1.3万 件 ・ 関連度順
概要と使いどころ
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.
日本語の概要は準備中です。原文の説明を表示しています。
Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.
日本語の概要は準備中です。原文の説明を表示しています。
Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working with Genkit Go code involving generation, prompts, streaming, tool calling, or model providers.
日本語の概要は準備中です。原文の説明を表示しています。
Find every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code actually does (support-reply, nightly-digest) instead of one anonymous bucket. Use when the user pastes the Caveman discovery prompt, says "discover workflows", or asks to break LLM spend down by workflow. The repo should already route through the Caveman gateway (the caveman-setup skill does that part).
日本語の概要は準備中です。原文の説明を表示しています。
Manages datasets, tables, and jobs in BigQuery. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources (datasets, tables, views), or perform basic data ingestion and analysis.
日本語の概要は準備中です。原文の説明を表示しています。
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting deployment failures. Boundaries: - Only use for GCP-specific cloud infrastructure. - Only use for Terraform coding within the ADC context.
日本語の概要は準備中です。原文の説明を表示しています。
Generates Python code using BigQuery DataFrames (BigFrames), the pandas/scikit-learn-style API over BigQuery. Use when writing BigFrames code or doing pandas-style dataframe/ML work against BigQuery (e.g. in a notebook). Don't use for SQL-first workflows or the google-cloud-bigquery client library — use bigquery-basics.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
日本語の概要は準備中です。原文の説明を表示しています。
Evidence-first academic research workflow for topic ideation, scholarly search, paper reading, literature and systematic reviews, study and experiment design, statistics and data analysis, scientific figures, manuscript drafting and polishing, citation checks, peer review, rebuttals, submission packages, theses, and paper-to-presentation work. Use when an agent must plan, execute, audit, write, revise, or package research while keeping claims traceable to verified sources, data, analysis, or official requirements.
日本語の概要は準備中です。原文の説明を表示しています。
Use OpenClaw Manager (OCM) safely and correctly for OpenClaw environment lifecycle work, runtime installation/builds, release-shaped local builds, upgrades, migration/adoption, cloning existing user state, service supervision, gateway logs, dev worktrees, plugin testing, model/provider smoke tests, TUI/dashboard checks, cleanup, and concise reporting. Use whenever Codex is asked to use OCM, manage OpenClaw envs/runtimes/services, test OpenClaw with OCM, reproduce existing-user or new-user flows, or avoid breaking user state while working with OpenClaw.
日本語の概要は準備中です。原文の説明を表示しています。
Write press releases for product launches, funding announcements, partnerships, executive hires, and milestones using the Inverted Pyramid (AP journalism) and Ogilvy on Headlines (David Ogilvy, Ogilvy on Advertising). The lede answers Who/What/When/Where/Why in 40 words or fewer. The headline selects the right audience and promises a specific benefit. Use when the user asks for a press release, media release, news announcement, PR for X, launch announcement, funding announcement, or "write a press release". Reads brand voice and positioning from knowledge/. For pitching it to a journalist, see pr-pitch-writer. For the customer story behind it, see case-study-writer.
日本語の概要は準備中です。原文の説明を表示しています。
Write SEO-optimized long-form articles targeting specific keywords using the They Ask You Answer Big 5 framework (Marcus Sheridan). Articles are categorized by Big 5 type (Cost, Problems, Versus, Best/Reviews, How-To) and structured accordingly. The "answer first" rule applies to every article. Use when the user asks for an SEO article, blog post for ranking, "rank for keyword X", organic content, search-optimized post, pillar page, or content for organic traffic. Includes keyword targeting, search intent matching, internal linking suggestions, and meta tags. For improving an existing article, see copy-review. For deciding what to write about, see social-calendar pillars and icp-research. For repurposing it, see content-repurposer.
日本語の概要は準備中です。原文の説明を表示しています。
Write personalized pitch emails to journalists, podcasters, newsletter writers, and analysts using AIDA adapted for media pitching and Ryan Holiday's journalist psychology from "Trust Me I'm Lying." Different from press releases (use /press-release-writer for those). Use when the user asks to pitch a journalist, pitch a reporter, "get coverage in X", media outreach, podcast pitch, analyst briefing request, or wants to land a story. Reads brand voice and positioning from knowledge/. For the press release itself, see press-release-writer. For the underlying customer story, see case-study-writer.
日本語の概要は準備中です。原文の説明を表示しています。
Plan a monthly content calendar across channels using the Content Marketing Matrix (Dave Chaffey, Smart Insights) - Entertain/Inspire/Educate/Convince. Every post gets a quadrant label. The monthly calendar must hit 40% Educate, 40% Inspire+Convince, 20% Entertain. Produces a week-by-week posting schedule with topics, formats, channels, and asset links. Use when the user says "content calendar", "social calendar", "plan next month's content", "what should we post", "content plan", "editorial calendar", "schedule posts for the month", or wants a structured posting plan for LinkedIn, Twitter, email, or blog. Reads brand voice, ICP, and past learnings from knowledge/. For writing the individual posts, see linkedin-post, newsletter-writer or content-writer. For the campaign this sits inside, see campaign-brief. For the end-of-month review, see retro.
日本語の概要は準備中です。原文の説明を表示しています。
Generate user research interview scripts using Mom Test principles. Use this skill when: - You are preparing for user interviews or pilot observation sessions - You need a question bank organized by behavior, context, pain points, and workflow - You want interview guides that avoid leading questions and hypotheticals - You need per-persona interview guides - You are preparing for field visits or pilot debriefs
日本語の概要は準備中です。原文の説明を表示しています。
Design and write QA test artifacts - test cases, test plans, acceptance criteria, API test specs, and PR testability reviews. Use this skill whenever a QA engineer or SDET needs to translate requirements, user stories, or feature specs into structured test documentation. Trigger on phrases like "write test cases", "create a test plan", "define acceptance criteria", "review this PR for testability", "write API test specs", "test coverage for this feature", "what should we test", "how do we test this", or any request to structure what and how to test before execution begins. Also trigger when a developer asks "is this testable?" or a PM asks "what are the edge cases?".
日本語の概要は準備中です。原文の説明を表示しています。
Structure and run a post-interview candidate debrief. Use when the user says "run the debrief", "how do we decide on this candidate", "let's calibrate", "we need to make a hire/no-hire call", "prep the debrief meeting", or wants to structure the decision-making process after interviews are complete - even if they don't explicitly say "debrief". Also use when a recruiter wants to prevent groupthink or HiPPO effect (highest paid person's opinion) from dominating the decision.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user says "run customer discovery", "help me interview customers", "write customer interview questions", "validate my assumption", "talk to users", "synthesize customer interviews", "what are my customers saying", "user research for my startup", "mom test interview", "are we solving a real problem", or wants to extract real insight from conversations with potential or existing customers.
日本語の概要は準備中です。原文の説明を表示しています。
Build interactive "living workflow" flowcharts in the visual style of https://statuesque-starship-49757d.netlify.app/revenue-engine - vanilla HTML/CSS/JS files with a horizontal step bar, a vertical trunk that grows per step, tool-to-tool columns with animated payload pills between brand-marked tool nodes, alternating left/right step descriptions, and per-step outputs. Use whenever the user says "build a flowchart", "interactive flowchart", "living workflow", "revenue engine flowchart", "demand gen flowchart", "GTM workflow diagram", "process diagram with animations", "Nebor-style flowchart", or asks to recreate the workflow visual from the Nebor site. Always asks which flowchart to build (Revenue Engine / Demand Gen / CRM & RevOps / Custom) and waits for explicit approval of the step + tool + edge table before generating any files.
日本語の概要は準備中です。原文の説明を表示しています。
Turn raw customer material into evidence-backed personas and verbatim voice-of-customer language. Two modes - analyse sources the user already has (call transcripts, support tickets, survey responses, sales notes, reviews), or source new material from public places customers actually talk. Produces quoted pains, objections, and switch triggers that other skills consume, never invented ones. Use when the user says "customer research", "voice of customer", "what do our customers actually say", "we need real quotes", "analyse these call transcripts", "read our support tickets", "build a persona from data", "find what customers complain about", or when a persona is marked provisional. For structuring the finished persona into the knowledge base, see brand-context. For the JTBD persona template itself, see customer-persona.
日本語の概要は準備中です。原文の説明を表示しています。
Write marketing content in the user's brand voice using PAS (Problem-Agitate-Solution) and AIDA (Attention-Interest-Desire-Action) copywriting frameworks. Use when the user asks to write a LinkedIn post, blog article, email, ad copy, landing page section, social post, newsletter, or any short-to-medium form marketing content. Reads brand voice and ICP from knowledge/ so the output sounds like the company, not like generic AI. For improving copy that already exists, see copy-review. For a landing page specifically, see landing-page-writer. For a LinkedIn post, see linkedin-post. For long-form POV, see thought-leadership-writer.
日本語の概要は準備中です。原文の説明を表示しています。
Write structured use cases with main and alternate flows. Use when the user says "write a use case", "document the user flow", "use case diagram", "actor goal list", "main success scenario", "fully dressed use case", "what does the user do step by step", "system behavior for this feature", "interaction flow" - even if they don't explicitly say "use case".
日本語の概要は準備中です。原文の説明を表示しています。
Generate diagrams of any kind from a description, ticket, spec, or file. Outputs Mermaid syntax (renders natively in GitHub, Notion, Confluence, Obsidian, Slack with apps) plus an optional single-file HTML preview that renders the diagram in the browser. Use this skill when the user says: - "draw a flowchart", "create a diagram", "visualize this flow" - "sequence diagram", "state diagram", "ER diagram", "class diagram" - "user journey", "mindmap", "timeline", "gantt", "org chart" - "sankey", "quadrant chart", "git graph" - or pastes a ticket / spec / description and asks for a visual Picks the right Mermaid diagram type for the input, asks if ambiguous, then emits clean syntax + an optional preview file.
日本語の概要は準備中です。原文の説明を表示しています。
Transform ideas, outlines, or documents into structured slide content with clear titles, bullet points, and speaker notes. Adapts to presentation type (pitch decks, business reviews, technical workshops, educational talks). Use when user says "create slides", "build a deck", "pitch deck", "presentation structure", "talk structure", "keynote", "slide deck", "conference talk", or needs slide content for any format. Also trigger when user has content they want to present to an audience - even if they don't explicitly say "presentation" or "slides".
日本語の概要は準備中です。原文の説明を表示しています。