Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Read, download or archive known web/social media links, URL lists, confirmed candidates or explicit bounded containers according to the user's request in the current turn. Supports explicitly bounded site archiving; not for keyword discovery, recommendation expansion or private bookmark export.
Automation skill for Lovable deployments. Activates when: - yolo_mode: on in CLAUDE.md - Running /deploy-edge or /apply-migration commands - After git push when auto_deploy: on (automatic detection) - Any mention of "yolo mode", "automate Lovable", "browser automation", "Lovable MCP" Uses Lovable MCP (preferred) or browser automation to submit deployment prompts. Runs verification tests based on configuration. Auto-deploys after git push when enabled.
Deep expertise on the ziflux Angular library — SWR caching for resource(). Use this skill whenever implementing cachedResource, cachedMutation, DataCache, or provideZiflux in Angular code. Also use when reviewing, debugging, testing, or cleaning up code that uses ziflux, or when the user asks about SWR caching patterns in Angular, data freshness lifecycle, or cache invalidation strategies. Triggers on: ziflux, cachedResource, cachedMutation, DataCache, SWR cache Angular, stale-while-revalidate Angular, cache invalidation Angular, optimistic updates Angular signals.
Build type-safe global state in React applications with Zustand. Supports TypeScript, persist middleware, devtools, slices pattern, and Next.js SSR. Use when setting up React state, migrating from Redux/Context API, implementing localStorage persistence, or troubleshooting Next.js hydration errors, TypeScript inference issues, or infinite render loops.
Use when you need to brief a specific campaign for the whole execution team — objectives, messaging, deliverables, a week-by-week timeline, approval gates, and a risk matrix. Trigger when the user mentions 'brief chien dich', 'ke hoach campaign', 'len brief cho team', 'chien dich thang toi', 'phan cong campaign', 'timeline chien dich'. Not for — a full-term marketing plan, use skill 00-ke-hoach-mkt; the list of assets to design, use skill 41-campaign-asset-list; assigning work to each person, use skill 64-team-brief.
Use when a specific campaign needs a brief the whole team can execute from — context, objective, audience, core message, creative direction, channels, deliverables, week-by-week timeline, approval gates, and risks. Trigger on 'campaign brief', 'creative brief', 'launch brief', 'brief the team on this campaign', 'we are running a promo next month', 'what is the plan for this campaign'. Also use when the user describes a promotion out loud and asks for something the team can actually run. Not for — the whole period plan, see `00-marketing-plan-global`; the list of design files needed, see `41-campaign-asset-list-global`; assigning work to one person, see `64-team-brief-global`; a new product launch sequence, see `59-go-to-market-global`.
Use when marketing numbers are bad and you need to know WHY — diagnose across 5 layers from tracking, delivery, creative, landing page to audience quality, then produce a 48h action plan. Trigger when the user mentions 'so dang xau', 'CPMess cao qua', 'ROAS thap', 'chan doan root cause', 'tai sao khong ra don', 'ads dot tien'. Not for — auditing the ad account setup and scoring Health Score, use skill 21-audit-ads-performance; writing a report for others to read, use skill 07-bao-cao-marketing; diagnosing a single page, use skill 68-cro-audit-trang.
Use when you need to write PAID ad copy for Meta, TikTok, or Google — 6 variants across the 3 TOFU/MOFU/BOFU funnel layers, complying with character limits and platform policies. Includes Mode A for products and Mode B for personal brands, auto-selected based on the context file. Trigger when the user mentions 'viet copy quang cao', 'noi dung chay ads', 'copy Facebook Ads', 'copy TikTok Ads', 'google rsa', 'tieu de quang cao', 'copy retarget'. Not for — organic captions with no paid spend, use skill 37-caption-social; slogans / puns / poster headlines, use skill 74-copy-hai-lop; video scripts, use skill 04-script-video; reviewing copy already written, use skill 62-marketing-review.
Use when the user needs to work backward from a revenue goal to the numbers that produce it — required leads, max CPA and CPL, funnel conversion thresholds, and the budget that has to be spent, with three scenarios and currency handling for US, EU, SEA, and LATAM. Trigger on 'reverse KPI', 'how much budget do I need', 'what CPA can I afford', 'work backward from revenue', 'how many leads to hit target', 'break-even ROAS'. Also use when the user names a revenue target and asks whether it is realistic. Not for — splitting an existing budget across channels and months, see `61-budget-planning-global`; a full paid media plan, see `54-media-plan-global`; the period plan, see `00-marketing-plan-global`.
Use when you need to back-calculate the number of leads needed, the maximum CPL, and the budget you must spend from a revenue target — with 3 scenarios and healthy thresholds at each funnel step. Trigger when the user mentions 'tinh KPI nguoc', 'CPL toi da la bao nhieu', 'can bao nhieu ngan sach', 'tinh nguoc tu doanh thu', 'muc tieu bao nhieu don', 'break-even ROAS'. Not for — allocating an existing budget across channels and months, use skill 61-budget-planning; building a detailed media plan by funnel, use skill 54-media-plan.
Use when a NEW landing page, sales page, or single-product page has to be built — seven-section structure, one page one goal one CTA, copy per block, mobile-first rules, technical and speed requirements, tracking plan, A/B test plan, and a dropshipping single-product mode. Trigger on 'landing page brief', 'build a sales page', 'I need a landing page', 'brief for the dev', 'Shopify product page', 'what should go on the page'. Also use when ad traffic is ready and there is nowhere to send it. Not for — the ad copy pointing at the page, see `05-ad-copy-global`; the offer and its value stack, see `31-offer-design-global`; scoring a finished design, see `47-design-review-global`; coded email, see `49-html-email-template-global`.
Use when you have raw data from Meta, TikTok, GA4, CRM, or Google Sheets and need to turn it into insights you can decide on — with a decision log recording the decision, the basis, the expected impact, and the review date. Trigger when the user mentions 'phan tich du lieu', 'doc so lieu nay', 'export data ra insight', 'so nay noi len dieu gi', 'lam decision log', 'cohort analysis'. Not for — diagnosing why ads are performing badly, use skill 03-danh-gia-hieu-suat; writing a presentation report, use skill 07-bao-cao-marketing.
Use when you need to build email or Zalo OA sequences sent by scenario — welcome series, nurture, promotion, win-back: segmentation, automation flow, subject lines, sending frequency, A/B testing, and open/click KPIs. Trigger when the user mentions 'email marketing', 'chuoi email tu dong', 'welcome email', 'email nurture', 'broadcast Zalo OA', 'co list ma khong biet gui gi', 'email khong ai mo', 'cham soc khach qua Zalo'. Not for — writing HTML email code that runs on any client, use skill 49-html-email-template; building a system to retain customers who already bought, use skill 69-giu-chan-khach-hang; designing a giveaway in exchange for contact details, use skill 70-lead-magnet.
Use when the user wants to monitor what is being said about the brand, competitors, and the category — channels and keywords to track, sentiment scoring, weekly and monthly listening reports, brand health metrics, early crisis detection, and content opportunities pulled from real conversations. Trigger on 'social listening', 'brand monitoring', 'sentiment analysis', 'what are people saying about us', 'track our mentions', 'monitor competitors online'. Also use when the user spotted a bad comment thread and wants to know if it is spreading. Not for — responding to a crisis already underway, see `66-crisis-playbook-global`; competitor strategy teardown, see `08-competitor-research-global`; auditing your own posts, see `39-content-audit-global`.
Use when you need to understand WHY people buy and apply psychological principles to marketing — scarcity, social proof, commitment and consistency, authority, liking, price anchoring, loss aversion — plus how to apply them to copy, landing pages, email, ads, and adapt them to Vietnamese culture. Trigger when the user says 'tam ly khach hang', 'marketing psychology', 'FOMO', 'social proof', 'khan hiem', 'Cialdini', 'lam sao thuyet phuc khach', 'trigger cam xuc', 'khach doc xong van khong hanh dong'. Not for — writing finished copy, use skill 05-copy-quang-cao; designing packages and bonuses, use skill 31-offer-design; diagnosing why a specific page does not convert, use skill 68-cro-audit-trang.
Use when a price has to be set or changed — value-based pricing, anchoring, charm pricing, decoy tiers, good-better-best packaging, discount policy, and margin math, with currency psychology for US, EU, SEA, and LATAM plus dropshipping markup and BE-ROAS. Trigger on 'pricing strategy', 'how much should I charge', 'should I raise prices', 'price tiers', 'customers say it is too expensive', 'dropshipping markup'. Also use when the product is not selling and the user suspects price is the reason. Not for — bonuses, guarantee, and value stack around the price, see `31-offer-design-global`; persuasion beyond price, see `16-marketing-psychology-global`; ad budget math, see `10-reverse-kpi-global`.
Use when you want existing customers to bring in new ones — designing referral, affiliate, and invite-code programs: one-sided or two-sided reward mechanics, reward amounts, tracking, anti-fraud, and a launch plan for the program. Trigger when the user says 'chuong trinh gioi thieu', 'referral program', 'affiliate', 'ma moi ban', 'hoa hong gioi thieu', 'word of mouth', 'khach gioi thieu khach', 'CTV ban hang huong hoa hong'. Not for — retaining existing customers so they buy again, use skill 69-giu-chan-khach-hang; building a community around a personal brand, use skill 28-community-building; hiring KOCs and creators to shoot content, use skill 06-brief-ugc-egc.
Use when you need to systematically review ad account configuration — 6 stages from account, campaign, adset, creative, landing to tracking, a 0-100 Health Score, and a list of Quick Wins. Trigger when the user says 'audit tai khoan ads', 'kiem tra tai khoan quang cao', 'health score ads', 'tai khoan chay kem qua', 'setup ads co dung khong', 'review tai khoan Meta'. Supports Meta, TikTok, Google, Zalo Ads. Not for — quickly diagnosing why numbers are bad, use skill 03-danh-gia-hieu-suat; setting a budget for a new period, use skill 54-media-plan.
Complete academic research skill suite covering the full pipeline: paper reading (read/explain papers with storytelling), idea generation (brainstorm research directions), experiment design (plan experiments, ablation, baselines), proof writing (mathematical proofs, LaTeX theorems), paper writing (draft to camera-ready for top venues like NeurIPS/ICLR/ACL), paper review (structured 4-step review with scoring), and professor fit analysis (evaluate advisors, cold emails, interview strategy). Use when the user wants the full research workflow or is unsure which specialized skill to pick. Trigger keywords: academic research suite, research pipeline, read paper, brainstorm, experiment design, prove, write paper, review, professor fit, advisor, cold email, LaTeX, research, NeurIPS, ICLR, ACL, arXiv, 讀論文, 寫論文, 審稿, 實驗設計, 數學證明, 研究方向, 教授分析, 選指導教授.
Audit a frontend against WCAG and fix what fails: semantic HTML, keyboard navigation, focus management, screen-reader support (ARIA), color contrast, forms, and media alternatives. Use when the user asks 'is this accessible', 'make this WCAG/AA compliant', 'add keyboard navigation', 'fix screen reader support', 'a11y audit', 'we got an accessibility complaint/legal notice', or whenever building/reviewing UI components with interactive behavior — even if accessibility isn't mentioned. Produces a prioritized accessibility audit (issue × WCAG criterion × severity × fix) plus the implemented fixes in code.
Generate Advanced Custom Fields (ACF) Local JSON configurations for WordPress from visual designs or HTML structures. Use when creating ACF field groups, converting designs to ACF schemas, building WordPress custom fields from mockups, or when working with ACF Pro Local JSON format. Supports flexible content, repeaters, clone fields, and all ACF field types.
Use this skill to gate DDD and ubiquitous-language quality with a pass/fail adversarial review — a single blind reviewer subagent judges a diff, a module/bounded context, or a DSL/semantic-model surface against 20 decidable rules across glossary lifecycle (a recorded ubiquitous language is required once domain concepts exist — absence is FAIL; code must conform; entries stay live and carry business meaning), language consistency (one name per concept, one meaning per name, no Manager/Helper/Data names on domain rules, transitions named as operations, one vocabulary across code, tests, docs, UI copy), domain model integrity (anemic models, valid-on-construction, value types over primitives, named states over flag piles), context boundaries (foreign-model reach, vendor-type absorption, infrastructure in the domain, multiple writers), and DSL surfaces. Language-agnostic; repeated runs converge code, team, and stakeholders on one recorded vocabulary. Verdicts only.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Diagnose and resolve ClickHouse grant and authentication errors, especially after upgrades. Use when queries fail with ACCESS_DENIED/NOT_ENOUGH_PRIVILEGES, AUTHENTICATION_FAILED/WRONG_PASSWORD/REQUIRED_PASSWORD, or ON CLUSTER privilege errors; when system.* or INFORMATION_SCHEMA access is denied; or when grant behavior changes after version upgrades.
Deep-research analysis of a codebase, a topic, or both. Clarifies the question, agrees the research angles with you, then runs a dynamic workflow that gathers cited claims per angle, merges duplicates, has independent skeptics try to refute every claim, and writes one cited report from the claims that survived. Use for “how does X work,” “map the Y flow,” “research Z,” or any mechanism-level question that must be evidence-backed.
AnyGen: AI-powered content creation suite. Create slides/PPT, documents, diagrams, websites, data visualizations, research reports, storybooks, financial analysis, and images. Supports: pitch decks, keynotes, technical docs, PRDs, white papers, architecture diagrams, flowcharts, mind maps, org charts, ER diagrams, sequence diagrams, UML, landing pages, CSV analysis, earnings research, posters, banners, comics, and more. Also trigger when: 做PPT, 写文档, 画流程图, 做网站, 分析数据, 帮我调研, 做绘本, 分析财报, 生成图片, 做海报, 思维导图, 做个架构图, 季度汇报, 竞品调研, 技术方案, 建个落地页, 做个估值, 画个故事.
Score and enrich a CSV of B2B leads using Apify Actors. Takes a CSV with company URLs, free-text scoring rules, and an enrichment preference; runs BuiltWith (tech stack), Website Content Crawler (content classification), and Contact Info Scraper (company metadata) for scoring; enriches with either department-specific contacts (Contact Info Scraper + Bulk Email Finder fallback) or copywriter discovery (Google Search Scraper → AI Web Scraper → Bulk Email Finder). Outputs an enriched CSV with a numeric score and a per-lead outreach_hook column that personalizes cold email copy (e.g. "uses Shopify → send Shopify install guide"). Use when user asks to score leads, qualify leads, enrich a lead list, detect a company's tech stack for outreach, find marketing/sales/engineering contacts at a list of companies, hunt down blog copywriters for guest-post pitches, personalize cold email at scale, or turn a raw domain list into a ready-to-pitch account list.
UIKit iOS/iPadOS UI framework. UIViewController, UINavigationController, UITabBarController, UISplitViewController, UIView, UILabel, UIButton, UITextField, UIScrollView, UIStackView, UITableView, UICollectionView, diffable data source, NSDiffableDataSourceSnapshot, UICollectionViewCompositionalLayout, Auto Layout, NSLayoutConstraint, NSLayoutAnchor, UILayoutGuide, intrinsicContentSize. UIArrangementViewController, UISplitArrangement, UIOverlayArrangement, UIView.ReservedRegion, UIHingeInteraction, vertical bar, iPhone Duo adaptive layout (iOS 27.1+), migration to the scene-based life cycle, UISceneAccessory. A separate API from SwiftUI ArrangementView.
Write, review, score, improve, or iterate on Statements of Purpose and PhD application essays for research programs. Use this skill whenever the user is applying to PhD programs, research internships, fellowships, or graduate programs and asks for SOP strategy, essay structure, research fit, faculty alignment, motivation framing, draft critique, or revision help. Every review and plan checks the statement against the programme's declared theme, specialisation, or track before faculty fit, searching the web for the live official programme page when the target is not already known. This skill is especially relevant for research-focused applications where the essay must connect prior work, future research direction, and program fit.
Use this skill to apply Android-team testing strategies — determinism, hermetic execution, Given-When-Then / Arrange-Act-Assert structure, naming conventions, and Hilt-based dependency replacement. Encodes which guidance actually lives on `/training/testing/fundamentals/strategies` (qualitative pyramid, network-access table) versus `/training/testing/instrumented-tests/stability` (determinism / flake) versus `/training/dependency-injection/hilt-testing` (`@HiltAndroidTest`, `HiltAndroidRule`, `@TestInstallIn`, `@UninstallModules`, `@BindValue`, rule ordering). Use when the user asks "how should I structure tests", "Given When Then or Arrange Act Assert", "how do I name test methods", "Hilt rule order", "@HiltAndroidTest", "@BindValue", "how to swap a binding for tests", "tests pass locally fail on CI", or "make tests deterministic".
Use on any page build, redesign, or 'make it look better' request on a site that has (or needs) a saved Art Direction. Loads the direction before the first element is written, plans tokens in two passes against the direction's donts and the known AI-default aesthetics, builds with tokens preserved, checks the result with respira_check_design, and mints a live preview. Also the import lane for Claude Design output and other design-system documents.
Render independent questions from an Agent workflow as a local interactive form, preselect recommended answers, collect an optional supplement for every question, save responses as portable JSON, and return submitted answers directly to the waiting Agent command. Use for grill-me, grill-with-docs, brainstorming, requirement clarification, configuration, planning, or any other workflow that needs user confirmation or question collection; explicitly invoke Ask UI when one round contains more than two questions. Also use the manual recovery path when the user says “已提交”, “提交好了”, or “答完了” after an active Ask UI round.
**WORKFLOW SKILL** - Safely migrates eligible Aspire 13.6+ AppHosts from legacy ProjectResource APIs to experimental DotnetProjectResource APIs after a per-resource assessment and explicit approval of exact edits. USE FOR: assess or migrate existing AddProject, addProject, AddCSharpApp, addCSharpApp, or AddBlazorGateway resources to Project v2; migrate ProjectResource to DotnetProjectResource; clean up the resulting obsolete AppHost ProjectReference edges. DO NOT USE FOR: upgrading Aspire versions, creating/wiring a new AppHost, Azure Functions migration, generic source modernization, ordinary C# resource wiring or adding a new AddProject resource (use aspireify), publishing, or build/lifecycle diagnostics. INVOKES: Aspire docs/API lookup, aspire add/restore/start/wait, AppHost and package edits. FOR SINGLE OPERATIONS: Assess first; never edit from a generic migration request alone
Play a local audio file through the system's default speakers using Sonilo's MCP server. Use after generating a track with Sonilo (or for any local WAV/MP3/M4A/AAC/OGG/FLAC file) when the user wants to hear it immediately instead of just getting the saved path.
Audit a database schema, ORM model, or migrations for design and performance — produces two independent 0-100 scores (Design & Integrity + Performance & Scale) plus a prioritized, evidence-backed report. Read-only; never writes or migrates. Use when the user asks to audit, analyze, review, check, or score a database, schema, data model, migrations, indexes, keys, referential integrity, types, constraints, query patterns, partitioning, or connection pooling — for Postgres, MySQL, Mongo, DynamoDB, Cassandra, pgvector, ClickHouse, Neo4j, and friends.
Audit source code for exploitable vulnerabilities using threat-model-driven review, taint tracing, invariant checking, and variant analysis. Use when reviewing a codebase or diff for security bugs, performing a security audit, hunting for vulnerabilities in a target's source, or validating whether a suspected finding is real.
Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.
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.