Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 696 files from 2 113 authors, of which 68 413 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> Use when programmatically creating, modifying, or querying Dataverse schema and metadata via the Web API (OData v4.0). Covers table/column/relationship definitions, solution ALM, form and view XML construction, app module composition, global option sets, business rules, "entitydefinitions", "web api schema", "create dataverse table", "create dataverse column", "fetchxml", "formxml", "layoutxml", "dataverse solution", "dataverse relationship", "odata dataverse", "metadata api", "publish customizations", "dataverse alm", "grid control", "editable grid", "business rule", "rich text", "auto-number", "file column", "image column", "pcf control", "security role", "column security", "environment variable", "custom api", "data migration", "solution import".
> Use when building, scaffolding, debugging, or deploying Microsoft Power Apps Code Apps using React, Vue, or TypeScript in VS Code. Handles project initialization via pac CLI, Dataverse and connector data access via the @microsoft/power-apps SDK, power.config.json configuration, Vite build pipelines, and deployment to Power Platform environments. "vibe coding", "scaffold power app", "deploy code app".
Record a Chrome browser tab to video via CLI. Use when the user wants to capture a screen recording of a browser tab. Supports list, start, stop, caption, and status subcommands. No debug mode required — uses a Chrome extension.
> AI-powered visual QA testing that walks through an app in the browser, records every action with annotated captions (what was done, what should happen), captures screenshots/GIFs, and sends the evidence to Gemini for automated review. Catches UX misalignments, broken flows, missing states, and edge cases that traditional tests miss. Can use Agent Teams for parallel "check the ui", "record a test", "walk through the app", "e2e test", "end to end test", "catch edge cases", "gemini review", "screen test", "ux test", "visual regression".
> 📈 SEO & Content Marketing skill suite derived from alirezarezvani/claude-code-skill-factory. Keyword research, content audits, SERP analysis, technical SEO and content strategy. Provides 10 specialised commands for seo, content, marketing workflows.
Alignment conversation starting from a user's rough idea. Co-decides with the user whether the idea should be acted on directly in the current session, or fixed into a formal Task by producing four documents in `.task/` for independent dispatch. Handles lightweight 'do it now while we talk', heavyweight 'define precisely, run later', and 'just help me think about this' — all on the same skill. Use when the user describes a task or intent they want to align on. Trigger phrases include 'help me plan this', 'let's think this through', 'I want to explore X', 'I have an idea', '/task-alignment'. Also use proactively when a user jumps into a complex task without defining scope or success criteria — pause, align, and help them pick the right vessel (this session vs. a task).
> Find and download virtually any digital resource from the internet — ebooks, academic papers, movies, TV shows, music, software, images, fonts, courses, and more. Covers both English and Chinese internet ecosystems. Includes CLI tool workflows (yt-dlp, aria2, gallery-dl, spotdl), resource site directories, cloud drive search engines (百度/阿里/夸克网盘搜索), and search from a URL, (2) find and download an ebook or academic paper, (3) find and download software, (4) search for any digital resource, (5) batch download images or media from a gallery/site, (6) download torrents or magnet links, (7) find free stock assets (images, video, audio, fonts), (8) search Chinese cloud drives for resources, or (9) any task involving finding or downloading digital content from the internet.
Autonomous task execution driven by documents under `.task/<MMDD_slug>/` (produced by /task-alignment). Reads task.md as the goal, decomposes work, delegates to subagents when appropriate, runs independent verification, and delivers results. Acts as a UserProxy Agent — the human's representative during autonomous execution. Use when a task subdirectory exists in `.task/` and the user wants to start execution, or right after completing /task-alignment. Trigger phrases include '/task-implement', '/task-implement <slug>', 'start the task', 'go ahead and implement', 'execute the plan', or when the user confirms alignment documents and says something like 'looks good, go'.
多AI并行深度研究。当用户需要对某个主题进行全面调研、深度研究、多方对比、或需要覆盖多个维度和来源的综合分析时触发。适合复杂主题（技术选型、竞品分析、行业趋势、争议性话题等），不适合简单事实查询。通过多个AI服务并行研究，交叉验证，输出带引用的综合报告。
> 🤖 Data Science & AI/ML skill suite derived from VoltAgent/awesome-agent-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.
N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' / 'adversarial empirical review'. Do NOT auto-trigger on generic 'review my results', 'check my tables', or manuscript-editing requests. For prose-style refinement use style-emulation instead; this skill AUDITS WHETHER THE TABLES ARE CORRECT — that each number in the tables is what the analysis code computes, reproduces from the data, and is internally consistent. It is an empirical + code review: the manuscript is read only to resolve table numbering, and prose is not examined.
| Download the actual PDF binary from bot-gated sites (taxpolicycenter.org, urban.org, SSRN-hosted mirrors, think-tank/publisher sites) via the Wayback Machine id_ URL form. "EOF marker not found" on a freshly downloaded file, (3) Firecrawl can parse the PDF to markdown but you need the original file on disk (e.g., filing a reference copy).
>- Place pre-screened literature citations into a LaTeX or Word manuscript, or restyle the with a compiled references.bib, for author-date journals (APA, MLA, Harvard, Chicago author-date, IEEE, Vancouver); (2) footnote placement — full formatted \footnote{} or OOXML footnotes for legal and notes styles (Bluebook, OSCOLA, Chicago, APA, McGill) with Id./supra short forms; (3) restyle — convert existing footnote citations from one style to another. This skill is manual-invoke ONLY — trigger ONLY when the user explicitly runs /cite-placement or explicitly names the "cite-placement" skill. Do NOT auto-trigger on general citation, footnote, or reference requests.
| Build human adjudication / hand-labeling sheets from LLM-pipeline data without rule on cases an LLM classifier or rater panel judged, (2) a labeler reports "there is no information to label from" or cells look empty in Excel, (3) excerpt columns cluster at one exact length (e.g. all 1,500 chars — a hard multi-line CSV mangling, ruling dropdowns, companion text files.
| Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
>- Complete methodology for computing publication-quality cumulative abnormal returns with proper event-study test statistics, matching the robustness of Kaspereit's eventstudy2 for Stata. Covers dateline construction, event-date mapping, estimation and event windows, thin-trading adjustment, OLS with Theil prediction error correction, abnormal return computation, CAR/CAAR/AAR accumulation, boundary contamination guards, and common tests such as Patell, BMP, Kolari-Pynnonen, generalized sign, Wilcoxon, and GRANK-T. Use when the user mentions abnormal returns, event windows, market-model regressions, CARs, CAAR, AAR, eventstudy2, thin trading, trade-to-trade returns, or event-study test statistics.
>- Set up, format, fix, and clean up LaTeX regression and estimation tables in empirical economics or finance papers. Use when (a) creating a .tex, results.tex, main.tex, or preamble to display regression or estimation output from Python (pyfixest), Stata, or R — including any mention of estout, esttab, estauto, estwide, or table fragments; (b) formatting or repairing estout-style regression tables that overflow the right margin, have cramped or boxed notes, misaligned columns, or poor significance stars, or when asked to match a reference paper, make the note fill the table width, or choose among \estwide, \estauto, and landscape layouts; (c) diagnosing "Misplaced \omit" errors from \input-ed table fragments inside tabular environments. Covers \@@input, \estwide, \estauto, \estautoLT, \specialcell, \sym, minipage notes below tabulars, and the convert-and-verify workflow. Do NOT trigger for general LaTeX documents like beamer presentations, problem sets, letters, or CVs.
| Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.
> Master controller for the lit-review pipeline, driven by a document. Give it a .tex or .docx file describing an article — a full manuscript, an abstract, or a proposal — and it extracts a search plan, runs Undermind (an automated Playwright driver in Classic mode) and Google Scholar (SearchAPI.io), then merges, deduplicates, and screens the results. Only use this skill when explicitly requested — e.g., the user says "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator". Do NOT auto-trigger on general literature review requests.
>- Convert between LaTeX and Microsoft Word for academic manuscripts in either .tex/LaTeX to Word/.docx ("tex to docx", "latex to word", "tex2docx", "convert to word", "pandoc convert"); converting .docx manuscripts to LaTeX for editing and back ("convert to latex", "manuscript", "footnotes", "reference doc", the docx-to-tex-to-docx round-trip / academic paper editing pipeline); high-fidelity delivery where plain pandoc loses tables, mangles cross-references, or fails on custom macros — booktabs/regression tables, OMML equations, cleveref, \estauto, \@@input, \thanks, TikZ, native Word tables, longtable, siunitx; and building .tex from mixed PDF/docx/LLM-generated sources. Replaces and reroutes the retired skills manuscript-editing-template-latex, latex-to-docx-fidelity, tex2docx, and latex-from-mixed-sources.
>- research question produced by Stage 0, scrape each result's citation (Cite to BibTeX), then parse + enrich into the pipeline schema. The driver signs in to Google with a persistent profile and runs headless via Playwright. Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.
> prior stages (Undermind, Scholar Labs, supplementary search) into a single LLM fuzzy match via DeepSeek/Claude. Only use this skill when explicitly requested — e.g., the user says "run lit-dedup", "lit-dedup", or "/lit-dedup". Do NOT auto-trigger on general literature review requests.
> Scholar (--scholar), SSRN, NBER, HeinOnline, citation chaining via Semantic Scholar, and forthcoming paper lists from top finance journals. Long research prompts are automatically condensed into 3-5 short queries via Claude Sonnet before searching. Only use this skill when explicitly requested — e.g., the user says "run supplementary search", "supplementary-search", or "/supplementary-search". Do NOT auto-trigger on general literature review or paper search requests.
> search (Interactions API) from the brief produced by Stage 0, then parse the cited report into the pipeline schema. API-driven (GEMINI_API_KEY), no browser. An alternative deep-search pathway alongside Undermind (Stage 1) and Scholar Labs (Stage 2). Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.
Run the lit-review orchestrator free index search channel against keyless OpenAlex, Crossref, and Semantic Scholar keyword-search endpoints. Use when the user invokes the free search channel, asks for keyless scholarly index search, or needs Stage 4e fallback discovery without SearchAPI, Gemini, or Undermind credentials.
> research prompt. The orchestrator's agent-driven flow runs this re-ranker on Opus subagents; a standalone run uses the in-script Claude Sonnet API fallback. Rates relevance 1-10, tags each paper as theoretical/empirical, identifies methodology, and classifies relationship to user's work. Only use this skill when explicitly requested -- e.g., the user says "run lit-screen", "lit-screen", or "/lit-screen". Do NOT auto-trigger on general literature review requests.
> from the natural-language brief produced by Stage 0, then parse + enrich the exported references into the pipeline schema. The driver logs in automatically with stored credentials and runs headless via Playwright. Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.
>- Convert Markdown (.md) files to a polished PDF with ALL images preserved and scaled to the page. Use whenever the user asks to "save this markdown as a PDF", "convert README.md to pdf", "export the .md as a pdf", "turn these notes/docs into a PDF", or wants a PDF deliverable of any GitHub-flavored Markdown document (README, design doc, report, notes) — especially when it contains images or diagrams (remote or local), tables, code blocks, or a headless Chrome print-to-pdf with a GitHub-like print stylesheet → pypdf verification that every referenced image is embedded. Do NOT use for .tex → PDF (use a LaTeX toolchain) or for .docx work (use word-docx / tex2docx).
| Gate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt-*-latest, gemini-*-preview, any credit-exhausted scoring run days after its last chunk, (2) topping up credits to finish a campaign, (3) extending a cached scoring pipeline with new items. Prevents silently splicing two model versions or serving serving-revision drift WITHIN DeepSeek v4-flash (same alias, same family, litigation scores systematically shifted across a 2-day gap) before an $83 resume spend.
Run the lit-review orchestrator keyless agent-driven web search channel that uses WebSearch and WebFetch outputs normalized through websearch_ingest.py. Use when the user invokes the web search channel, asks for Stage 4d open-web literature discovery, or needs a Claude Code web-search fallback without SearchAPI, Gemini, or Undermind credentials.
| Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix candidates are prompt edits, (3) inter-rater agreement on the the exact feature the revision would exclude, no prompt can pass a gold-scored gate — recall craters while precision barely moves. Also documents the verified surgical-pilot design (single-section diff, tune/holdout split, pre-registered gate, perturbation check on untouched sections).
Style every matplotlib figure like the Stata 18/19 default (stcolor) scheme — Arial embedded as TrueType, white background, recessive light-gray grid below the data, no top/right spines, unframed legends, and the validated blue/red/gray palette. Use whenever a task generates or restyles charts, plots, or figures for papers, reports, or slides, even if the user doesn't mention Stata — this is the house style for all publication figures. Also use when asked to make figures "look like Stata", match the stcolor scheme, or restyle existing matplotlib output.
| pyfixest demeaner_backend="cupy64" (including its CPU fallback when cupy is absent) is NOT numerically identical to the default numba backend and does adding demeaner_backend="cupy64" to existing pf.feols/fepois calls changes the printed coefficient table, (2) a regression report suddenly gains rows with absurd estimates (e.g. coef 435.8, SE 7106) for controls absorbed by the fixed effects, (3) diffing outputs before/after a backend change, or (4) anything parses a pyfixest text report by line position.
| Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.
>- Use this skill whenever the user asks to run Stata commands, estimate econometric models, work with .dta files, run a .do file, generate Stata output, or do any statistical analysis where Stata is involved. Also trigger when the user mentions Stata variables, Stata syntax, or econometric tasks where Stata is the natural tool, including regressions, IV estimation, diff-in-diff, RDD, panel data, clustering, summary statistics, and margins. Stata runs through pystata on StataNow 19.5 BE; configure once with stata_setup, then drive everything with stata.run() and exchange data directly with pandas. Prefer this skill over subprocess calls or .do-file shelling for Stata work, including cases where the user does not say pystata.
Connect to and query WRDS (Wharton Research Data Services) from any research project. Use this skill whenever the user needs to download, query, or explore data from WRDS — including Compustat, CRSP, FactSet, I/B/E/S, or any other WRDS-hosted database. Also trigger when the user mentions WRDS tables, WRDS libraries, or wants to look up variable definitions or coverage in WRDS datasets. Do NOT trigger for general SQL or database questions unrelated to WRDS.
Provides the complete Swift Concurrency Migration Guide. Use when migrating to Swift 6, resolving data-race safety errors, understanding Sendable and actor isolation, or incrementally adopting async/await.
| 当用户说「深度研究 X」「深入研究 X」或要求生成某产品、公司、概念、人物、产业链、政策、趋势的深度研究/发展研究报告时触发，自动进行联网搜索和研究，产出排版后的 PDF 文档，总字数通常 1-3 万字。
Parse RSS 2.0/0.9x, Atom 1.0, RSS 1.0 (RDF) and podcast (itunes:*) feeds in Python into typed pydantic v2 models with the `rss-parser` package. Use this skill whenever a task involves reading, polling, validating or normalizing a feed in Python - building a feed reader or aggregator, ingesting podcast episodes, deduplicating items while polling, extracting namespaced tags like dc:creator or media:content, or converting feed XML to JSON - even when the user only says "parse this RSS", names feedparser, or hands over a feed URL without naming a library.
> Spin off parallel cloud Devin sessions. Hand off a task to a fresh cloud Devin session that runs in the background — each gets its own VM with shell, browser, and full repo access — so you can fan out several sessions at once and keep working locally while they run. Use for parallel or long-running work and CI work, browser automation, migrations, or large refactors. Also an API for reading and interacting with current sessions — given a session URL or ID, the check/poll commands return its PR, status, branch, and latest message.
Search your conversation history using ripgrep. Use when you need to find previous messages, file edits, tool calls, or decisions from earlier in the session.
> Build beautiful, editable Feishu / Lark (飞书) whiteboards with deliberate composition, not just good colour. Use whenever the user wants to create or draw a Feishu whiteboard, infographic, diagram, poster, system map, or visual explainer and wants it to actually look designed — strong visual hierarchy, intentional layout, breathing room — rather than a templated grid of boxes. The agent commits to a design brief (composition archetype + colour strategy + type roles + an anti-cliché check) BEFORE drawing, builds against a coordinate skeleton with a fixed type scale and spacing grid, then runs a design-critique pass (hierarchy / balance / density / contrast / alignment) after rendering and fixes the weakest axis until it clears. Returns the doc link and the rendered image, and offers to switch palettes. Requires lark-cli (npm @larksuite/cli) installed and authenticated, and a Feishu/Lark account.
> 把内容生成为「真正设计过」的可编辑飞书白板——强视觉层级、有意图的构图、留白，而不是 一堆等大方块。先定设计简报（构图原型 + 配色策略 + 字号角色 + 反套路检查）再画，按坐标 骨架施工，渲染后跑设计评审（层级/平衡/密度/对比/对齐）补到最弱项达标，最后写进你自己的 飞书文档成为可编辑白板。飞书走扣子「平台授权」，一键授权即用（见 CREDENTIALS.md）。
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use for web browsing, form submission, web scraping, or UI testing. NOT for static content (use curl/wget).
| This skill conducts discovery conversations to understand user intent and agree on approach before taking action. It should be used when the user explicitly calls /interview, asks for recommendations, needs brainstorming, wants to clarify, or when the request could be misunderstood. Prevents building the wrong thing by uncovering WHY behind WHAT.
Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.
AI video production workflow using Remotion. Use when creating videos, short films, commercials, or motion graphics. Triggers on requests to make promotional videos, product demos, social media videos, animated explainers, or any programmatic video content. Produces polished motion graphics, not slideshows.
| Creates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Gathers context from codebase, conversation, and authentic sources before creating adaptable skills.
| Validates skills against production-level criteria with 9-category scoring. This skill should be used when reviewing, auditing, or improving skills to ensure quality standards. Evaluates structure, content, user interaction, documentation, domain standards, technical robustness, maintainability, zero-shot implementation, and reusability. Returns actionable validation report with scores and improvement recommendations.
Generates a complete fullstack application template with Python FastAPI backend and React Vite frontend. Includes OpenAI ChatGPT integration, CORS configuration, comprehensive error handling, and a modern Tailwind CSS + shadcn/ui React UI. Use this skill when the user wants to bootstrap a new fullstack web application project with both API backend and web frontend components ready to go.
> 电商美工助手 - 做详情页、海报、Banner、社媒封面、套模版、AI生图、批量适配。支持淘宝/京东/拼多多/小红书/抖音/公众号全平台尺寸。发送"做详情页"、"做海报"、"做主图"、"做封面"开始。关键词：电商设计、产品图、详情页、海报设计、Banner、美工
店铺视觉风格拆解 - 自动分析电商店铺/竞品的配色方案、排版布局、摄影风格、设计语言。支持淘宝/天猫/京东/拼多多店铺。激活条件：需要竞品分析、风格提取、视觉对标、店铺拆解、配色分析时使用。关键词：竞品、风格分析、配色、视觉DNA、设计语言、store teardown、visual analysis
美工全流程 - 从参考店铺到成品设计，自动分析风格并生成同风格电商素材（主图、海报、Banner）。激活条件：(1) 用户需要分析店铺/竞品视觉风格 (2) 用户需要生成电商产品主图 (3) 用户需要制作活动Banner/海报 (4) 用户需要批量生成同风格产品图 (5) 用户需要从参考URL提取设计语言并复用。关键词：美工、设计、主图、海报、Banner、批量生成、风格分析、店铺拆解、电商素材、详情页、小红书、产品图、视觉风格
踩坑经验库 - 遇到问题时自动查阅 GitHub 上的历史踩坑记录(Capsule)，解决后自动提交新经验回 GitHub Issue。激活条件：(1) 遇到报错/异常/失败时 (2) 配置不生效或行为异常时 (3) 成功解决一个非显而易见的问题后 (4) 用户要求查阅或记录经验时。关键词：踩坑、经验、报错、failed、error、不生效、为什么、pitfall、experience
UI/UX 设计智能助手 - BM25 搜索引擎覆盖 8 大设计领域（风格/配色/字体/图表/Landing/产品/UX/Prompt），支持 8 种框架技术栈。当需要界面设计参考、配色方案、字体搭配、UI审查、设计规范时使用。关键词：UI设计、界面优化、配色、字体、设计规范、landing page
获取商品在淘宝(Taobao)、天猫(TMall)、京东(JD.com)、拼多多(PinDuoDuo)、抖音(Douyin)、快手(KaiShou)的最优价格、优惠券的技能，商品价格全网对比，当用户想购物或者获取优惠信息时使用。Get the best price, coupons for goods on Chinese e-commerce platforms, compare product prices, and use when users want to shop or get discount information.
| 美股/港股盘前分析框架。抓取五大观测指标（VIX/IGV/MAGS/MEME/布油）、 个股实时价格、期权隐含波动率，生成结构化盘前简报。 包含量化模块：粒子滤波概率追踪、期权蒙卡定价、Copula VaR。 支持持仓 JSON 格式管理，实时浮盈亏计算。
> Nano Banana2 多模态 AI - 支持文生图、图生图、Vision 分析。发送"生图 柴犬"生成图片，发送图片+描述做风格化重绘。底层调用 Gemini，支持 10 种宽高比。关键词：生图、画图、AI画图、文生图、图生图、generate image、Gemini、重绘
上传视频/音频/图片到即梦(Jimeng) VOD 平台并获取 Vid。支持 mp4/mp3/jpg/png 等格式，自动处理 STS 鉴权和分块上传。当需要上传媒体文件、获取视频ID、发布素材到字节跳动平台时使用。关键词：上传、即梦、VOD、视频ID、媒体文件
小红书笔记素材创作技能。当用户需要创建小红书笔记素材时使用这个技能。技能包含：根据用户的需求和提供的资料，撰写小红书笔记内容（标题+正文），生成图片卡片（封面+正文卡片），以及发布小红书笔记。
Claude Skills — questions
Answers built from the skills we actually parsed.