Hideki Koike

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".

The English summary is being prepared. Showing the original description.

Create, build, and install custom Claude Code skills into Hideki's local marketplace. End-to-end workflow from requirements gathering to a fully installed and usable skill. Use when the user asks to create a new skill, build a skill, make a plugin, add a new capability, or says "make me a skill for X". Also use when updating or reinstalling an existing custom skill. Trigger phrases include "create skill", "make skill", "new skill", "build plugin", "skill for X", "update skill".

The English summary is being prepared. Showing the original description.

仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。

The English summary is being prepared. Showing the original description.

日本語の技術文書 (技術ブログ・技術記事・README・設計書・英語の技術語が混ざるドキュメント) に絞った AI 臭レビュアー。ファイル / 貼り付けテキスト / ディレクトリを読み、プレ AI 時代の技術ブログ調へ整えるための禁止フレーズ辞書 (16 カテゴリ A–P。曖昧・稚拙な用語の的確化も含む。実フィードバックと公開研究を統合) と、grep + 質的レビューの二段監査で検出・置換します (subagent をさらに spawn せず、自分のコンテキスト内で完結)。英語語混在の技術ドキュメントには、カタカナ技術語→英語表記・英字↔日本語の境界スペース除去のハウススタイルも適用します。en-to-ja-explainer と japanese-tech-writing が名前指定で委譲する先でもある。技術文書以外 (議事録・レポート・メール・企画書などのビジネス文書、note・一般のブログ・エッセイ) の AI 臭除去、読みやすさの改善、AI 臭さの採点・診断は natural-japanese の担当なので、そちらを使う。Triggers: 「技術ブログの AI 臭を抜いて」「技術記事の日本語を自然にして」「README の日本語が AI っぽい」「技術ドキュメントの ChatGPT 臭をチェック」「カタカナ技術語を英語表記に揃えて」「naturalize Japanese」「naturalize-ja」「/naturalize-ja」

The English summary is being prepared. Showing the original description.

Operate Notion from the terminal via the official Notion REST API on TypeScript + deno — search workspace, get/create/update/archive pages, query databases with filters and sorts, list/append/delete blocks, list and retrieve users, list databases, retrieve page comments. Two-tool stack: mise + deno (no node_modules, no pnpm, no bash). Token stays outside the agent: existence-only check, scoped `--allow-env=NOTION_TOKEN,NOTION_API_KEY,NOTION_TOKEN_FILE` and `--allow-net=api.notion.com` flags only, no `.env` files, never echo or print the token. Token resolved in order: NOTION_TOKEN → NOTION_API_KEY → contents of the file at NOTION_TOKEN_FILE (suits agenix / sops-nix / 1Password CLI mounts). Walks first-time users through creating a Notion Internal Integration and sharing pages with it. Trigger patterns (match any variation): notion / Notion / notion-cli / notion cli / notion api / notion page / notion pages / notion database / notion db / notion search / search notion / find in notion / create notion page / new notion page / update notion page / edit notion page / archive notion page / delete notion page / notion blocks / list blocks / append blocks / notion users / list notion users / notion workspace users / query notion database / list notion db / notion db query / get notion page / show notion page / read notion page / notion workspace / notion integration / notion token / /notion-cli.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Senior QA/QC engineer that evaluates existing codebases for test quality. Runs existing tests, diagnoses failures, identifies missing test coverage, and writes missing tests. Framework-agnostic — works with any language and test runner. Use when the user asks to run tests, diagnose failures, do test gap analysis, QA, quality assurance, test coverage analysis, find missing tests, test audit, quality check, quality report, fix failing tests, evaluate test quality, or assess test health of a codebase. Trigger phrases include "run tests", "QA", "quality assurance", "test audit", "test coverage", "missing tests", "gap analysis", "quality report", "fix failing tests", "diagnose test failures", "quality check", "evaluate test quality", "test health".

The English summary is being prepared. Showing the original description.

Fans out multiple agents in parallel via the Workflow tool to investigate a codebase question — bug root cause tracing, cross-file or cross-repository behavior tracing, "why does X happen for some cases but not others" questions — then synthesizes a ranked, file:line-cited answer in chat. The point of this skill is explicitness: it announces the investigation dimensions and agent count before launching, narrates progress, and reports a structured synthesis, rather than leaving multi-agent orchestration as an implicit background behavior the user can't see into. Supports investigations that span more than one local repository on disk (e.g. a backend service and a client app that talks to it). Investigation only — does not edit code or fix anything; pair with another skill or a follow-up request for that. Use when the user wants to investigate a bug, trace behavior across files or repositories, understand why something happens under some conditions but not others, or explicitly asks for a parallel/multi-agent investigation. Trigger phrases: "parallel-investigate", "/parallel-investigate", "並列で調査して", "並列調査", "複数エージェントで調べて", "複数エージェントで並列調査して", "investigate this in parallel", "fan out and investigate", "investigate across repos", "trace this across repositories".

The English summary is being prepared. Showing the original description.

Run Playwright CLI commands via Bash for test execution, code generation, browser management, reporting, and debugging. Covers the full `npx playwright` surface: test, codegen, install, show-report, show-trace, screenshot, pdf, open, clear-cache, merge-reports, and more. Use when the user asks to run playwright tests, generate test code, install browsers, view a test report or trace, take a page screenshot or PDF, open a URL in a specific browser, clear the playwright cache, merge shard reports, debug tests, or use playwright UI mode. Also covers the guided workflow for turning a codegen recording into a structured test suite with assertions, resilient selectors, and page objects. Trigger phrases include "playwright test", "run playwright", "npx playwright", "codegen", "install browsers", "show report", "show trace", "playwright screenshot", "playwright pdf", "open in chromium", "open in firefox", "open in webkit", "clear playwright cache", "merge reports", "shard tests", "playwright debug", "playwright ui mode", "record test", "run e2e tests with playwright cli", "playwright headed", "playwright retries", "update snapshots", "playwright grep", "list playwright tests", "codegen to test", "generate playwright test", "create test from recording", "turn recording into test", "bootstrap test suite", "record browser test", "generate spec from codegen".

The English summary is being prepared. Showing the original description.

Review local git changes from a PMBOK-based product management perspective. Analyzes changes against 7 PMBOK knowledge areas: Scope, Risk, Stakeholder, Quality, Integration, Schedule, and Resource management. Produces a structured report identifying project-level impacts and risks. The PMBOK analyst role itself lives in the `pm-review:pm-review` subagent; this skill is a thin orchestrator that gathers the change set and project context before delegating. Use when the user asks for a PM review, product management review, PMBOK analysis, project impact assessment, scope review, risk review, or stakeholder impact analysis of local changes. Trigger phrases include "pm review", "product management review", "PMBOK review", "project impact", "scope review", "risk review", "stakeholder impact", "pm-review", "review from PM perspective", "project management review".

The English summary is being prepared. Showing the original description.

Generate a blameless postmortem (incident report) from a Slack incident thread and publish it to Confluence. Fans out to subagents that collect evidence from Slack, GitHub, and Jira, merges their compact evidence cards into a sourced timeline with TTD/TTM/TTR, drafts the report (Overview, Impact, Root Cause & Contributing Factors, Timeline, Lessons, Action Items), independently fact-checks every factual claim against the original sources, then publishes to Confluence and optionally files action-item Jira tickets. Raw Slack messages, diffs, and logs never enter the main session — only the cards. Use when the user asks to write a postmortem, an incident report, a retrospective for an outage, or to turn an incident thread into a document. Trigger phrases include "postmortem", "ポストモーテム", "incident report", "障害報告", "障害レポート", "インシデントレポート", "障害の振り返り", "write a postmortem", "postmortem from slack", "incident writeup", "outage report", "RCA", "root cause analysis", "/postmortem".

The English summary is being prepared. Showing the original description.

Review a teammate's pull request. The reviewer role (multi-lens analysis, severity calibration, suggestion writing) lives in the `pr-review:pr-review` subagent; this skill is the orchestrator — it resolves the PR, fetches diff and changed files, delegates analysis to the subagent, stages the resulting comments for user approval, then submits a batch review via the GitHub API. NOT for self-review of your own PR (use `self-pr-review` instead). Trigger phrases include "review PR #123", "code review PR", "peer review", "check this PR", "give PR feedback", "review pull request", "review someone's PR".

The English summary is being prepared. Showing the original description.

Run a multi-model adversarial mutual review with facilitator synthesis: 2+ panelists (different model families where possible — use codex-server / codex-cli for the external-family seat) independently answer, adversarially critique each other across rounds, and the main session acts as facilitator, synthesizing agreements, live disagreements, and calibrated confidence into one answer. Use ONLY on high-stakes, hard-to-reverse claims, designs or decisions, and only when the user EXPLICITLY asks to debate or adversarially review with multiple models — "discuss with Opus and Codex", "red-team this", "devil's advocate", 敵対的レビュー, 相互レビュー, 多モデル討論, 議論させて. A full run costs ~6 subagent/CLI dispatches: state the panel size and round count and get a go-ahead before launching. Where the Workflow tool is available, run the panel as a Workflow (judge-panel / adversarial-verify) instead of ad-hoc fan-out. Do NOT self-trigger on a bare "are you sure?" — that is a cue to OFFER the panel, not to run it.

The English summary is being prepared. Showing the original description.

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

The English summary is being prepared. Showing the original description.

Sync a session-recap directory (summary.md + note.md + meta.json) to Notion under the explicit "My Agent Notes / Session Recaps" database via the notion-cli skill. The Notion target is fixed by design — the value of this skill is being explicit about its destination, not configurable. Appends to the shared session-recap manifest on success and retries previously-failed uploads on next invocation. Cleanup and retention are owned by session-recap, not this skill. Standalone — pass a recap dir path, or invoke in retry-only mode. Auto-invoked by session-recap via the chain in its ~/.claude/session-recaps/.recap-config.json. Use when the user says "recap to notion" / "Notionに recap を上げて" / "recap upload" / "/recap-to-notion" / "recap retry" / "再アップロード" / "Notion同期".

The English summary is being prepared. Showing the original description.

Review local git changes from 8 expert perspectives by spawning the matching reviewer subagents in parallel. Produces a consolidated report with Critical/Important/Nice-to-have severity. Lightweight pre-commit or pre-push quality gate — no PR or branch push required. Use when the user asks to review local changes, check changes before committing, get a team review of working tree changes, or run a pre-commit review. Trigger phrases include "review local", "review my changes", "review local changes", "pre-commit review", "review before commit", "review before push", "team review my changes", "check my changes", "review working tree", "local code review", "review diff", "review my diff".

The English summary is being prepared. Showing the original description.

Generate test scenarios from git branch changes. Compares current branch to main/master, identifies changed files, classifies them by type (frontend, API, backend, config), and generates test scenarios covering those changes. Produces a Markdown report with embedded screenshots for UI changes and CSV files compatible with the e2e-test skill for automated execution. Captures screenshots for frontend changes via the playwright-cli skill (no MCP browser server required). Diff-driven — not to be confused with the test-scenario skill, which works from a natural-language feature description instead. Use when the user asks to generate test scenarios, create test cases from changes, analyze branch for testing, generate test plan from diff, create e2e scenarios from code changes, or build test coverage for a branch. Trigger phrases include "generate test scenarios", "test scenarios for this branch", "create test cases from changes", "what should I test", "generate test plan", "test coverage for my changes", "scenario generator", "test scenario generator", "generate scenarios from diff", "create e2e scenarios", "test scenario from branch".

The English summary is being prepared. Showing the original description.

Self-review loop for YOUR OWN PR — request AI reviews (Copilot + Gemini), apply their fixes, push, re-request, and repeat until clean. NOT for reviewing someone else's PR. Use when the user asks to self-review their PR, run the AI review loop, or wants Copilot + Gemini to review their own code. Trigger phrases include "self-review", "self-pr-review", "review my PR", "AI review my PR", "review loop", "copilot + gemini review", "run self-review on my PR".

The English summary is being prepared. Showing the original description.

Install a PreCompact hook that auto-generates .agent/local/HANDOVER.md before context compaction, plus a SessionStart hook that restores context from a previous handover. Run once to install, then it works automatically forever. Use when the user says "handover", "setup handover", "install handover hook", or wants seamless context transfer between sessions.

The English summary is being prepared. Showing the original description.

Read a Claude Code session's transcript and produce two markdown artifacts plus a meta.json: a scannable Summary (TL;DR, key terms, files, decisions, open threads) and a complementary Detailed Note (full glossary, chronological flow, command-by-command annotations, pitfalls). The output language follows the watched session's dominant language (>= 50% Japanese characters → Japanese, otherwise English; overridable via --language). Standalone — pass a session ID, or omit to pick from recent sessions in the current directory. After generation, dispatches a configurable chain of follow-up skills (default ["recap-to-notion"]) read from ~/.claude/session-recaps/.recap-config.json. Owns the manifest schema and runs cleanup of confirmed-uploaded local recap dirs past retention. Read-only on the transcript itself. Use when the user says "session recap" / "セッションのまとめ" / "セッションサマリ" / "学びをまとめて" / "用語集を作って" / "summarize the session" / "recap session" / "session note" / "セッションのノート" / "/session-recap" / "セッション解説まとめ" / "recap掃除" / "recap cleanup" / "古いrecap削除".

The English summary is being prepared. Showing the original description.

Watch another running Claude Code session in real time and narrate its activity in Japanese with detailed term-by-term explanations. By default targets a session active in the current working directory; if multiple are active, asks the user to pick. Can also target a specific session by ID. Read-only on the watched session. After the watch ends, invokes session-recap; any further chain (e.g. recap-to-notion for Notion sync) is configured by session-recap's own ~/.claude/session-recaps/.recap-config.json, not this skill. Use when the user says "session監視" / "監視して" / "別のClaudeを観察" / "他のセッションを見ていて" / "Aliseを観察" / "watch session" / "observe" / "observe claude" / "observe session" / "observe the session" / "Observe" / "/session-watch" / "セッションウォッチ" / "オブザーブ" / "他のセッション解説" / "別Claudeをモニタ".

The English summary is being prepared. Showing the original description.

Retrofit the OIAE self-improvement loop to existing skills and analyze feedback to propose evidence-based amendments. Adds Retrospective, Feedback Check, and version tracking to skills that lack them. Reads feedback/log.md to identify recurring issues and propose targeted skill improvements. Use when the user asks to improve a skill, retrofit feedback to a skill, add the improvement loop, fix a skill based on feedback, or analyze skill performance. Trigger phrases include "improve skill", "retrofit skill", "add feedback loop", "skill keeps failing", "fix skill", "analyze skill feedback", "skill performance", "add retrospective", "skill improvement".

The English summary is being prepared. Showing the original description.

Operate Slack from the terminal via `slack-cli` (@urugus/slack-cli). Send messages, check unreads, search history, upload files, manage reactions/pins, schedule messages, and manage channels — all through Bash commands. Prefer this skill over `mcp__slack__*` MCP tools when you need: scheduling, unreads, search with pagination, reactions/pins, file uploads, multi-workspace profiles, canvas operations, or jq pipelines for filtered output. Trigger phrases include "slack-cli", "slack cli", "send slack message", "check slack unreads", "slack history", "search slack", "schedule slack message", "slack channel", "upload to slack", "slack reactions", "slack pins", "slack canvas", "slack users", "slack unread".

The English summary is being prepared. Showing the original description.

Create Jira tickets from Slack conversations, optionally with Confluence documentation pages. Reads Slack threads/channels/search results via slack-cli, analyzes the conversation to extract problems, participants, decisions, and action items, then creates Jira issue(s) via jira-cli with the conversation context. A single conversation may produce multiple tickets if it covers distinct topics. For long or complex conversations (>15 messages), recommends creating a Confluence documentation page via confluence-cli with a context-aware format (postmortem for bugs, PRD for features, slim summary for tasks). Supports input as Slack permalink URL, channel name, thread timestamp, or search query. Presents drafts for interactive review before creating. Trigger phrases include "slack to ticket", "slack-to-ticket", "create ticket from slack", "jira ticket from slack", "create ticket from #channel", "create ticket from thread", "slack conversation to jira", "ticket from slack thread", "jira from slack", "slack to jira", "create issue from slack".

The English summary is being prepared. Showing the original description.