Explore

盒子原创行业研究 Skill 组合中的 PEST 外部环境分析专项。以行业为研究对象，分析政治与政策、经济、社会和技术环境及其对行业和行业内企业的影响；可做完整 PEST，也可只分析一个或几个维度。企业研究需要判断外部环境时，分析目标企业所在行业。 由 hehe-industry-researcher 派发任务卡时按组合模式执行；用户直接要求“做 PEST 分析”“分析某行业的政策、经济、社会或技术环境”“判断外部环境对行业有什么影响”“做宏观环境分析”等问题时独立启动，自行确认范围、搜索材料、分析、自审并交付专项报告。

盒子原创行业研究 Skill 组合中的市场规模测算专项。按问题选择市场机会、交易经营、采购预算、财政经费、已有规模续算、宏观统计拆分、保有量更替或类比代理等方法，提供公式、参数、情景与敏感性分析，默认交付 Markdown 主报告和带公式的 Excel 计算附件。 由 hehe-industry-researcher 派发任务卡时按组合模式执行；用户直接要求“测算市场规模”“推算市场空间”或相关市场机会测算时独立启动，自行确认范围、搜索材料、分析、自审并保存成果。

盒子原创行业研究 Skill 组合中的行业痛点分析专项。辨析不同参与者在明确任务、流程或产业节点上反复、持续，或在关键时点承担的时间、成本、收入、结果、风险或责任损失，并核对现有替代为何仍未解决。用于“分析行业痛点”“行业瓶颈”“梳理行业发展卡点或障碍”“判断用户抱怨与行业瓶颈的关系”等问题。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；用户直接提出上述痛点问题时独立启动，自行确认范围、搜索并审核材料、分析和交付本专项结果。

盒子原创行业研究 Skill 组合中的行业驱动力分析专项。用于解释行业收入、销量、价格、利润、渗透率、供给或结构变化为何发生：先拆解需要解释的结果，再识别并核查需求、供给、价格与成本、技术、渠道、政策制度等驱动，最后给出主要驱动、作用路径、限制与观察指标。用户提出“分析行业驱动力”“解释增长或下滑原因”“进行多因素归因”“什么在推动或抑制这个行业”等请求时使用。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；用户直接提出上述驱动力问题时独立启动，自行确认范围、搜索并审核材料、分析和交付本专项结果。

盒子原创行业研究 Skill 组合中的治理与资本配置专项。判断公司的实际控制权与决策机制、管理层和股东激励、少数股东保护、关联交易及资本配置历史质量。用于“分析公司治理或实际控制人”“评估股权激励、关联交易、并购、融资、分红、回购或资本开支”等问题。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；用户直接提出上述治理或资本配置问题时独立启动，先读已有材料，只对会改变结果的关键歧义追问，再完成搜索审核、分析和交付。

盒子原创研究 Skill 体系中的企业财务分析大专项。重构并勾稽利润表、资产负债表和现金流量表，诊断增长、盈利、现金转换、资产质量、资本效率、债务与会计质量，并在需要时建立驱动式预测和压力测试模型。 用户直接要求“分析公司财务或三表”“解释业绩变化、盈利质量和现金流”“检查营运资本、ROIC、债务风险或异常科目”“做财务预测或公式工作底表”等时独立启动；没有完整财报时也可进行有限披露财务分析、经营财务情景测算或可分析性评估；不用于估值或投资建议。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；独立启动时自行确认范围、搜索并审核材料、分析和交付本专项结果。

盒子原创行业研究 Skill 组合中的竞争格局分析专项。行业研究梳理参与企业、份额、集中度及变化，按共同维度横向比较核心企业；企业研究比较目标企业与主要对手，并单独分析目标企业的地位、优劣势、问题、痛点、机会与策略。 由 hehe-industry-researcher 派发任务卡时按组合模式执行；用户直接要求“分析竞争格局”“计算市场份额或集中度”“比较龙头、挑战者或竞品”“判断竞争优势、进入壁垒或格局变化”等问题时独立启动，自行确认范围、搜索材料、分析、自审并交付专项报告。

盒子原创行业研究 Skill 组合中的公司画像专项。建立一家企业或经营主体的可追溯经营画像，核对公司历史与组织、业务与产品、客户供应商等关键经营关系、商业化进展、增长与基础财务质量、治理、战略动作、风险及待验证信号。用于“建立某家公司经营画像”“梳理公司业务、客户供应商和商业化进展”“分析单公司经营基本面、经营质量或成长驱动”“梳理企业战略变化”或制作公司事实卡。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；用户直接提出上述公司画像问题时独立启动，自行确认范围、搜索并审核材料、分析和交付本专项结果。

盒子原创行业研究 Skill 组合中的商业模式分析专项。研究一个行业常见的商业模式、组合方式、演变趋势与护城河；或研究一家企业的业务与盈利模式，并与主要竞争企业比较。用于“这个行业有哪些商业模式”“分析某公司的商业模式”“这家公司和同行怎么赚钱”“模式怎样组合、扩张和演变”等问题，也支持收入成本、单位经济、现金转换等局部分析，交付对应的商业模式分析报告。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；用户直接提出上述商业模式问题时独立启动，自行确认范围、搜索并审核材料、分析和交付本专项结果。

LiveCanvas（实况画布）的旧名兼容入口；用户沿用 LiveChart 或 $livechart 时转入 LiveCanvas。

Generate Infinite Pokémon map stories, terrain features, content profiles, NPC policies, and interiors from a host-supplied saved-run snapshot and output schema.

Generate grounded NPC intentions, dialogue, memory and optional movement policies for Infinite Pokémon from a supplied saved-run observation or map-design context.

Design interior furniture layouts, rugs, room names and inspectable details for new Infinite Pokémon maps within the supplied protected room and service constraints.

Set up and start Infinite Pokémon when a user asks to install, play, or launch the game with their AI assistant. Clone missing game files, install dependencies, build, and launch the local desktop or browser game; not for background map or NPC generation jobs.

做 PPT 和美化 PPT 的一站式 skill，输出可编辑的原生 .pptx。从零生成时，给一个题目、一篇文章或口播稿、一份大纲，产出结论式标题、带口播备注、风格统一的 PPT；按参考图美化时，给一份朴素的 .pptx 和一张参考图，文字一字不改地换上统一的配色、母版、版式、图标和插画。当用户说"做个PPT""把这篇文章做成PPT""生成口播PPT""美化PPT""照这张图的风格改PPT""套个风格""make slides""beautify my deck"，或丢来 pptx、文章、大纲时，务必使用此skill。生图模型可配置，没配置时自动用程序化插画兜底。

Apply small, meaning-preserving rhetorical edits to a finished academic manuscript, to counter wording-driven LLM review penalties while keeping the scientific assessment a human could make materially unchanged. Uses model-agnostic strategies from LLM reviewer preference research without querying a target reviewer. Use after ordinary writing and polishing; not for drafting or generating reviews.

Edit Chinese or English academic prose for natural language, translation, and de-templating while preserving evidence, citations, author voice, and requested scope.

Run browser-grounded, read-only social research through Jev Social when a user wants posts, profiles, comments, video evidence, or a source-linked report from Instagram, TikTok, or LinkedIn and the local socai CLI reports support for that platform. Do not use for publishing, engagement actions, or general web research.

Bug bounty report triage, validation, and severity escalation. Use when the user provides a bug bounty report to validate, wants to check if a finding is submittable, needs to escalate severity for maximum payout, or says 'triage this', 'validate this report', 'escalate this', 'is this submittable', 'check this bounty report', 'max bounty', or 'will this get accepted'.

阅读单篇生物医学研究论文，提供完整精读、速读或指定图／方法解析；按原文与图表解释研究逻辑、记录可追溯证据并提炼研究设计。默认中文，支持英文及明确要求的中英双语。输入可为 PDF、DOI、链接或正文；全文翻译、系统综述和多篇比较不是默认任务。

Jev browser automation with indexed actions. Replay YAML/Markdown/API cases, run goal-driven flows, generate cases, and explore sites in a real browser. Use when the user mentions Jev, browser automation, UI automation, E2E replay, test case generation, exploratory crawl, or YAML/MD/API test cases. Not a fork of browser-use/jev-ultrafast.

Use when an engineering task requires diagnosis, runtime verification, correction of recurring agent failures, or coordination of delegated coding work.

Explicitly installed compatibility alias for MathModel Copilot competition workflows. Use only when the owner deliberately enabled this alias and asks for CUMCM, MCM/ICM, Diangong or custom modeling contest work. This is not an upstream mathmodel-skill installation.

MathModel Copilot, an evidence-based mathematical-modeling competition workflow built on mathmodel-skill. Use for CUMCM, MCM/ICM, Diangong or custom modeling contests, including requirements, per-question modeling, actual Python runs, independent validation, paper assembly, team handoff and submission audit. Preserves ten stages and Critic/Red Team. Do not trigger for unrelated data analysis or ordinary paper review. Maintenance requests modify the skill rather than start a contest.

作业提交前检查 / assignment preflight checker。用于“检查作业能不能交、提交前再 check、是否符合老师要求、check my assignment before I submit it、review my homework/essay/report/code against the brief or rubric”等场景。把老师要求拆成 requirement ledger，逐条映射到学生证据；能用工具就实际验证，最后按潜在失分影响给出最该先改的 1–3 项。

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Turns an answer into a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled CLI builds one page. Use it proactively and liberally, without being asked, whenever a page would help the reader more than plain text, even if plain text would also work: any explanation of how something works or how parts relate (flow, request path, architecture, code or folder structure, state machine, lifecycle, history); any comparison, trade-off or decision with pros and cons; any diagnosis, review or investigation, especially with several causes or findings to rank; any answer with a table, a numbered or ranked list, steps, branches or several sections; or when the user says "I don't get it / draw it / explain visually / 讲讲原理 / 没看懂 / 画个图". When in doubt, use it: a page is quick and cheap to make. Also for explainer videos ("make a video", "做个视频") and for changing its settings. Skip only for small talk, a trivial one-line answer, or when the user asks for plain text.

开箱 / 对比评测模板：生成电商开箱视频与 A/B 对比评测的结构、口播稿、拍摄清单与分镜（含公平对比规则、测试设计、缺点与适合人群），可直接转成 storyboard.json 渲染。Use when the user wants an unboxing video, 开箱, 测评, 评测, 横评, 对比, review script, product comparison, versus video, or UGC-style creator review for an ecommerce product.

字幕与花字：为带货短视频生成 ASS/SRT 字幕与花字（大标题弹出、关键词高亮、贴纸标签、行动号召按钮），自动避开平台底部/右侧 UI 安全区，并用 ffmpeg/libass 烧录。Use when the user wants subtitles, captions, 字幕, 花字, 大字报, keyword highlight, burned-in captions, SRT/ASS files, or text overlays that don't get covered by TikTok/抖音 UI.

TikTok Shop / 抖音 / 视频号 / 小红书 / 淘宝主图视频 / Amazon 规格导出：把一条母版视频一键转成各平台推荐画幅与编码（9:16、3:4、1:1、16:9，模糊填充或智能裁切），输出规格报告，并可叠加 UI 安全区预览。Use when the user asks for export settings, 导出规格, 尺寸, 分辨率, 画幅, 上传要求, re-encode for TikTok Shop / Douyin / WeChat Channels / Xiaohongshu / Taobao / Amazon, or safe zones.

多语言本地化配音：把中文带货视频本地化为英语、日语、韩语、东南亚语（印尼/泰/越/马来/菲律宾）、西语等版本——本地化改写口播（不是直译）、选对 edge-tts 音色、生成对应字幕与花字，并用同一份 storyboard 一键渲染多语言成片。Use when the user wants dubbing, 多语言, 本地化, 翻译配音, 出海, localize a product video for TikTok Shop US/UK/SEA, English voice-over, or multiple language versions of one video.

直播切片：从电商直播录屏中找出高光片段（按时间戳 / 按字幕关键词 / 按停顿自动提议），批量导出 9:16 竖屏切片，自动模糊填充横屏画面、烧录标题与字幕、响度标准化，并给切片写标题与开头钩子。Use when the user has a livestream recording and wants 直播切片, 切片, highlights, clips, 高光片段, repurpose a live stream into short videos for 抖音 / 视频号 / TikTok.

主图转视频：把一张或几张商品主图/白底图/场景图，写成可直接喂给图生视频模型的镜头提示词（运镜、主体动作、光线、时长、负面约束），并保证商品不变形。Use when the user has product images and wants a product video, 主图视频, 图生视频, image-to-video, animate a product photo, or 让主图动起来 — with any image-to-video model (Seedance / 可灵 Kling / Veo / Runway / Hailuo / Wan …) or a local Ken Burns fallback.

ffmpeg 自动拼接成片：一条命令把 storyboard.json（商品图/视频片段 + 口播稿）渲染成带配音、字幕花字、转场、BGM 自动闪避、响度标准化的 9:16 MP4，纯本地运行。Use when the user wants to assemble/edit/render a product video, 自动剪辑, 一键成片, 拼接视频, 图片转视频, Ken Burns, add BGM/subtitles/voice-over with ffmpeg, or batch-produce short videos without an editor.

封面与标题 A/B：为带货短视频生成多套封面（自动挑选清晰帧或用干净素材图 + 不同标题与版式）和多组标题/文案，导出 3:4 / 9:16 封面文件和对比图，并给出 A/B 测试方法与记录表。Use when the user wants a video cover, 封面, 首图, thumbnail, 标题, 文案, title variants, A/B test covers for 抖音 / 视频号 / 小红书 / TikTok, or wants to improve click-through rate.

AI 口播配音：用免费的 edge-tts（微软 Edge 在线语音）为带货短视频逐句生成配音，自动去首尾静音、统计每句时长、缓存复用，可选音色/语速/音调，并给出口播稿改写规则。Use when the user needs a voice-over, 配音, 口播, 旁白, TTS, text-to-speech, AI 主播声音, or wants to turn a script into audio for 抖音 / TikTok / 视频号 videos.

Create Xiaohongshu (RED / 小红书) note covers and first images in 3:4 (1080×1440) for product seeding (种草), reviews, hauls and tutorials: big bold Chinese headline, product hero, visual anchor and stickers, in proven viral layouts. Use for 小红书封面, 种草图, 笔记首图, RED cover, rednote.

Plan and generate a Taobao/Tmall/Pinduoduo/JD product detail page (详情页) as 750-px-wide screens stitched into one long image: pain point → benefits → scenes → details → specs → after-sales, with a campaign style lock for consistency. Use for 详情页, 详情长图, 淘宝详情, 拼多多详情, detail page, PDP long image.

Create size / dimension / specification chart images: product line drawing or photo with measurement callouts (cm + inch), apparel size tables, capacity and compatibility charts, with a human-hand or object reference for scale. Numbers come only from the user. Use for 尺寸图, 规格图, size chart, dimension image, spec sheet.

Design selling-point / feature infographic images (one benefit per image, icons, callout lines, short headlines, comparison or spec rows) for Amazon secondary images, Taobao detail screens and ads, keeping the real product and exact user-approved copy. Use for 卖点图, 信息图, feature image, infographic, benefit graphic.

Design promotional sale banners and store hero images for Taobao/Tmall (双11, 618, 年货节), Shopee/Lazada (9.9, 11.11, 12.12), TikTok Shop, Amazon Prime Day/Black Friday and DTC sites, with the real product and exact campaign copy at the right pixel size. Use for 海报, banner, 首焦图, 大促图, campaign banner, store header.

Generate a consistent multi-angle product image set (front, back, left/right side, top, 45°, detail macro, packaging, in-hand) with identical lighting and background, optionally combined into a grid. Use for 多角度图, 多视角套图, 360 view, angle set, gallery images.

Dress a model in a real garment or accessory from a flat-lay, hanger or mannequin photo (on-model / virtual try-on) while preserving fabric, colour, fit, prints and logos. Supports pose references, multiple body types and ghost-mannequin output. Use for 模特图, 上身图, 试穿, try-on, on-model photo, apparel and jewellery.

Place a real product into a believable lifestyle or in-use scene (kitchen, bathroom, desk, outdoor, gym, bedroom, festive) for listing images, ads and social posts while keeping the product identical. Use for 场景图, 生活场景图, lifestyle image, in-use photo, context shot.

Orchestrate a complete ecommerce image set for one product: confirm product facts, plan the gallery per platform (Amazon 7-image set, Taobao 5 main + detail page, Shopee, TikTok Shop, Xiaohongshu), lock identity and campaign style, then call the specialised skills and QA every image. Use when the user wants a full listing image set, 全套图, 套图, 一键出图, listing images, PDP image pack.

Batch-replace backgrounds or recolour SKU variants across a folder of product photos (white background, brand colour, seasonal scene, colour variants) while keeping the product untouched, with resume, retries, budget cap and a CSV log. Use for 批量换背景, 批量白底, SKU 换色, colour variants, background replacement, bulk edit.

Create an Amazon-compliant white-background main image (pure #FFFFFF background, product fills ≥85% of the frame, no text, props or watermark) from a product photo with GPT Image 2.5, then verify it with a Python check script. Use for Amazon/Walmart/eBay main images, 白底图, 白底主图, hero image, listing main photo.

Plan and generate Amazon A+ Content / Premium A+ module images (970×600 header, 970×300 banner, 300×300 / 220×220 tiles, 350×175 comparison, 1464×600 premium) with a consistent campaign style lock across all modules. Use for A+ content, A+ 页面, EBC, brand story, enhanced brand content.

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

盒子原创行业研究 Skill 组合中的产业链分析专项。梳理行业或企业所在链条的功能、角色、上下游关系与代表企业，分析成本、利润、瓶颈和技术替代，交付 Markdown 分析及可编辑、美化的产业链图。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；用户直接要求“分析产业链或价值链”“梳理上下游关系或企业图谱”“判断供应链卡点”或“绘制产业链图”等问题时独立启动，自行确认范围、搜索并审核材料、分析和交付本专项结果。

将主题或材料经搜索核实制成苹果 Live Photo 信息动效卡。用 Remotion 编排图片、PNG、emoji、场景、时间线和可选图表，适用于知识解释、产品比较、变化过程及数据故事；制作可预览动效与配对实况资源，说明接收端兼容性。

Query the user's local knowledge bases through the Carrel search API, fetch original text or images as needed, compose the answer, list the reference files and offer follow-up directions drawn from the knowledge graph. Use when the user asks to search the knowledge base, find evidence in the stored material, compare records, or answer from several documents together.

Conduct a retrospective on a coding session.

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.

Compact the current conversation into a handoff document for another agent to pick up.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

A relentless interview to sharpen a plan or design.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

A relentless interview to sharpen a plan or design.