), (2) Debugging yrkesaktiv/ikke-yrkesaktiv/pensjonist processing flows, (3) Understanding trygdedekning options and combinations, (4) Investigating vilkår for each bestemmelse, (5) Understanding medlemskapsperiode generation logic, (6) Debugging frivillig vs pliktig membership determination.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert knowledge of lovvalg (law determination/applicable legislation) domain in melosys-api. Use when: (1) Understanding which EU/EEA article applies (11, 12, 13, 16), (2) Debugging LA_BUC processing and SED sending/receiving, (3) Understanding A1 attestation generation, (4) Investigating lovvalgsperiode and unntaksperiode management, (5) Understanding automatic vs manual lovvalg determination, (6) Debugging lovvalgsbeslutning status transitions, (7) Understanding the mapping between regulations and kodeverk.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert knowledge of Fagsak (case) domain in melosys-api. Use when: (1) Understanding the fagsak lifecycle and status transitions, (2) Working with actors (aktører) - citizens, employers, authorities, (3) Debugging case creation, closure, or type/theme changes, (4) Understanding relationship between fagsak and behandling, (5) Working with EU/EEA authorities or bilateral treaty authorities. Triggers: "fagsak", "saksnummer", "MEL-", "aktør", "sakstype", "sakstema", "avslutt sak".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert knowledge of REST endpoint patterns in melosys-api's frontend-api module. Use when: (1) Creating new REST endpoints for melosys-web, (2) Understanding controller patterns and Swagger documentation, (3) Working with DTOs and request/response objects, (4) Understanding exception handling and HTTP status codes, (5) Adding access control to endpoints. Triggers: "new endpoint", "REST controller", "@RestController", "add a DTO", "ResponseEntity", "Aksesskontroll", "access control on endpoint", "Swagger/@Operation", "return 404/403/401/400", "@Protected", "frontend-api", "search endpoint", "/sok".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert knowledge of vilkår / vilkårsvurdering (requirements evaluation) in melosys-api. Use when: (1) Understanding inngangsvilkår structure for FTRL bestemmelser (VilkårForBestemmelse), (2) Debugging Vilkaarsresultat / oppfylt status or begrunnelser, (3) Understanding avklarte fakta (AvklarteFaktaForBestemmelse) collection, (4) Investigating why a vilkår fails or which vilkår a bestemmelse requires. Triggers: vilkår, vilkaar, vilkaarsresultat, vilkårsvurdering, oppfylt, begrunnelse, inngangsvilkår, avklarte fakta, FTRL_2_5, FTRL_2_8, VilkårForBestemmelse.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.