494 件 ・ 関連度順
概要と使いどころ
Use this skill to write or revise a README.md for a Shipfox workspace package (libs/*, tools/*). It applies the shared package README standard and repository prose policy. Trigger on write a README, draft README, rewrite README, document this package, or improve the README.
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。
ALWAYS use this skill when creating pull requests. Applies Shipfox agent sequencing for GitHub CLI review preparation and pull-request creation. Trigger on create PR, open PR, submit PR, make PR, push and create PR, or prepare changes for review.
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 a Changeset file for the current branch using Shipfox agent automation. Trigger when the user asks to add a Changeset, document a change for release, bump versions, or prepare a PR that touches published packages.
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。
ALWAYS use this skill when committing changes. Applies Shipfox agent sequencing for branch checks, scoped validation, and commit creation. Trigger on commit, commit changes, save changes, make a commit, or create commit.
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 checking a local Shipfox workflow change without starting a run.
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 developing Firefox WebExtensions - Manifest V2/V3 configuration, WebExtension APIs, content security policy, web-ext CLI, cross-browser support with the polyfill, AMO submission, or debugging extensions
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 cross-browser extensions with WXT — the modern framework for Chrome, Firefox, Safari, and Edge extensions. Use when someone asks to "build a browser extension", "Chrome extension with React", "WXT framework", "cross- browser extension", "manifest v3 extension", "build Firefox extension", or "browser extension with TypeScript". Covers content scripts, background workers, popup/options pages, storage, messaging, and publishing.
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。
Requires OFOX_API_KEY — create one at https://app.ofox.ai, plus a video you already have. Makes an existing clip longer, or replaces its ending. Use when a user wants more of footage they already have, e.g. "extend this 5-second clip to 15", "keep going from where this one ends", "re-shoot the ending from 4 seconds on", or "add another shot onto this". A frame is pulled out of the clip at zero cost and becomes the first frame of a newly generated segment, which is then joined onto the original. Do not use to change what is inside the picture — measured, the API accepts an edit mode field and silently ignores it, so no content-editing route exists here and none returns an error either; for two stills you already have see keyframe-animation, and for a clip from nothing see the seedance-* scenarios.
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。
Requires OFOX_API_KEY — create one at https://app.ofox.ai. Generate a handheld, phone-shot UGC clip — imperfect framing, one practical light, vertical, no cinematic grading, no beauty filter. It inverts the polish every other video skill here defaults to — a UGC clip that looks like an ad has failed. Use when a user wants a video that reads as filmed by a real customer rather than by an agency, e.g. "a real-looking phone unboxing of this product", "a creator first-impression clip for TikTok", "an honest review video, nothing slick", or "make it look like a customer shot it". Do not use for a polished brand ad (see seedance-ad-creative), plain catalog footage (see seedance-product-video), a dialogue scene between people (see seedance-short-drama), or a set of cheap vertical drafts to choose from (see shorts-reels).
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。
Requires OFOX_API_KEY — create one at https://app.ofox.ai, plus a publicly reachable reference video the user is authorized to use. Use when a user has a rough 3D white-model, clay, wireframe, blockout, previs, or animatic clip and wants a finished visual treatment that preserves its shot order, cut timing, camera framing, spatial layout, and motion directions. Distinguishes that structure-preserving job from a continuation beginning at the reference's final state. Do not use for two still endpoints (keyframe-animation), for appending and locally joining a new ending (video-extend-edit), or when still-image references must be combined with the video in one request — first/last-frame anchors conflict with video references in the shipped core, while mixed image/video references are untested.
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。
Requires OFOX_API_KEY — create one at https://app.ofox.ai. Generate cheap vertical 9:16 drafts in one priced batch, pick a winner off the contact sheet, then re-render only that one. The cheap tier is the point — several times cheaper per second, so a whole set can cost less than one flagship clip. Use when a user wants Shorts/Reels/TikTok raw material rather than one finished video, e.g. "give me 5 vertical clips to choose from", "a few Reels drafts for this product", "some cheap options before we commit", or "batch me some 9:16 takes". Do not use when one finished clip is wanted — go straight to the scenario skill (seedance-ad-creative, ugc-ads, seedance-short-drama, seedance-product-video), which is also where this skill gets the prompt it drafts.
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。
Requires OFOX_API_KEY — create one at https://app.ofox.ai. Turn a portrait plus a short script into a clip of one person speaking those words to camera. You supply the text and the model generates the voice — audio cannot be uploaded, measured. Defaults to alibaba/wan-3.0-prime rather than this repo's usual seedance-2.5, because seedance-2.5 refuses a real person's photo at submission. Use when a user has a face and some words and wants the face to say them, e.g. "make this headshot read my intro", "a spokesperson clip from this portrait", "have her say this line to camera", "use this avatar to read the announcement". Do not use for a scene between two or more people (see seedance-short-drama), a polished brand or product ad (see seedance-ad-creative), a handheld creator clip (see ugc-ads), or when the words still have to be pulled out of an article and no particular face is required (see explainer).
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。
Requires OFOX_API_KEY — create one at https://app.ofox.ai, plus the music file the finished video must carry. Your audio never reaches the API (measured) — the visuals are written to the track's tempo, mood and sections, then your own file is laid on locally at zero cost. One job caps at 30 seconds, so a three-minute song is six jobs minimum and the cost table says that before anything is spent. Use when a user has a specific piece of music and wants visuals for it, e.g. "make a music video for this track", "visuals for my song", "an MV for this instrumental", "generate footage cut to this beat". Do not use for cheap vertical social drafts (shorts-reels), a brand film that happens to have a music bed (seedance-ad-creative), or when there is no particular audio file the finished video has to carry.
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。
Requires OFOX_API_KEY — create one at https://app.ofox.ai. Turn an article, doc or release note into a short explainer clip — one person to camera, or a voiceover over illustrative footage. The user supplies the source text and the model generates the speech; audio cannot be uploaded, measured. A 30-second clip holds about eighty spoken words in eight sentences — measured, and well under a tenth of a 1,200-word post — so this skill does not summarise an article, it picks the single idea worth saying and helps choose which one. Use when a user asks to turn writing into a short spoken video, e.g. "make a 30-second explainer from this blog post", "explain this feature in a short video", "turn our changelog into a clip", "a quick video explaining what this paper found". Do not use for a scene between people (see seedance-short-drama), a brand or product ad (see seedance-ad-creative), a handheld creator clip (see ugc-ads), or when the user already has both a portrait and the finished words (see talking-head). Budget sentences as well as words — each sentence boundary costs about 0.7 seconds of silence, so a script with more sentences runs longer at the same word count.
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。
TikTok 监控订阅推送工具 — 订阅关键词、指定账号与话题，每日早上 9:00 自动拉取昨日时间窗内新内容（关键词新爆款视频 / 账号新作品 / 话题新作品），按订阅项分组生成 HTML 日报推送，无需手动操作。支持三类订阅项批量管理（总上限 100 项）、按日期过滤翻页、互动数据（播放/点赞/评论/分享）展示与 AI 总结。当用户需要订阅 TikTok 关键词、追踪指定账号新作品、监控话题热度变化、获取 TikTok 昨日内容日报时使用。触发词：TikTok订阅、TikTok监控、TikTok日报、TikTok关键词订阅、TikTok账号订阅、TikTok话题订阅、TikTok订阅推送、监控订阅推送。
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。
懂车帝作品关键词搜索工具。基于红狐数据，按关键词搜索懂车帝作品，返回标题、作者、播放、点赞、评论、发布时间和完整作品链接。适用于用户要求“懂车帝搜索”“懂车帝关键词作品”“搜索某车系/品牌在懂车帝的内容”“懂车帝视频搜索”“懂车帝图文搜索”时使用。
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。
TikTok账号深度分析，输入TikTok主页链接、handle、secUserId或昵称即可定位账号，一次输出账号基础信息、主页作品榜与喜欢作品透视三类数据。基于红狐数据，作品含播放、点赞、评论、收藏与分享数据及作品链接，输出六维量化诊断（100分制评分+风险预警）、爆款作品拆解、喜欢偏好解读与账号诊断总结，支持翻页与 HTML 报告导出。适用于 TikTok 达人背调、竞品账号拆解、合作前评估时使用。触发词：TikTok账号分析、TikTok账号诊断、TikTok达人背调、TikTok账号深度分析、TikTok博主分析、TikTok账号数据、TikTok竞品分析。
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。
懂车帝用户搜索和作品订阅工具。输入关键词就能搜到懂车帝上的用户（作者）账号，粉丝数、简介一眼看清；选中想看的用户即可拉取他的作品列表，标题、类型、阅读、点赞、评论、收藏、发布时间全部呈现，每条作品点一下就能跳转原页；还支持订阅用户，每天自动推送 TA 昨日更新的作品。当用户需要搜索懂车帝用户、查找懂车帝作者/达人、查看懂车帝用户作品列表、订阅懂车帝用户更新、研究懂车帝创作者内容时使用。触发词：懂车帝、懂车帝用户、懂车帝作者、懂车帝作品、懂车帝账号、懂车帝搜索、懂车帝达人、懂车帝用户搜索、懂车帝订阅。
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。
TikTok热门搜索，一次输入关键词同时获取热门视频、相关用户与相关话题三类数据。基于红狐数据，视频支持排序与发布时间、地区筛选，用户支持粉丝数与认证筛选，话题附浏览量、使用次数与直达链接，输出榜单表格、爆款视频拆解、达人推荐与话题趋势解读，支持翻页与 HTML 报告导出。适用于 TikTok 出海选题调研、竞品扫描、达人发现时使用。触发词：TikTok热门搜索、TikTok视频搜索、TikTok用户搜索、TikTok话题搜索、TikTok关键词搜索、TikTok搜索、TikTok搜视频、TikTok搜用户、TikTok找达人。
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。
根据关键词搜索 TikTok 话题数据，并支持按话题 ID 查询该话题下的作品列表。基于红狐数据，按关键词返回话题名称、话题 ID、使用次数、浏览量、参与人数等核心数据；输入话题 ID 可继续查询该话题下的作品，输出播放、点赞、评论、分享等核心数据与可点击完整作品链接，支持分页与排序切换。适用于用户要求搜索 TikTok 话题、查询关键词相关话题、根据话题 ID 查话题作品时使用。触发词：TikTok 关键词搜话题、搜索 TikTok 话题、TikTok 话题数据、话题 ID 查作品、hashtag 搜索。
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。
检测文案、文件或网页中的小红书违禁词并加粗显示，提供违禁词替换建议和仅替换违禁词后的文案；当用户需要查询小红书平台违禁词、检查小红书笔记文案是否包含敏感词、或希望获得安全替换词和修改后文案时使用。
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。
深度拆解小红书账号，输出七维度量化评分诊断报告与可导出HTML；当用户提供小红书号进行账号诊断、rednote分析、账号健康度评估、商业价值评估、多账号对比或制定优化策略时使用
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。
AI小红书信息源 — 每日自动扫描小红书 AI 相关笔记，按互动量（点赞/分享/评论）筛选最火内容，智能聚类生成精美 HTML 日报，支持封面图、数据指标和每日订阅。当用户需要 AI 小红书日报、小红书AI热点、AI小红书内容、小红书信息源、xhs ai feed 时使用。
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。
想知道小红书哪些账号涨粉最猛？帮你查询日榜/周榜/月榜涨粉榜单，覆盖 25 个热门品类，还能一键生成精美排名图片、导出 Excel、订阅每日推送！
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。