aktsmm

aktsmm/Agent-Skills

Agent

Business operations orchestrator: Task classification, sub-agent delegation, report generation coordination.

aktsmm/Agent-Skills

Agent

Report generator agent: Automated daily/weekly/monthly report generation with review loop.

aktsmm/Agent-Skills

Agent

Report review agent: Evaluate reports from results-oriented perspective and propose improvements.

aktsmm/Agent-Skills

Agent

Task management agent: Task creation, updates, classification, and progress tracking.

aktsmm/Agent-Skills

Agent

Work inventory agent: Work analysis, time allocation, improvement proposals, and manager PR support.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Operate a reusable technical book manuscript workspace with writing structure, reader persona SSOT, review rules, and optional Markdown to Re:VIEW/PDF support. Use when organizing a book manuscript repo, defining or reviewing target readers, standardizing chapter/section files, setting writing/review agents, handling…

aktsmm/Agent-Skills

Agent

Markdown to Re:VIEW conversion agent.

aktsmm/Agent-Skills

Agent

Manuscript review agent with P1/P2/P3 priority system.

aktsmm/Agent-Skills

Agent

Manuscript writing agent for the book project.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Safely audit, classify, deduplicate, and reorganize bookmarks or favorites in Google Chrome and Microsoft Edge while preserving intentional toolbar shortcuts, signed-in profiles, and sync state. Use when asked to organize browser bookmarks/favorites, clean duplicate bookmarks, redesign bookmark folders, classify…

aktsmm/Agent-Skills

Skill Claude CodeCodex

Browser automation using Playwright MCP, CDP, and direct WebSocket CDP for web testing, UI verification, and form automation. Use when navigating websites, clicking elements, filling forms, taking screenshots, testing web applications, reusing an existing browser session, or troubleshooting CDP / iframe / modal / file…

aktsmm/Agent-Skills

Skill Claude CodeCodex

A development guide for building Chrome and other browser extensions, including extensions using WXT and Chrome's Manifest V3 format. Browser extensions are small programs that add features to a browser.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Guide for simplifying and refining code after coding sessions. Use when cleaning up complex code, reviewing PRs for readability, or applying consistent refactoring patterns. Triggers on simplify code, refactor, clean up, code review, コード整理, リファクタ, 複雑さ削減, コードレビュー.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Turn any context (blog URL, pasted article, PR diff, meeting notes, release notes, raw prompt) into a narrated explainer mp4 with slides, subtitles, and optionally a talking-head avatar. Uses a free local stack (Pillow + edge-tts + ffmpeg) with optional SadTalker for the avatar. Use when the user says "動画化"…

aktsmm/Agent-Skills

Skill Claude CodeCodex

Customer workspace initialization skill. Provides inbox (information accumulation), meeting minutes management, and auto-classification rules. Use for "setup customer workspace" or "add inbox feature" requests. Triggers on customer workspace, 顧客ワークスペース, inbox 追加, 議事録管理, 顧客フォルダ作成.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Generate draw.io editable diagrams (.drawio, .drawio.svg) from text, images, or Excel. Orchestrates 3-agent workflow (Analysis → Manifest → SVG generation) with quality gates. Use when creating architecture diagrams, flowcharts, sequence diagrams, or converting existing images to editable format. Supports Azure/AWS…

aktsmm/Agent-Skills

Skill Claude CodeCodex

Run a Duck Critic producer-critic loop: you (main) keep producing the plan/code/tests and gate your own work at checkpoints with a different-model critic, revising until it passes. Use when asked for rubber duck, ラバーダック, 別モデルレビュー, second opinion, critic, code review, design review, plan critique, or review by another…

aktsmm/Agent-Skills

Skill Claude CodeCodex

Export the current chat session as a structured Markdown work timeline or blog-draft seed. Use when the user asks for a session log, work log, timeline, 作業ログ, ブログネタ, blog draft, article seed, Zenn, Qiita, or はてな. Do not use for verbatim dialogue export or distilled reusable knowledge only.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Run an explicit end-to-end goal loop with frozen Scope/criteria, worker delegation, external verification, evaluator review, and bounded retries. Use when the user asks for 'goal-loop', 'ゴールまで回す', '必ずやり遂げる', 'loop until done', 'until it actually works', or an orchestrator + evaluator loop. Do not use for ordinary…

aktsmm/Agent-Skills

Skill Claude CodeCodex

Remove AI-generated tone and make writing sound more human in Japanese and English. Use when reviewing drafts for AIっぽさ, humanizing article/blog text, 文体チェック, AI感を消したい, or ChatGPT tells.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Transcribe local MP4/M4A/MP3/WAV/WEBM audio or video with ffmpeg and Whisper, then optionally produce diarized transcripts, customer-facing meeting minutes, action items, and PPT-ready summaries. Use when: 文字起こし, transcription, transcribe mp4, meeting transcript, mp4から文字起こし, 録画から議事録, 顧客向け議事録, 話者分離, diarization…

aktsmm/Agent-Skills

Skill Claude CodeCodex

Route Microsoft Graph work in this workspace. Use when users want to read or write Outlook mail, calendar events, contacts, OneDrive or SharePoint files, Teams, Planner, To Do, users, groups, directory data, or arbitrary Microsoft Graph endpoints from VS Code. Prefer WorkIQ for common read scenarios. Use Microsoft…

aktsmm/Agent-Skills

Skill Claude CodeCodex

GPU-optimized OCR using Surya. Use when: (1) Extracting text from images/screenshots, (2) Processing PDFs with embedded images, (3) Multi-language document OCR, (4) Layout analysis and table detection. Supports 90+ languages with 2x accuracy over Tesseract.

aktsmm/Agent-Skills

Skill Claude CodeCodex

Run a reusable opportunity-to-artifact workflow: discover unmet needs, set up workspace factories, schedule recurring commander/worker/reporter prompts, batch-refine many items, optionally use SQLite state, build small artifacts, review quality, and track outcomes. Use when the user wants to repeatedly create apps…