调研与学习技能

Research 3–5 confirmed same-industry or cross-industry websites and translate their brand narrative, page architecture, art direction, and visual-system evidence into one reusable Visual Reference Brief. Use when strong references are scarce, a site needs brand-led or premium positioning, a page lacks a narrative spine, or a key module lacks a credible design precedent. Do not create page content, a Design System, UI directions, HTML, or a permanent brand gallery.

中文简介正在准备中。当前显示原文说明。

Answer a factual question from the web, or enumerate what exists, with sources

中文简介正在准备中。当前显示原文说明。

Research a question across web and academic sources and produce a cited report.

中文简介正在准备中。当前显示原文说明。

Find academic papers on arXiv, with citation counts and BibTeX.

中文简介正在准备中。当前显示原文说明。

`.agent/agents/` のエージェント定義を入口に、タスクを調査・計画・実装・レビュー・検証へ分担するスキル。ユーザーが「エージェント」「マルチエージェント」「orchestrator」「役割分担」「複数担当」などを求めたとき、または大きな変更で担当境界を決める必要があるときに使う。

中文简介正在准备中。当前显示原文说明。

不具合報告（GitHub Issue、フォーラム投稿、社内報告）を起点に、調査・再現・修正・検証・記録までを一貫実行するスキル。症状の切り分け、原因仮説の整理、最小再現、修正実装、ExecPlan作成、PR下書き、ナレッジ追記が必要なときに使う。

中文简介正在准备中。当前显示原文说明。

Use only for user-provided academic text, explicit scholarly claims, existing citations, or known bibliographies needing citations added, verified, replaced, extracted, or formatted. Supports claim-to-source matching, citation-support checks, replacements, and common academic citation formats. Do not use for general fact-checking, legal/journalistic citation work, open-ended 'find literature about X', topic-level exhaustive discovery, systematic-review corpus construction, PRISMA searches, or creating new research claims. Chinese: 为已有段落补参考文献、核验已有引用、替换错误引用、提取需引文论断、GB/T 7714 格式化.

中文简介正在准备中。当前显示原文说明。

Create branded 试界TryWorld AI-knowledge videos in the fixed "Paper Algorithm" (纸上算法) style with HyperFrames. Input is a Chinese voiceover script and optional images; output is a 16:9 horizontal video with Azure YunxiNeural (真·云希) voiceover, word-synced captions, ink/paper animations and unified transitions, an always-visible anti-counterfeit red seal, plus horizontal (4:3) and vertical (3:4) cover images and platform-optimized titles for Bilibili/Douyin/Xiaohongshu. Brand values are theme-driven (themes/paper-algorithm.json by default; custom brand themes supported — see references/theme-guide.md). Use when the user provides an AI 科普/教程/内容解读/知识分享 script and wants a TryWorld/试界 branded video, asks for the 纸上算法/Paper Algorithm style, wants a consistent script-to-video pipeline with covers and titles, or wants this pipeline with their own brand theme.

中文简介正在准备中。当前显示原文说明。

试界TryWorld AI 口播视频的统一定位入口，覆盖口播全流程（选题/写稿/优化/出片）。涉及口播的请求都应触发：做口播/口播视频/口播稿/写口播稿/帮我选题/口播选题/这周做什么口播/AI 资讯盘点，或直接粘贴口播稿要求优化出片。自动识别两种模式：①直接给稿 → $tryworld-paper 优化并出片；②要选题 → $tryworld-topics 拉 AIHOT 资讯产选题清单 → 挑选 → 写稿 → 优化 → 出片。子命令：只要选题/只要写稿/只优化不出片。交付附四平台推荐发布时间。无需同时引用其他技能。

中文简介正在准备中。当前显示原文说明。

基于 aihot.virxact.com 最新 AI 资讯，为 AI 口播频道（试界TryWorld · 纸上算法风格）产出选题清单。由 $tryworld-koubo 在模式 B 下路由调用；被显式点名「只要选题」时也可直接触发。产出为 3-8 个候选选题（含选题名、角度、素材与原文链接、流量原理命中、优先级），可直接进入 $tryworld-paper 流程做片。

中文简介正在准备中。当前显示原文说明。

Teach models new tasks from a handful of examples — prompting strategies, example selection, and in-context learning mechanics.

中文简介正在准备中。当前显示原文说明。

Uncensored open-model inference on Featherless AI — raw model behavior for research and evaluation.

中文简介正在准备中。当前显示原文说明。

Research libraries and APIs automatically by pulling live documentation into the agent's context before answering. Use when writing code against unfamiliar or fast-moving libraries so examples match current versions.

中文简介正在准备中。当前显示原文说明。

Manage citations and references — collecting sources, organizing libraries, formatting bibliographies, and keeping reference integrity. Use when writing anything that cites sources.

中文简介正在准备中。当前显示原文说明。

Run a monthly money check-in with an AI assistant: categorize spending, spot leaks, set one savings target, and view it through the 50/30/20 lens — judgment-free. Use once a month to stay aware of where your money goes. General educational information, not financial advice.

中文简介正在准备中。当前显示原文说明。

Label smarter, not more — pick the most informative examples for annotation to maximize model gains per label.

中文简介正在准备中。当前显示原文说明。

Build with BAAI's Aquila models — open bilingual models from Beijing's academy with research transparency.

中文简介正在准备中。当前显示原文说明。

Learn effectively from courses and academies: choosing programs, studying actively, and converting courses into skills. Use when investing time/money in structured learning.

中文简介正在准备中。当前显示原文说明。

Writing abstracts that get papers read — structured content, the 5-sentence core, and journal-specific constraints.

中文简介正在准备中。当前显示原文说明。

Optimize content for AI answer engines (AEO/GEO): citation-friendly structure, factual precision, and measuring AI visibility. Use when AI search drives discovery.

中文简介正在准备中。当前显示原文说明。

MMDで静止ポーズ、表情、短いモーション、アクセサリ配置を制作・修正する。mmd-mcpによる実機操作、モデル骨格・軸・付与・IKの読み取り専用調査、モデル別の姿勢調整、主要キーと補間の編集、連続プレビューを扱う。

中文简介正在准备中。当前显示原文说明。

Build detailed buyer personas and audience profiles from research. Use this skill whenever the user mentions audience, buyer persona, ideal customer, target market, ICP, watering holes, 'who am I selling to', customer research, or audience profile. Also use when content feels unfocused or generic (that's an audience problem), when conversion is low because messaging doesn't resonate, when starting any new project (audience should be first), or when any downstream skill needs audience.md but it doesn't exist yet. Even if the user doesn't explicitly ask for audience research, trigger this if they're writing copy or building a landing page without a clear audience defined. Three approaches: Quick Profile, Persona Build, Community Mining.

中文简介正在准备中。当前显示原文说明。

Generate enriched ICP-based lead lists with Exa Agent, including structured scoring and CSV output. Use when generating leads, building prospect lists, finding companies to sell to, outbound research, or ICP-based company discovery. Triggers on leads, lead gen, prospect list, find companies, ICP, outbound list. Distinct from lead-magnet (content asset that captures emails).

中文简介正在准备中。当前显示原文说明。

Scan the current market landscape and produce a ground-truth ecosystem snapshot. Chains /last30days for live research, validates with user, and writes brand/landscape.md with a Claims Blacklist that hard-gates all content generation. Use when: "landscape", "ecosystem", "market snapshot", "ground truth", "what's happening", "refresh landscape", "market trends", or before any content campaign to verify claims.

中文简介正在准备中。当前显示原文说明。