Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Write content to Feishu documents, create new documents, and create blank documents. Supports creating documents from Markdown with doc import; precise append/overwrite/replace/insert/delete operations with doc content-update; low-level block operations with doc add/update/delete; and image/file insertion. Use when the user requests creating, writing, or updating a document; replacing, inserting, or deleting a section; appending content; overwriting a document; or inserting an image or file.
Finds trending products on TikTok Shop using apidojo's TikTok scraper on Apify. Triggers when the user asks to: find trending TikTok Shop products, discover what products are selling on TikTok Shop right now, identify viral TikTok Shop items in a category, find trending items with TikTok affiliate links, research TikTok Shop bestsellers, discover products going viral on TikTok for e-commerce, find hot items being promoted by TikTok creators, or build a trending product list from TikTok Shop data. Returns product name, creator promotion count, engagement signals, price range, and trend momentum. Ideal for TikTok Shop sellers, dropshippers, and e-commerce trend researchers.
The cultural-fluency + meme-craft skill — participate in internet culture and meme formats as a brand without being cringe, tone-deaf, or legally exposed. Use when someone wants to make a meme, join a cultural moment, build a meme/humor pillar, or decide whether to jump on a format. Meme marketing done wrong is worse than none. Uses the VIBES framework. Reads brand-profile + the meme/moment first. Two hard gates: brand-fit (would it work without your logo?) and safety + IP (never tragedies/divisive/ appropriation/punching-down; original visuals only, no copyrighted characters or celebrity likeness). The agent advises fit/safety/IP and writes the copy/concept; the human/creator makes the asset and adds the final wit pass; WoopSocial publishes/schedules (reactive ones often post in the moment). Sitting a meme out is valid; never fabricates relevance or virality. Distinct from trend-jacking, image-prompt/design-and-templates, community-management, and ai-music-and-sound.
Monitors Twitter for competitor hiring announcements to track growth signals using apidojo's Tweet scraper. Triggers when the user asks to: monitor competitor job postings on Twitter, track hiring signals from competitor companies on X, find out what roles competitors are hiring for on Twitter, analyze competitor team growth from their Twitter activity, monitor startup hiring signals for competitive intelligence, track which departments competitors are growing via their Twitter, or discover competitor expansion strategies from job post tweets. Returns company handle, role being posted, department, posting date, urgency signals, and growth pattern. Ideal for competitive intelligence teams, recruiters targeting competitor employees, and investors tracking company growth.
SuiteScript 1.0, 2.0, and 2.x to 2.1 migration assistant. Analyzes, converts, explains, and validates script upgrades. Covers 125+ API mappings, 34 object conversions, 13 unmapped API workarounds, all script type entry point changes, SuiteScript 2.0/2.x to 2.1 upgrade guidance, and 16 categories of breaking behavioral changes. Essential for modernizing legacy SuiteScript codebases.
Best practices for building Nuxt 3 and Vue 3 applications with TypeScript, the Composition API, and Tailwind CSS. Use when structuring Nuxt/Vue projects, writing composables, typing components and props, wiring up server routes and plugins, or optimizing Nuxt builds and Web Vitals.
Track which stacks across a Pulumi organization use a specific package and at what versions. Use for cross-stack audits, identifying outdated or unmaintained package versions across many stacks, finding affected stacks before publishing breaking changes to a component package, or planning coordinated upgrade rollouts. Do NOT use for upgrading a cloud provider package (pulumi-aws, pulumi-azure-native, pulumi-gcp, pulumi-kubernetes, etc.) in a single project — use skill `provider-upgrade` instead. Do NOT use for general infrastructure creation, resource provisioning, or how-to questions about a package.
Use when animating characters or objects in Blender through Python, a bouncing ball, walk or run cycle, jump, acting shot, lip sync, eye darts or facial animation, blocking in stepped keys, splining, polish, timing and spacing, arcs, overlap, squash and stretch, graph editor handles, slotted actions or NLA layers, staging a playblast, or when animation looks floaty, stiff, slides, pops, chatters, the subject is too small in frame, or a knee pops and needs an expert review.
Scrapes Instagram posts tagged at a specific location or place using apidojo's Instagram Location scraper on Apify. Triggers when the user asks to: get Instagram posts from a location, scrape photos tagged at a restaurant or hotel, fetch Instagram content from an event or venue, collect posts from a geographic area on Instagram, export location-tagged Instagram media, or find what people post from a specific place on Instagram. Returns post URL, author handle, caption, likes, comments, and timestamp per post. Ideal for hospitality brands, event teams, and UGC content collectors.
Use to write a thread — a connected sequence of posts on X/Twitter or Threads that tells one story or makes one argument across multiple posts. Run when the user says "write a thread," "turn this into a thread," "X thread," "Twitter thread," "thread about X," or has a multi-beat idea that won't fit one post. Reads brand-profile and voice first, uses hook-writer for the opening post (which must hook AND promise the payoff), builds one cohesive idea where every post earns the next, and lands a close with one CTA. Knows when a single post beats a thread. Naming trap: "write a thread" means this multi-post chain; "post on/to Threads" means a single post on Meta's Threads app — use threads-post for that. For a single caption use caption-writer; for just the opening hook use hook-writer.
The TikTok Photo Mode format-execution skill. Use when someone wants a “TikTok photo carousel,” “photo mode,” “TikTok slideshow,” “swipeable TikTok post,” or to publish a multi-image TikTok post via WoopSocial (postType PHOTO). Builds a TikTok-native carousel designed for completion rate: hook slide 1, progressive reveal with cliffhangers, reward + one CTA — and sets the exact WoopSocial PHOTO publish config (privacy, comments, music, truthful disclosure flags). Uses the SWIPE framework. Reads brand-profile + goals-and-kpis first. The agent writes the slide plan + overlay copy + caption + config; the IMAGES are made by a human/image skill, not WoopSocial; WoopSocial publishes the native PHOTO post; metrics are never fabricated and photo mode is never promised as a reach hack. Distinct from tiktok-script (VIDEO) and carousel-writer (cross-platform copy)
UGC and influencer marketing — paid or gifted creator partnerships, briefs, usage rights, and disclosure done right. Use when someone wants to run an influencer campaign, sponsored post, paid or gifted creator partnership, write a creator brief, license/whitelist creator content, source customer UGC, or build a UGC pipeline. Vets creators on engagement + audience quality (not follower count); briefs with guardrails not scripts; inks usage rights up front; enforces FTC/ASA disclosure on EVERY paid AND gifted post; runs the customer-UGC pipeline. Uses the BRIEF framework. Reads brand-profile + goals-and-kpis first. WoopSocial publishes the BRAND'S OWN posts (rights-cleared UGC reshares, campaign posts) — NOT creator DMs/payment/whitelisting/contracts. Undisclosed sponsorship = decline and correct; a tag is not usage permission. Distinct from collabs-and-cross-promotion (mutual, unpaid), creator-monetization (the creator's side), and social-proof-and-testimonials (UGC as proof content)
Audit herdr release readiness by comparing commits since the base release against next-release changelog and docs. Use when asked to run or apply the repo's pre-release audit, validate docs/next before release, inspect issue refs that release CI will close, or finalize release docs for herdr
Detect software architecture bad smells, algorithmic complexity hotspots, and anti-patterns in a codebase. Produces a detailed markdown report identifying violations of architectural principles, design patterns, code quality, and performance complexity. Triggers on: smell, code smell, architecture smell, find anti-patterns, detect bad smells, complexity analysis, 代码坏味道, 架构坏味道, 反模式, 找出坏味道, 复杂度分析.
The craft of turning real data into honest, scannable, shareable infographics and charts. Use when someone wants to visualize data, make an infographic, build a chart/graph, turn a finding or stat into a visual, or fix a chart that's confusing or misleading. A great data viz makes one insight land in 3 seconds. Uses the CHART framework (chart choice, headline takeaway, honest scale, reduce to signal, tag source + accessibility). Reads brand-profile + design-and-templates first and pulls real data from data-and-original-research / analytics-and-reporting. The agent designs the spec; a design/chart tool renders it; the human approves; WoopSocial publishes the image (it does not generate media). NEVER distorts scales or fabricates a data point/source; cites source + date; accessibility required. Distinct from design-and-templates (brand design), quote-cards-and-text-graphics (a lone quote/number), data-and-original-research (originates the data), and analytics-and-reporting.
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.
Identifies and tracks thought leaders and key voices in any industry on Twitter/X using apidojo's scrapers. Triggers when the user asks to: find the top voices in an industry on Twitter, identify thought leaders in a niche, discover who has the most influence in a topic area on X, find experts tweeting about a subject, build a list of influencers to engage with on Twitter, track who is gaining followers fastest in a category, or identify key opinion leaders in a field for PR or partnership outreach. Returns name, handle, follower count, engagement rate, bio keywords, and recent top tweets. Ideal for PR teams, community managers, and B2B content marketers.
Creator collabs and cross-promotion — organic creator-to-creator partnerships that swap audiences. Use when someone wants to set up a collab, audience swap, cross-promotion, shoutout swap, joint giveaway, guest spot, joint video/series, a YouTube/IG collab post, or co-promo with another creator. Picks a complementary, similar-size, values-aligned partner, agrees the plan before creating, and co-creates shared-value content (not a bare shoutout) on a coordinated schedule. Uses the UNITE framework. Reads brand-profile + goals-and-kpis first. WoopSocial publishes each partner's OWN posts to their OWN accounts; it does NOT create native IG Collab co-authored posts, run giveaways, duet/stitch, or manage the agreement. A pure mutual collab isn't a sponsorship, but payment/free product makes it one -> disclose -> ugc-and-influencer; partnerships must be genuine; metrics never fabricated. Distinct from ugc-and-influencer (brand->creator) and creator-monetization (the creator's income).
Guide AI agents through Electron app development with React including security patterns, type-safe IPC, React integration, packaging with code signing, and testing. Keywords: electron, electron-vite, electron-forge, contextBridge, IPC, security, react, packaging, code signing, notarization, playwright, desktop app.
Extracts slang definitions, cultural terms, and crowd-sourced meanings from Urban Dictionary using apidojo's Urban Dictionary Scraper on Apify. Triggers when the user asks to: look up internet slang terms, find how Gen Z or millennials define a word, research cultural vocabulary or meme terminology, understand what a term means on social media, analyze slang used in brand monitoring, find crowd-sourced definitions for multiple keywords, or track how language is evolving around a topic or brand name. Returns word, definition, usage example, author, upvotes, downvotes, and date. Ideal for brand researchers, social media analysts, content teams, and cultural marketers.
Terminal User Interface (TUI) performance and UX guidelines for TypeScript applications using Ink and Clack. This skill should be used when building CLI tools, interactive terminal prompts, or developer tooling with TUI components. Triggers on tasks involving TUI components, CLI prompts, terminal rendering, keyboard input handling, or developer tooling.
The Canva craft skill — produce on-brand social graphics, carousels, quote cards, infographics, and thumbnails at scale without a designer, and escape the "Canva look." Use when someone wants to design in Canva, make social graphics, set up a Brand Kit, batch-produce graphics (Bulk Create), resize one design for every platform (Magic Resize), use Canva's AI (Magic Studio), or asks why their posts look like a template. Uses the SCALE framework. Reads brand-profile + design-and-templates + voice-builder first. The agent specs, and creates designs directly where the Canva MCP/Connect APIs are connected; the human approves every visual; the export publishes via WoopSocial. Never strips watermarks, impersonates another brand, or uses unpermitted likeness; AI-disclosure + accessibility floor apply. Distinct from design-and-templates (the brand system this executes), image-prompt + the image tools (dedicated generation), ai-image-editing (the edit router), and capcut/descript (video editing).
Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit an `lfg`-ready plan. First run sets up sources; supports mode:non-interactive for scheduled runs.
Defines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptions to test or aligning a team on what success looks like, before any experiment is designed. To design the A/B test or experiment that will validate the hypothesis, use measure-experiment-design.
Use when installing or running the Inngest CLI and Dev Server for local development, local testing, serve endpoint debugging, Docker or Docker Compose setup, MCP configuration, self-hosted `inngest start`, or deployment workflow checks. Covers `inngest dev`, `inngest start`, auto-discovery, config files, environment variables, `@inngest/test`, local event sending, platform gotchas, and production/self-hosted server flags.
Lead magnets and funnels — design offers that turn social traffic into subscribers, leads, and customers. Use when someone wants to "create a lead magnet," "build a funnel," "design a freebie/opt-in," "make a quiz/calculator/template to grow my list," or turn social traffic into qualified leads and customers. Designs the magnet the capture paths deliver PLUS the whole social->capture->nurture funnel, using the MAGNET framework. Reads brand-profile + goals-and-kpis first. WoopSocial has no landing/form/email/quiz builder: the agent designs the magnet + funnel and drafts the nurture and promo posts; WoopSocial publishes the promo posts; capture/delivery/nurture run in external tools; metrics from those + GA4, never fabricated; no dark patterns. Distinct from link-in-bio-and-traffic / social-selling-and-dm (the capture paths) and email-and-newsletter (the owned channel).
Create, modify, debug, or migrate Minecraft mods for current NeoForge or Fabric 26.x, legacy 1.21.x, and Forge 1.20.1. Use for loader-based gameplay code and assets; use minecraft-multiloader when one codebase must target both modern loaders.
Deploys a chosen Unified Catalog Service Process template into a Salesforce org using the Salesforce CLI (sf), resolving the template by name against the live catalog and verifying by re-reading. Deterministic: it deploys only a template the user explicitly named, only when the name resolves to exactly one live template, and never guesses. Use when a business user asks to deploy, install, activate, set up, or provision a specific Unified Catalog or Service Process template they already identified—for example, “deploy the Reset Account Password template” or “install the laptop request service process”. Triggers on: deploy a catalog template, install a Service Process template, set up the X template, activate the X service process. Do not trigger when the user is still searching or comparing templates and has not named one (use service-catalog-template-search), or when the request concerns Data Cloud data kits, CRM Analytics, or App Framework templates rather than Unified Catalog Service Process templates.
Searches the Salesforce Unified Catalog for available Service Process templates matching a business need, using the Salesforce CLI (sf), ranking them by relevance to the request. Read-only: it recommends and installs nothing. Use when a business user wants to find, search, browse, discover, or explore available Unified Catalog or Service Process templates for a request, or asks what catalog templates exist. Triggers on: find a catalog template, search Service Process templates, what Unified Catalog templates are available, browse the service catalog, is there a template for X, recommend a template for this request. Do not trigger when the user already chose an exact template and asks to deploy, install, or activate it (use service-catalog-template-deploy), or when the request concerns Data Cloud data kits, CRM Analytics, or App Framework templates rather than Unified Catalog Service Process templates.
Implements Syncfusion React Grid component for feature-rich data tables and grids. Use this when working with data display, sorting, filtering, grouping, aggregates, editing, or exporting. This skill covers grid configuration, CRUD operations, virtual scrolling or infinite scrolling, hierarchy grids, state persistence, and advanced data management features for data-intensive applications.
Use this skill to poll the status of an asynchronous DevOps Center request — a promotion or deploy operation. Provide the request token returned by dx-devops-promote (the promote response) to check completion, monitor progress, or verify success or failure via sf devops request status. TRIGGER when the user wants to check whether a promotion or deploy finished, monitor an in-flight async request, poll until a request completes, or confirm a request succeeded before finalizing. DO NOT TRIGGER for initiating a promotion or deploy (use dx-devops-promote), for work item creation or status transitions (use dx-devops-work-item-manage), or for conflict detection. Read-only status check — never mutates pipeline state.
JLCPCB PCB fabrication and assembly — BOM/CPL generation, basic vs extended parts, assembly constraints, design rules, ordering workflow. Use with KiCad for JLCPCB manufacturing. Use this skill when the user mentions JLCPCB, wants to order PCBs or assembled boards, needs prototype bare PCBs and stencils, wants to know JLCPCB design rules and capabilities, or is asking about PCB manufacturing costs or turnaround times. For gerber/CPL export, stencil ordering, and BOM management, see the `bom` skill.
LinkedIn company-page (LINKEDIN_PAGES) growth strategy skill — a separate platform from personal LINKEDIN. Use when someone wants to grow a company/business page, fix low page reach ("our LinkedIn page gets no engagement"), set up employee advocacy, or plan company-page content. In 2026, pages get a tiny share of feed reach, so the page is a credibility hub + paid launchpad (Ads + Thought Leader Ads), NOT the reach engine — the growth lever is employee advocacy (people, not logos). Uses the HUMAN framework. Reads brand-profile + goals-and-kpis first. The agent strategizes, designs the advocacy program, and drafts page posts + advocacy content; WoopSocial publishes the page's own posts on a schedule; employees post from their OWN profiles (routes to linkedin-growth); first-hour engagement, Ads, and analytics stay human/native. No bait, pods, or bought followers; never fabricates metrics. Distinct from linkedin-growth (personal profile) and linkedin-post-writer (the post craft)
Use when planning demand generation, paid acquisition across Google, LinkedIn and Meta, or a marketing budget, before allocating spend. Computes blended and per-channel CAC with calculate_cac.py and sets MQL to SQL handoffs.
Monitors Instagram for brand mentions and tagged posts using apidojo's Instagram scraper on Apify. Triggers when the user asks to: track Instagram mentions of a brand or product, monitor hashtag activity around a brand on Instagram, find posts where users tag or mention a company on Instagram, discover organic brand sentiment on Instagram, find untagged brand mentions in captions, track user-generated content featuring a brand, or monitor competitor mentions on Instagram. Returns post URL, caption, author handle, likes, comments, timestamp, and mention type. Ideal for brand managers, social listening teams, PR agencies, and community managers.
Expert guidance for React Flow (@xyflow/react): building interactive node-based graphs, custom nodes and edges, handles, state management, layouting, TypeScript patterns, performance optimization, accessibility, SSR, and theming. Use when writing React Flow code, creating custom nodes or edges, debugging flow issues, optimizing graph performance, integrating with Zustand, or building canvas-based UIs with React Flow.
Investigate a topic against preserved sources and write a draft-status research article under `research/` in a Knowledge Base project (the `knowledge-base` starter pack). Read when asked to research a topic, compare options, synthesize sources, gather evidence, or extend an existing research doc. Carries the full procedure: scan existing coverage, agree a research rubric, capture every source verbatim before analyzing, write the article incrementally so a crash never loses work, cite every claim, and link it back into the graph. Does not promote findings to canonical knowledge — that is the sibling `consolidate-notes` skill, after a decision lands.
Linting and formatting SAS code with @sasjs/lint - the .sasjslint rules and their defaults, the macro-declaration rules and ignoredMacros, banned strings, severityLevel and exit codes, per-file @sasjslint overrides, what the formatter fixes, and how the SASjs CLI, VS Code extension and SASjs Server run it. Use when configuring lint rules, resolving a lint warning, or wiring lint into CI, a git hook or an editor.
Use when subtitles or the spoken text of a YouTube video is needed: pasted video links or IDs, requests to translate a video, read along, follow foreign-language content, or extract what was said. Also use for language learning or accessibility. Fetches timestamped subtitles from any YouTube video. Not for uploading subtitles or account management.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.