Skills 目录 · 第 79 页

Convert blog posts or newsletters into X/Twitter articles with handles inserted and a posting strategy. Use when the user wants to turn an article into X content, create a tweetstorm, or promote content on Twitter/X with expert tagging. (project)

Post and schedule content to X/Twitter. Use when batch processing social posts, promoting podcasts/blogs, or scheduling content. Handles guest tagging, template matching, and getlate.dev API integration.

用于在 X/Twitter 上增长：推文、推文串、个人资料审计、竞争对手或发布计划。用 profile_auditor.py 审计个人资料，用 tweet_composer.py 起草内容，用 content_planner.py 规划帖子。

面向 AI 编程智能体的 X API 与 Twitter 抓取技能。基于 Xquik REST API、MCP 服务器与 webhook 构建集成：推文搜索、用户查询、粉丝提取、互动指标、抽奖活动开奖、热门话题、账号监控、回复/转推/引用提取、社区与 Space 数据、互相关注检查。可与 Claude Code、Cursor、Codex、Copilot、Windsurf 及 40 多个智能体配合使用。

当用户希望通过 Xquik 集成 X（Twitter）API 以搜索推文、查询用户资料、提取关注者、进行抽奖、监控账号或访问热门话题时使用。当用户提到“Xquik”“Twitter API”“X API”“推文抓取器”“关注者提取”或“Twitter 监控”时也使用。涵盖 REST API、webhook 和 MCP 服务器设置。

仅当用户明确要求使用 GitHub CLI（`gh`）一次性完成暂存、提交、推送并打开 GitHub 拉取请求时使用。

Use for GitHub PR/issue/discussion workflows: create/update PRs, issues, or discussions and post issue or discussion comments; triggers include yeet.

Yelp business data API: search businesses in a metro, pull one business in full with hours, amenities and health inspections, and page through reviews. Returns rating, review count, price band, categories, address, contact details, photos, and review text with owner responses. 3 endpoints, 2 credits each, structured JSON.

Workflow for compressing prompt and instruction files using LLM-powered techniques, with backup management and restore.

Guided walkthrough for using ynd inspect to bootstrap a project's AI skills and agents from its codebase signals.

Bring an existing AI setup — a .claude folder, .cursorrules, a grown CLAUDE.md — under ynh without losing it. Use when someone already has assistant config and wants to adopt ynh, rather than starting a harness from scratch.

Compose harnesses from other harnesses — includes, delegates, profiles, focuses and fork. Use when someone has one working harness and wants to reuse parts of it, share it, or vary it per situation rather than copying folders around.

Interactive wizard to create a ynh harness from scratch. Walks through naming, vendor selection, artifact scaffolding, and installation.

Development workflow for the ynh codebase. Build, test, lint, and format in the right order.

Choose, declare and calibrate the sensors a project needs, then gate on them with ynh check. Use when a harness has no sensors, when ynh check reports nothing useful, or when setting up an agent loop that needs something to converge against.

Guide graduation from a personal harness to a team setup with delegation. Creates a team harness that delegates to personal harnesses.

Diagnose a ynh setup that is not working — a harness that will not install, a launcher that is not found, a vendor that cannot see the skills, instructions that are not applied, or a check that gates for no visible reason. Use when something is broken and it is not obvious why.

Fast CLI-first LLM council, bundler, and multimodal gateway. Use ONLY when user explicitly mentions "yoetz", "yoetz ask", "yoetz council", "yoetz review", "yoetz generate", "yoetz bundle", "yoetz browser". NOT triggered by generic "second opinion" or "ask another model" requests.

The ultimate YouTube creator skill. Covers channel audits, video SEO, retention-engineered scripts, hook writing, thumbnail briefs, content strategy, content calendars, Shorts optimisation, analytics interpretation, monetisation planning, competitor research, cross-platform repurposing, upload metadata packages, and data-driven video idea generation. Triggers on: "youtube", "channel", "video", "views", "subscribers", "watch time", "shorts", "thumbnail", "CTR", "retention", "monetize", "script", "hook", "upload", "youtube audit", "video ideas", "content calendar", "competitor analysis", "repurpose video", "youtube seo", "youtube strategy", "youtube analytics".

Download YouTube videos, identify compelling clips from transcripts, cut clips with ffmpeg, and generate platform-optimized on-screen text and captions. Complete workflow from URL to publishable clips.

YouTube data API: search videos, Shorts and channels, then pull video metadata, comments and replies, transcripts, related videos, download streams, channel info, videos and community posts, and a single community post with its comments. Returns title, view count, duration, published time, channel and caption fields as JSON. 17 endpoints, 1-5 credits each.

Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.

适用于任何YouTube URL、视频ID或@handle，或对转录文本、视频搜索、频道、播放列表或新上传监控的请求。通过yt-dlp、youtube-transcript-api和公开RSS源获取，无需API密钥；不下载视频或音频。

Write a high-retention YouTube script — explainer, tutorial, video essay, review, or talking head — on the packaging then cold-open then value-stack then retention structure that holds watch time past the drop-off cliffs. Use when asked to write a YouTube script, script a long-form or explainer video, draft a video hook, outline a video essay, or turn a blog post or talk into a video. Produces title and thumbnail concepts, multiple hook options, a beat-by-beat body with retention devices, and clear visual and audio cues.

Generate high-CTR YouTube titles and thumbnails using framework fitting method. Match content to 119 proven formulas from Creator Hooks, apply psychological principles, test variations.

Audit a YouTube channel end to end - packaging, consistency, the first fifteen seconds, and what to fix first. Use for "audit my channel", "why isn't my channel growing", "review my videos", or a pasted channel URL.

Write YouTube chapters from a transcript, validated against YouTube's own rules so they actually render. Use for "add chapters", "timestamps", "break this video into sections".

Draft replies to YouTube comments in the creator's voice, triaged by which ones are worth answering. Use for "reply to my comments", "handle the comment section", "someone asked X", or a pasted comment thread.

Turn a raw recording's transcript into an edit decision list - dead air, filler cues and retakes, with timecodes. Use for "edit this", "cut the dead space", "tighten this video", "I rambled", or any request to shorten footage from a transcript.

Write and lint the title and thumbnail for a YouTube video as one pairing, checking truncation, duplication and vagueness before publish. Use for "title ideas", "what should I call this", "thumbnail text", "my CTR is bad", packaging, or any request to rename or repackage an existing video.

Plan a week or a month of YouTube uploads - what to post, when, and in what order, sized to the creator's actual capacity. Use for "plan my week", "content calendar", "what should I post", "I have no idea what to make next".

Read a YouTube Studio audience-retention export and find where viewers actually leave, then say what to change. Use for "why do people stop watching", "my retention is bad", a pasted retention chart or CSV, or "fix my pacing".

Write a YouTube video script from a raw idea - hook options off 21 formulas, scored, then the full spoken script with the retention beats marked. Use whenever the user wants a video script, a hook, an opening line, "what should I say", "write my next video", or is about to record and does not have the first fifteen seconds yet.

Write the description, tags and search-facing text for a YouTube video, aimed at the query a real person types. Use for "write my description", "tags", "SEO", "help this video get found", "nobody is finding this".

Find the Shorts hiding inside a long video and write them, using the transcript to pick self-contained moments. Use for "cut this into shorts", "clip this", "repurpose this video", "what should I clip".

Find what is actually working in the user's niche on YouTube and rank it by how far each video beat its own channel, then name the formula. Use for "what's working right now", "find viral videos in my niche", "why did this blow up", competitor research, or a swipe file.

无代码自动化让工作流构建走向大众化。Zapier 和 Make（原 Integromat）让非开发者无需编写代码即可自动化业务流程。但无代码并不意味着无复杂性——这些平台有其自身的模式、陷阱和瓶颈。本技能涵盖何时选用哪个平台、如何构建可靠的自动化，以及何时应升级到基于代码的解决方案。关键洞察：Zapier 侧重简洁性和集成（7000+ 应用），Make 侧重强大能力。

管理并触发预先构建的 Zapier 工作流及 MCP 工具编排。适用于用户提到工作流、Zaps、自动化、每日摘要、研究、搜索、线索跟踪、费用，或要求“运行”某个流程。也处理基于 Perplexity 的研究和 Google Sheets 数据跟踪。

用于云存储的分块 N 维数组：压缩数组、并行 I/O、S3/GCS 集成，以及 NumPy/Dask/Xarray 兼容性，面向大规模科学计算流水线。

Use before high-stakes or multi-file coding (auth, databases, migrations), or when asked to plan carefully and avoid invented APIs. Runs discuss, map, decompose, execute and verify, checking every import and API exists. Not for trivial edits.

Zillow property data API: search listings for sale, for rent or sold, pull one property in full, and read an agent's profile and reviews. Returns price and price history, Zestimate, tax history, beds, baths, living area, days on market, schools, open houses and photos. 3 endpoints, 1 credit each, structured JSON.

访问ZINC（230M+可购买化合物）。按ZINC ID/SMILES搜索、相似性搜索、用于对接的3D就绪结构、类似物发现，用于虚拟筛选和药物发现。

Develop zero-knowledge proofs: private voting and identity, zk-rollups, verifiable computation, and compliance without exposing data. Use for privacy-preserving apps.

Zod 专家——以 TypeScript 为先的 schema 校验。涵盖解析、自定义错误、细化校验、类型推断，以及与 React Hook Form、Next.js 和 tRPC 的集成。

Archive Zoom cloud recordings, read stored meeting transcripts and summaries, or manage a Zoom meeting through zm. Use for Zoom CLI workflows, not joining calls or operating the desktop video client.

使用 TypeScript、subscribeWithSelector 中间件和合理的状态/操作分离创建 Zustand store。用于构建 React 状态管理、创建全局 store，或使用 Zustand 实现响应式状态模式。

按照既定模式创建Zustand store，使用恰当的TypeScript类型和中间件。