skills

アプリ組み込み AI チャットフロントエンドの設計・実装ガイド。 前半は言語非依存の抽象設計パターン（ストリーミングファースト、チャット状態マシン、 メッセージモデル、楽観的UI、エラーリカバリ、UX原則、マルチセッション、サーバー設計原則）、 後半は Vercel AI SDK (useChat) による TypeScript 具体実装。 フレームワーク非依存（Next.js, React SPA, Vue, Svelte, SvelteKit, Nuxt 対応）。 Use when チャット機能を追加したい、AIチャットUIを作りたい、useChat を使いたい、 ストリーミングチャットを実装したい、チャットボットUIを組み込みたい、 AI SDK でチャットを作る、またはチャットUIの設計パターンを整理・レビューしたい時。 Python/Go/Rust 等の非 TypeScript 環境でも設計パターン部分は適用可能。 既存のチャットUIのレビュー・改善にも使える。 対象外: チャット以外の AI SDK 用途（テキスト生成のみ、画像生成、エンベディング等）。

Use this skill whenever the user asks to create, structure, review, or refine a business plan, new business proposal, growth strategy, GTM outline, or venture hypothesis. Build a rational, persuasive business plan with reader-specific framing and bottom-up numerical planning. Distinguish researched facts from benchmarks and estimates, use frameworks only as supporting tools, and forecast outcomes from causal drivers instead of reverse-engineering a desired result. Use it even when the user only says "事業計画", "戦略を考えたい", "新規事業を整理したい", or asks for AI agent / SaaS business planning without naming any framework.

デジタル庁のダッシュボードデザイン実践ガイドブックに基づく、見やすいダッシュボード設計・作成のガイド。グラフ選び、レイアウト、カラーパレット、アクセシビリティ、チェックリストを網羅。Use when ダッシュボードを新規作成したい、既存ダッシュボードを改善したい、可視化設計をレビューしたい、または軽量HTML・Grafana・SQLiteベースのダッシュボード設計方針を決めたい時。

Use this skill whenever the user asks for brainstorming, ideation, concept expansion, service improvement ideas, strategy options, workshop structure, or says thinking is stuck and needs more perspectives. Select and apply one or more brainstorming frameworks based on the user's goal, solo vs group setting, divergence vs convergence need, and business vs creative context. Use it even if the user does not name a framework.

Design principles for building CLI tools that LLM/AI agents can safely and reliably operate. Provides 7 core principles (Machine-readable, Non-interactive, Idempotent, Safe-by-default, Observable, Context-efficient, Introspectable) with scorecard, templates, and anti-patterns. Use when: (1) designing new CLI tools for agent use, (2) improving existing CLIs for agent compatibility, (3) reviewing CLI design for agent-friendliness, or (4) need guidance on JSON output formats, exit codes, authentication flows, or self-describing CLI patterns.

Fast, script-friendly CLI for Google services via `gog`. Use this skill whenever the user needs to work with Gmail, Google Calendar, Drive, Docs, Sheets, Slides, Forms, Apps Script, Contacts, Tasks, People, Chat, Classroom, Groups, Admin, or Keep from the terminal, especially for Google Workspace automation, account setup, OAuth/client configuration, service accounts, domain-wide delegation, or JSON/scriptable workflows. Prefer this skill even when the user does not mention `gog` explicitly but is clearly trying to automate or inspect Google services from a CLI or agent workflow.

Audit and reorganize an existing test suite to remove outdated tests, reduce duplication, and isolate external dependencies from unit tests. Use this skill whenever the user wants to clean up tests, find obsolete or redundant tests, detect unit tests that directly hit APIs/URLs/timers/commands/databases/filesystems/env state, improve mock boundaries, reduce flakiness, or clarify the boundary between unit and integration tests. Use it even if the user only says things like "整理したい", "モック化したい", "テストが遅い", or "古いテストを掃除したい".

Create and maintain `.wt/setup` bootstrap scripts for git worktree environments. The `.wt/setup` script is a repository-local convention executed automatically by supporting tools (e.g. wt) when creating new git worktrees. Use when: (1) a project needs a `.wt/setup` script, (2) setting up worktree-aware bootstrap for a new repo, (3) reviewing or fixing an existing `.wt/setup`, or (4) the user mentions "wt setup", "worktree setup", ".wt/setup", or "bootstrap worktree".

Delegate autoresearch tasks to a headless Claude Code sub-agent process. Use when the current agent needs to run any autoresearch command (autoresearch, ship, plan, security, debug, fix, scenario, predict, learn) as an autonomous background or foreground subprocess via `claude --dangerously-skip-permissions -p`. Ideal for long-running autonomous loops, overnight improvement runs, CI/CD pipeline integration, and fire-and-forget shipping workflows. Triggers on: "run autoresearch in background", "headless autoresearch", "delegate autoresearch", "spawn autoresearch", "autoresearch sub-agent", "autoresearch agent", or any request to run autoresearch non-interactively.

Summarize YouTube videos by extracting and analyzing auto-generated subtitles. Use when the user provides a YouTube URL and asks to summarize, explain, or analyze a video's content. Triggers on patterns like "this video summarize", "summarize this YouTube", "what does this video say", or any request involving a youtube.com or youtu.be URL combined with summarization/analysis intent. Supports both Japanese and English videos.

Contribute new profiles to tumf/greats-soul-archive. Use when the user wants to add, submit, or open a PR for a new person/character profile, scaffold IDENTITY.md/SOUL.md/sources.md, add meta.yml (category/tags), run scripts/build_index.py, or follow the repo's contribution rules.

Create specialized OpenCode agents with proper configuration for primary agents and subagents. Use when the user wants reusable OpenCode agent profiles, needs `agent/*.md` files or `opencode.jsonc` agent entries, wants to configure prompts/models/tool access, or needs to split work between a primary agent and subagents safely.

Create custom OpenCode commands with proper structure, trigger descriptions, arguments, and configuration. Use when the user wants reusable slash/command workflows in OpenCode, needs `.opencode/commands/*.md` or `opencode.jsonc` entries, wants command templates with `$ARGUMENTS`, or needs to override/extend built-in commands safely.

Introduce OpenSpec into an existing codebase by deriving baseline specs from current behavior, then switch future work to change-driven development. Use when a project already has substantial implementation but no trustworthy spec baseline, when the user wants to bootstrap `openspec/specs/` from current behavior, or when a team needs to capture present-day contracts before making further changes.

Design and implementation guidance for maintainable Rust CLIs with strong ergonomics, machine-friendly behavior, testable structure, and release automation. Use when creating or refactoring a Rust command-line tool, choosing crates like clap/anyhow/tracing/serde_json, improving command UX, adding JSON output, tightening test/release workflows, or making an existing CLI safer for agents and automation.

Collect and answer questions about Japanese subsidies/grants (補助金・助成金) with up-to-date sources. Use when a user asks: which programs they qualify for, eligibility, deadlines, required documents, application steps, or where to find official calls for proposals and past award/adoption examples (e.g. J-Grants, METI/SME Agency, MHLW, prefectures/municipalities). Includes workflows and scripts for web search + structured extraction with citations. This skill is methodology-focused rather than program-specific: it provides reusable ways to discover and verify official information across many programs.

Scaffold opinionated Python projects with uv as the package/project manager and `uv init` as the bootstrap step. Use when creating or standardizing a Python repository that should include: git initialization, Makefile-driven `test`/`format`/`lint`/`typecheck` workflows, `prek` git hooks, strict typed data models with Pydantic, and Hatch-based semantic version bumps via `make bump-patch`, `make bump-minor`, and `make bump-major`. Also use when you want a solid generic Python repo baseline with README, LICENSE, `.gitignore`, `.editorconfig`, CI, coverage, settings management, and typed-package scaffolding.

Solve user questions with defensible Fermi estimates using explicit assumptions, source-backed inputs, uncertainty ranges, and sensitivity analysis. Use when exact data is unavailable or too slow to collect but the user still needs a quantitative answer for counts, market size, demand, costs, revenue, capacity, timing, or operational scale. Prefer quick primary-source lookup when it exists; use Fermi estimation as fallback or cross-check when direct measurement is unavailable, stale, fragmented, or too slow. Autonomously gather accessible evidence, prefer current primary sources, and drive to a conclusion without asking for approval.

Open source publication and release hygiene for repositories and CLIs (language-agnostic): choose and add LICENSE, prepare README/CONTRIBUTING/SECURITY/CODE_OF_CONDUCT, standardize versioning/tags/releases and release notes, set up CI matrices, quality gates (pre-commit/pre-push), and safe-by-default automation/bootstrapping. Use when preparing a project to be published publicly (GitHub/GitLab), cutting a release, or standardizing repo tooling across languages.

Propose concrete, high-leverage product/UX improvements to increase a software project's appeal and retention. Use when asked to generate product improvement proposals, UX ideas, onboarding/doc improvements, packaging/pricing positioning suggestions grounded in repo evidence, and prioritized MVP plans (ideation only; no implementation).

Create and maintain OpenClaw agent workspaces using the "Memory as Documentation" layout. Use when you need to: (1) create a new OpenClaw workspace/profile, (2) generate bootstrap files (AGENTS.md, SOUL.md, USER.md, IDENTITY.md, TOOLS.md, MEMORY.md, memory/YYYY-MM-DD.md), (3) keep instructions/persona/memory separated and token-lean, or (4) set up a safe git backup of an OpenClaw workspace without committing secrets.

Comprehensive Clawdbot configuration and skills system management. Use when working with Clawdbot setup, configuration files, creating/modifying AgentSkills-compatible skills with YAML frontmatter, troubleshooting agent behavior, managing channels, workspace, sandbox, or multi-agent routing.

Comprehensive web scraping, crawling, and data extraction toolkit powered by Firecrawl API. Provides scripts for single-page scraping (scrape.py), web search (search.py), URL discovery (map.py), multi-page crawling (crawl.py), structured data extraction (extract.py), and autonomous data gathering (agent.py). Use when you need to: (1) extract content from web pages, (2) search and scrape the web, (3) discover URLs on websites, (4) crawl multiple pages, (5) extract structured data with JSON schemas, or (6) autonomously gather data from anywhere on the web. Requires FIRECRAWL_API_KEY environment variable.

Slack Web API automation via the slack-rs CLI (Rust). Use when you need to authenticate to Slack via OAuth (PKCE), manage multiple workspace profiles, call arbitrary Slack Web API methods (e.g. chat.postMessage, conversations.list, users.info), and run safe scripted Slack operations from the terminal. Includes tunnel-assisted remote login (see auth login --help), encrypted profile export/import, and a write-safety guard via SLACKCLI_ALLOW_WRITE. Credentials are stored in file-based storage under ~/.config/slack-rs/.