Research & Learning skills

Conduct Critical Decision Method (CDM) interviews to elicit expert reasoning strategies (L3 knowledge) from practitioners about specific challenging past incidents. Use when capturing expertise for skill development, preserving knowledge before practitioner departure, building post-incident learning artifacts, or investigating decisions in complex sociotechnical systems. Outputs structured incident reconstructions with cues, decisions, alternatives considered, and counterfactual analysis suitable for distillation into skills or training material.

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

Naturalistic causal reasoning for failures and disputed attribution. Use when postmortems or root-cause debates need reframing. NOT for causal inference, fault trees, or fully observed failures.

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

Revise the Harbor Book so prose, drawings, and marginalia explain the same argument without unpublished development-document dependencies. Use for chapter additions, substantive rewrites, caption editing, visual exposition, and eliminating internal ADR citations.

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

Research AI coding assistant products, audiences, user stories, social proof, hacks, and unmet needs for apps like Cursor, Claude Code, Codex, Warp Code, Devin, Windsurf, GitHub Copilot, Cline, Aider, and homegrown agent stacks. Use when designing or positioning agentic developer tools, Port Daddy Agent Harbor, swarm consoles, background coding agents, or competitive/product research for AI software engineering. NOT for implementing the coding agent runtime, generic market research, or UX mockups without developer workflow evidence.

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

Use for insight, reframing, contradiction, impasse, and anomaly-driven problem solving when execution effort no longer helps. NOT for routine optimization, error correction, or well-specified tasks with known solution paths.

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

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

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

Apply AlphaGo-style patterns: learned priors plus search, mixed evaluators, self-play, and asynchronous fast/slow loops. Use for intractable search and compute allocation. NOT for basic supervised learning, tractable optimization, or domains without search bottlenecks.

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

Generates creative, research-backed domain name ideas and checks availability with competitor analysis, pattern recognition, and quality scoring. Use when brainstorming brandable domains for a product or project.

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

実行中・実行済みのプログラムやジョブの状況を知りたいとき，自分が起動したものか無関係のものかを問わず調べて答える．「どうなってる？」「学習状況は？」「進捗見せて」など，実行そのものを頼んでいるわけではなく既存の何かの様子を尋ねられたときに使う．新しく実行を頼まれたときは /ops:exec を使う．

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

ユーザーからの修正・指摘を受けた際の学習記録と自己改善ループ。ユーザーから「違う」「そうじゃない」「前にも言ったけど」といった修正を受けた時、同じミスを繰り返していると気づいた時、セッション開始時の教訓確認で使う。修正やフィードバックを受けたら必ずこのスキルを参照する。

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

repositoryを調査し、`docs/PLAN/YYMMDD_{slug}.md` にPhase、Gate、完了状態、実行ルール、チェック項目を持つ自己完結した永続計画を作成または再構成する。Use when the user asks for simple-plan、チェックリスト式の計画、複数停止点を持つ中規模作業、段階的なapp分割やlocal migration、production前Gate、または既存planの構成変更。単発Sprintでは収まらないが、詳細なworker委任計画までは不要な作業向け。既存planをそのまま実行・再開するだけの場合は使わない。

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

HeroUI Pro React の新リリースを公式サイトから調査し、 指定されたリリースノートドキュメントを追記更新するスキル。 「できるようになったこと・作れるようになったもの」を主軸に、 自然な日本語でユーザーストーリーとして記述する。 Trigger: HeroUI Pro リリースノート更新, heroui-pro release notes, heroui-pro更新, /dev:heroui-pro-release-notes

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

品質管理、不適合調査、根本原因分析、是正措置、サプライヤー品質管理に関する 体系化された専門知識。規制下の製造環境で15年以上の経験を持つ品質エンジニアの 知見に基づく。FDA、IATF 16949、AS9100環境を網羅。NCRライフサイクル管理、 CAPAシステム、SPC解釈、監査方法論を含む。不適合の調査、根本原因分析、 CAPA管理、SPCデータの解釈、サプライヤー品質課題の対応に使用。

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

コーディング前のリサーチワークフロー。カスタムコードを書く前に既存のツール、ライブラリ、パターンを検索する。リサーチャーエージェントを起動。

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

市場調査、競合分析、投資家デューデリジェンス、業界インテリジェンスをソース帰属と意思決定指向のサマリーとともに実施。市場規模推定、競合比較、ファンドリサーチ、テクノロジースキャン、ビジネス意思決定に活用するリサーチに使用。

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

firecrawlとexa MCPを使用したマルチソースディープリサーチ。Webを検索し、調査結果を統合し、ソース帰属付きの引用レポートを提供。トピックについてエビデンスと引用付きの徹底的なリサーチが必要な場合に使用。

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

フックを介してセッションを観察し、信頼度スコアリング付きのアトミックなインスティンクトを作成し、それらをスキル/コマンド/エージェントへ進化させるインスティンクトベースの学習システム。v2.1ではプロジェクトスコープのインスティンクトを追加し、プロジェクト間の汚染を防止します。

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

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、学習済みスキルとして保存。

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

Exa MCPによるニューラル検索。ウェブ、コード、企業リサーチに対応。ウェブ検索、コード例、企業インテリジェンス、人物検索、AIによるディープリサーチが必要な場合に使用。

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

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

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.

Use when the user names interviews, user research, a survey, a beta, or a pile of feedback to make sense of: the interview plan with a story opener, or ranked themes led by verbatim quotes with a roadmap verdict on each.

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

Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap recommendations.

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

Run cold outreach that gets replies: research the account, write a short specific first message, and follow up on a fixed schedule without nagging.

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