surfmind のスキル

Extracts factual claims from selected text or a page and checks each against the visible context and available sources, flagging what is supported, weakened, contradicted, or still unverified. Use when the user says "fact check this", "verify", "is this true", "check the sources", or asks about a page's accuracy, credibility, or possible misinformation.

Finds credible primary or authoritative sources that verify, challenge, or strengthen the claims in selected or visible text, weighing each for authority, recency, and whether it actually supports the claim. Use when the user says "find a source", "back this up", "is there evidence for this", "cite this", "find references", or asks for citations, primary sources, or proof for a statement.

Finds the technical terms, acronyms, and domain phrases on the current page and defines each in plain language, with why it matters in this context. Use when the user says "explain the jargon", "define these terms", "what does X mean here", "build a glossary", or asks about acronyms, abbreviations, or unfamiliar terminology on the page.

Converts visible web tables — HTML tables, pricing grids, comparison charts, reports — into clean Markdown tables that users can copy or download as CSV from the extension. Use when the user wants to extract, scrape, convert, copy, or export a table from a webpage.

Creates a staged learning plan from a topic, course page, or documentation set with goals, practice tasks, and checkpoints. Use when the user wants a "study plan", "learning roadmap", "curriculum", "syllabus", "learning path", or asks "how do I learn X" or "help me learn X in N weeks".

Turns a page, article, or product update into platform-ready social posts — Twitter/X threads, LinkedIn posts, and short captions with clear hooks, takeaways, and calls to action. Use when the user wants to repurpose content into social media, draft a tweet or thread, or write a LinkedIn or announcement post.

Explains a repository's purpose, structure, setup and run commands, key scripts, and the first files worth opening. Use when the user wants to understand a new repo or codebase — "what does this project do", "how do I get started", "give me a codebase overview", "onboard me to this repo".

Drafts and refines replies for email, chat, Slack, comments, support tickets, and follow-up messages — adjusting tone and formality, summarizing prior context, and addressing every open question. Use when the user asks to reply to, respond to, or draft a response for a message, email, comment, or support thread.

Explains academic papers, abstracts, PDFs, and technical articles by laying out their method, findings, limitations, and implications. Use when the user says "explain this paper", "summarize this study", "read this paper", "break down this research", or asks what a paper or abstract means.

Summarizes product reviews into recurring pros, cons, reliability issues, buyer-fit notes, and repeated red flags. Use when the user asks to summarize, analyze, or compare product reviews, customer feedback, ratings, or user reviews on a store, app, restaurant, or marketplace listing.

Turns messy notes, pages, or selected text into a structured outline with headings, key points, evidence, and gaps. Use when the user wants to "organize my notes", "create an outline", "structure my thoughts", "outline from notes", or pull bullet points and key points out of rough material.

Creates a summary that adapts to the source, such as an article, email thread, chat, PDF, document, image, or transcript, while surfacing the key points, decisions, and takeaways. Use when the user says "summarize", "TLDR", "key points", "recap", "overview", or "condense this".

Rewrites, rephrases, and adapts text to match the tone, voice, sentence structure, vocabulary, and formatting of a reference example while preserving meaning and facts. Use when the user asks to match a writing style, mimic a voice, copy a tone, or write like a provided sample.

Translates and localizes text for a target language, region, and audience — adapts idioms, units, currency, dates, examples, formality, and tone while preserving the original message. Use when the user asks to translate, localize, internationalize (i18n), or adapt content for a specific country, language, or cultural audience.

Reviews a landing page for message clarity, audience fit, proof, calls to action, friction, and conversion improvements. Use when the user wants feedback on a landing page, homepage, pricing page, or signup page, asks for a website copy or CRO review, or wants to improve conversions or funnel performance.

Finds legitimate discount codes for the store the user is shopping, points to the sources most likely to carry a working code, and flags suspicious or unverifiable coupon claims. Use when the user asks for a "promo code", "coupon code", "discount code", "voucher", "deal", or "savings" for an online store, or asks "is there a code for this".

Converts a code snippet from one programming language to another while preserving behavior and flagging library, runtime, and type-system differences. Use when the user asks to translate, port, rewrite, or convert code between languages — "port this to Python", "rewrite in Rust", "convert Java to Go".

Builds and applies a consistent glossary for translation — extracting recurring domain terms, suggesting preferred translations, and flagging inconsistencies so terminology stays uniform across a page or document. Use when the user needs term consistency across translations or localization, mentions a glossary, terminology, or terminology database, or asks to translate domain material uniformly.

Lists the citations, links, and referenced sources a page relies on and explains what each one appears to support, flagging anything missing, circular, or weakly sourced. Use when the user says "list the sources", "what does this cite", "show the references", "check the citations", or asks for a page's bibliography, footnotes, or links.

Breaks a regular expression down into plain-language parts with examples of what it matches and what it rejects. Use when the user asks to explain, decode, or understand a regex, regexp, or pattern — "what does this regex match", "explain this pattern", a .match/.test call.

Explains how to pronounce and naturally use a selected word or phrase, with register, meaning, collocations, and example sentences. Use when the user asks "how do you pronounce / how do you say this", "what does X mean", or wants vocabulary and usage help for a foreign-language word or phrase.

Evaluates whether a portfolio project, side project, or resume project idea is worth building to land a target role, scoring role signal, uniqueness, demo ability, metrics, time to a working version, and interview-story potential. Use when the user asks if a project idea is worth building, wants to evaluate side projects for a job search, or wants to pick a project that signals to hiring managers.

Generates strong opening lines for a topic or page using curiosity, contrast, story, and data-driven angles while avoiding unsupported clickbait. Use when the user asks for a hook, intro, lead, headline, first sentence, or attention-grabbing opener for a post, article, video, newsletter, ad, or landing page.

Judges whether a product's price is worth it by checking typical prices, alternatives, total cost, and timing, then giving a clear buy / wait / skip call. Use when the user asks "is this a good deal", "should I buy this", "is this worth the price", "too expensive", or wants a price check or comparison before purchasing.