Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges
Choose the right y-axis unit when creating or updating an insight via `posthog:insight-create` or `posthog:insight-update`—for both TrendsQuery (`trendsFilter.aggregationAxisFormat`) and SQL insights (`DataVisualizationNode`, `chartSettings.yAxis[].settings.formatting`). Use when the agent is about to add a `formula` purely to convert units (e.g. dividing seconds by 60 to display minutes), when a `math_property` or SQL column is a duration, currency, ratio, or large count, or whenever the user mentions "format the y-axis", "duration", "seconds", "minutes", "hours", "milliseconds", "ms", "percentage", "%%", "currency", "decimals", "axis label", or "axis unit" in the context of a graph insight.
Execute git and GitHub operations with Conventional Commits and agent-safe defaults. Use raw git/gh directly. Use gw only for worktree lifecycle (create/finish). Use when making commits, managing branches, working with PRs/issues, or performing any version control operations.
Generate and A/B test Google Ads copy. Use when asked to write ad copy, headlines, descriptions, create ad variants, test ad messaging, improve CTR, or generate RSA (Responsive Search Ad) components. Trigger on “ad copy,” “write ads,” “headlines,” “descriptions,” “RSA,” “responsive search ad,” “ad text,” “ad creative,” “improve CTR,” “ad A/B test,” “ad variants,” “write me an ad,” “ad variation experiment,” or when the user wants to improve click-through rate on existing ads.
Designs GraphQL schemas with types, queries, mutations, subscriptions, resolvers, and DataLoader patterns for efficient data fetching. Use when users request “GraphQL API”, “schema design”, “GraphQL setup”, “resolvers”, or “Apollo Server”.
Design a process, idea, or body of knowledge into an ICM (Interpretable Context Methodology) workspace, where folder structure is the agent architecture, or restructure an existing folder, repo, or vault into one. Use for “make this an ICM”, “ICM this”, “build me a workspace”, “structure this for agents”, “map this repo”, “audit this folder”, “what would a change hit”, a second brain, team brain, or context map, or turning transcripts and research into material for lectures, scripts, or docs.
End-to-end iOS red-team pipeline — IPA acquisition (App Store extraction, TestFlight, enterprise/ad-hoc sideload), class-dump/Hopper/Ghidra static analysis, Info.plist + entitlements + Keychain secret extraction, App Transport Security (ATS) misconfig + certificate-pinning bypass (frida-ios-dump, objection, SSL Kill Switch 2), URL-scheme / Universal Link hijack, exported-service enumeration, Frida runtime instrumentation. Companion to apk-redteam-pipeline for the iOS side of a mobile app catalogue. Use when target has an iOS app (App Store listing, TestFlight link, enterprise MDM distribution), when an IPA URL is found hosted on a web server, or when post-recon mentions "iOS app" / "mobile app" in scope alongside an Apple developer account.
Audit Android Jetpack Compose repositories for performance, animation phase correctness, state management, side effects, composable API quality, and adjacent Android launch UX resource risks such as blurry Android 12+ splash icons. Scans source code, scores each category from 0-10, writes a strict markdown report, and summarizes the most important fixes. Use when reviewing a Compose codebase, rating repository quality, inspecting recomposition/state issues, animation issues, or running a Compose audit.
Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint (grover_base / cmim / hybrid / finetuned). Writes one .npy per readout type (atom_from_atom, bond_from_atom, atom_from_bond, bond_from_bond) plus canonical_smiles.npy and validity.npy. Calls task/extract_embeddings.py (which featurizes SMILES on the fly — no pre-computed features needed).
Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rdkit_2d features), then launches main.py predict inside the kermt container (blocking, minutes-scale).
A specialist guide to configuring dynamic deployment parameters (lzc-deploy-params.yml) for 懒猫微服 (Lazycat MicroServer) applications, rendering manifest files with Go templates, and injecting scripts into frontend pages using application.injects.
Seerfar Ozon product detail lookup: retrieves complete details for a single product by Ozon product SKU, including title, price (rubles), rating, review count, QA count, total and average daily sales within the statistical window, revenue, stock, category rank, daily sales trend, brand, seller, fulfillment method (FBO/FBS/OZON), weight, and listing time/days/months. Use for in-depth single-product analysis, competitor product breakdowns, Ozon product selection evaluation, Listing diagnostics, and tracking sales trends and category rankings. Triggers when the user mentions Ozon product details, Ozon single-product analysis, Ozon SKU lookup, competitor product data, Ozon sales trends, Ozon category ranking, Ozon inventory, Ozon listing time, Seerfar Ozon product search, Ozon product detail, Ozon SKU lookup, single product analysis, competitor product teardown, Ozon sales trend, or category rank. Trigger this skill even if the user does not explicitly mention “Seerfar” when they intend to view detailed data for an Ozon product.
Shopee Account Health (same series as linkfox-shopee-store-auth), forwarding all 6 endpoints in the Shopee Open API Account Health module through /shopee/developerProxy: get_shop_performance, get_metric_source_detail, get_penalty_point_history, get_punishment_history, get_listings_with_issues, and get_late_orders. Trigger when the user mentions Shopee account health, Account Health, store performance, penalty point records, punishment history, late orders, or listing issues. Trigger even without an explicit mention of “account health” if the request involves querying health metrics or penalty data for an authorized Shopee store.
Shopee Affiliate Marketing Solutions (AMS), in the same series as linkfox-shopee-store-auth. Forwards all 36 interfaces in the Shopee Open API AMS module through /shopee/developerProxy, including get_open_campaign_added_product, batch_add_products_to_open_campaign, create_new_targeted_campaign, get_affiliate_performance, and get_shop_performance. Triggered when users mention Shopee affiliate marketing, AMS, influencer sales, affiliate, Open Campaign, Targeted Campaign, commission rates, influencer promotion, or get_open_campaign_added_product. Also trigger for affiliate promotion or influencer campaign management for an authorized Shopee store, even if “affiliate” is not explicitly mentioned.
Shopee store returns and refunds (same series as linkfox-shopee-store-auth), forwarding all 15 endpoints in the Shopee Open API Returns module through /shopee/developerProxy, including get_return_list, get_return_detail, confirm, dispute, offer, accept_offer, upload_proof, and get_reverse_tracking_info. Trigger when the user mentions Shopee returns, refunds, return_sn, return lists, confirming a return, return disputes, dispute, or reverse logistics. Trigger even without an explicit mention of “returns” if the request involves querying or processing returns/refunds for an authorized Shopee store.
Shopee store flash sales (Shop Flash Sale), in the same series as linkfox-shopee-store-auth. Forwards all 11 interfaces in the Shopee Open API Shop Flash Sale module through /shopee/developerProxy, including get_time_slot_id, create_shop_flash_sale, get_shop_flash_sale_list, add_shop_flash_sale_items, and update_shop_flash_sale. Triggered when users mention Shopee store flash sales, Shop Flash Sale, limited-time flash sales, get_time_slot_id, flash_sale_id, or flash sale time slots. Also trigger for Flash Sale campaign management for an authorized Shopee store, even if “flash sale” is not explicitly mentioned.
Queries patent citation data from PatSnap, including citation counts and details of citing patents. Triggered when users mention patent citations, citation analysis, patent influence, citation frequency, citations of a patent family, forward citations, or ask which patents cite a given patent; also for patent citations, citation count, patent influence, citation analysis, or PatSnap. Use even if “PatSnap” is not explicitly mentioned, as long as the user wants to find how often a patent is cited or which patents cite it.
Queries forward citation details for patents from the PatSnap patent database. Use when users ask about patent citations, cited patents, cited literature, patent references, forward citations, prior-art citations, or which patents and non-patent literature a specific patent cited during its application; also trigger for patent cited references, forward citations, patent references, citation analysis, or PatSnap. Apply to any request for references cited by a patent when the user provides a patent ID or publication number, even if they do not explicitly say “forward citations.”
Post a comment (or a formal PR review) to a GitHub issue or pull request in mariadb-operator/mariadb-operator. Use whenever the user wants to publish something to GitHub for this repo — "comment on issue #123", "post this as a PR comment", "leave a note on #456", "reply on the PR" — and especially when they want the output of the mariadb-operator-pr-review skill delivered to GitHub instead of just shown in chat, e.g. "review PR #1234 and post it as a comment" or "post the review results to the PR". Always confirms the exact comment text with the user before publishing — never posts autonomously.
Processes meeting notes or transcripts to extract structured information. Use after meetings to quickly generate action items, capture decisions, and create follow-up tasks. Extracts: action items with owners, decisions made, key discussion points, follow-up tasks with priorities.
Manage AI agent memory with a P0/P1/P2 priority system and automatic archiving. Use when setting up memory management, cleaning up MEMORY.md, creating lessons files, configuring automatic archive cron jobs, or reviewing memory structure. Reduces token usage by 70–80% while maintaining recall through semantic search.
Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation
Search Google News, Google Shopping, Google Images, and Google Lens using Serper APIs via x402. USE FOR: - Finding recent news articles on a topic - Current events and breaking news - Product searches and price comparisons - Shopping research and product discovery - Industry news monitoring - Image search and finding photos/headshots of people - Reverse image search (Google Lens) TRIGGERS: - "news about", "latest news", "recent articles" - "current events", "breaking", "headlines" - "shopping", "buy", "price", "product search" - "compare prices", "where to buy", "deals on" - "image of", "photo of", "headshot", "reverse image search" Use `npx agentcash@latest fetch` for Serper endpoints. Most endpoints are $0.04 per call; Lens is $0.20.
Production-grade web scraping with automatic anti-bot bypass, structured JSON parsing for 40+ targets, and geo-targeting. Use when the user needs to scrape web pages, extract product data, get search results, or collect structured data from supported e-commerce and search platforms without worrying about getting blocked and when geo targeting is required.
Investor pitch deck structure with a slide-by-slide framework, visual design rules, and data presentation. Covers the 12-slide framework, chart types, team slides, and common investor turn-offs. Use for: fundraising decks, investor presentations, startup pitches, demo days, grant proposals. Triggers: pitch deck, investor deck, startup pitch, fundraising deck, demo day, pitch presentation, investor presentation, seed deck, series a deck, pitch slides, startup presentation, vc pitch, investor meeting
Implement the fix for a GitHub issue from its RCA artifact (created by piv-investigate-issue) — drift-check the plan, branch, implement, add regression tests, and validate. Use after the investigation artifact exists and you're ready to fix the issue.
Use when working in a Quarkus project and the user wants to check if their build files are up-to-date, compare project structure against a reference, or upgrade their Quarkus version. Triggers on "check project", "update quarkus", "is my project up to date", "compare build", "quarkus upgrade".
Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI. Models: Qwen-Image-2.0 (fast), Qwen-Image-2.0-Pro (professional text rendering). Capabilities: text-to-image, multi-image editing, complex text rendering. Triggers: qwen image, qwen-image, alibaba image, dashscope image, qwen image 2, qwen image pro
Unified entry point for qwskill. Use when the user says /qws, qws, or “invoke QWS”; wants an AI interview or to clarify experiences, ideas, or judgments through successive questions; explicitly asks to take a higher-level or global view, check whether a solution addresses only part of the problem; or remains dissatisfied after repeatedly revising the same issue and asks to step back.
Build 3D applications with React Three Fiber (R3F), the React renderer for Three.js. Use this skill when building 3D scenes with React, using declarative JSX for 3D objects, integrating Three.js with React state/lifecycle, or using Drei helpers. Covers Canvas setup, hooks, Drei utilities, performance patterns, and state management for 3D React apps.
Use for Roblox multiplayer communication across the client-server boundary: designing RemoteEvent, UnreliableRemoteEvent, and RemoteFunction flows; validating client requests; handling replication-aware gameplay; applying rate limits and anti-exploit checks; reasoning about network ownership, server-authority patterns, Input Action System use in authoritative gameplay, and streaming-sensitive multiplayer correctness
RollingGo hotel search and booking assistant, providing the full hotel search and order process by calling the RollingGo hotel service API. Supported scenarios: ① Search hotels by city, attraction, subway station, airport, and other locations ② Filter by star rating, budget, and tags (pool, breakfast included, family-friendly, pet-friendly, etc.) ③ Check real-time room types and prices for a specified hotel ④ Compare multiple hotels ⑤ Guide users through booking ⑥ Cancel orders (check cancellation fees before cancellation and confirm cancellation). Triggers: find a hotel, book a hotel, search hotels, hotel recommendations, hotel lookup, nearby hotels, five-star hotel, homestay, resort, check room rates, view room types, check in, where to stay, lodging, rollinggo, travel accommodation, business travel accommodation, family-friendly hotel, hotel with a pool, hotel with breakfast, cancel order, cancel hotel booking, refund after checkout, cancel reservation.
Scans a Docker image with Trivy for vulnerabilities in OS packages and language dependencies, misconfiguration, exposed secrets, and licence violations, emitting SARIF, CycloneDX, or SPDX output. Use when scanning or gating a specific image, wiring an image scan into CI/CD, or checking an image during an incident investigation. Keywords: Trivy, image scan, --severity, --exit-code, SARIF, ignore file, .trivyignore. Do not use for cluster-wide scanning or non-image targets - use performing-container-security-scanning-with-trivy; when the toolchain is Grype use scanning-container-images-with-grype.
Generate videos with ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized audio, up to 1080p, 4-15s duration. Pro and Fast variants. Studio variants with private asset library for portrait consistency. Use for: social media videos, music videos, product demos, animated content, AI video with sound. Triggers: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio, seedance 2.0, bytedance seedance, seedance studio
SEO content brief creation with keyword research, search intent analysis, and content structure. Covers SERP analysis, heading hierarchy, word count targets, and internal linking strategy. Use for: content briefs, SEO writing, blog strategy, content planning, keyword targeting. Triggers: seo content brief, content brief, seo brief, keyword research, search intent, content strategy, blog brief, seo writing, content planning, keyword targeting, serp analysis, content outline, seo article, blog seo
Audit and generate hreflang annotations for multilingual sites — check reciprocity, BCP-47 validity, self-reference, x-default, hreflang/canonical conflicts, and <html lang> agreement, and emit reciprocal hreflang link sets. Module M20 (conditional). Feeds the Search SEO score.
Set up a Stylus smart contract project with OpenZeppelin Contracts for Stylus on Arbitrum. Use when users need to: (1) install Rust toolchain and WASM target for Stylus, (2) create a new Cargo Stylus project, (3) add OpenZeppelin Stylus dependencies to Cargo.toml, or (4) understand Stylus import conventions and storage patterns for OpenZeppelin.
Use when building browser-based presentation slide decks, creating training presentations, generating React+Vite slide decks with animations, or making professional slides. Triggers on slide deck, presentation, training slides, Vite slides, Framer Motion slides, animated presentations.
Writing a Succession-style ensemble series (继承之战群像剧写法) — distilled from Jesse Armstrong's complete shooting scripts for all four seasons, 39 episodes (Faber 2023), with his introductions and footnotes, plus Frank Rich's and Lucy Prebble's essays on the writers' room. Covers the invisible-act three-test for scripts with no ACT marks, container episodes built on a ceremony's running order, pressure chambers, one core question per episode, finales with fewer and longer scenes, the absent protagonist at the climax, humiliation passed downward, stage directions carrying subtext and "maybe", reversals turned on one word, writing long, alts, the mega-chart, and engineering an ending once the plot engine loses pressure. Use when the user wants a dynastic family drama, a media-power ensemble, a wedding/funeral/summit set piece, a streaming hour with no act breaks, a finale that redraws alliances, or asks how to "Succession-ize" a script or kill a lead mid-season.
Implements Syncfusion® .NET MAUI Cartesian Chart (SfCartesianChart) for data visualization with 20+ chart types including line, area, column, bar, financial, statistical, and stacked charts. Use when implementing cartesian charts, line charts, area charts, or financial charts (candle, OHLC). Covers chart axes, legends, tooltips, trackball, zooming and panning, chart annotations, and trendlines.
Manage Tencent Cloud COS (Cloud Object Storage) buckets and objects. Use whenever the user asks about COS / 对象存储 / Tencent Cloud bucket operations: list buckets, list objects, upload, download, delete, pre-signed URLs, calculate bucket size (du), batch delete with prefix, copy objects between keys. Backed by the official cos-python-sdk-v5.
Creates reusable Terraform modules with proper structure, variables, outputs, and state management for infrastructure as code. Use when users request “Terraform setup,” “infrastructure as code,” “IaC module,” “cloud provisioning,” or “Terraform module.”
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.