Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
A reference library of 45+ visual ad formats for Meta and paid social, each with a definition, funnel stage guidance, and medium (video/static/both). Use this whenever choosing how an ad should look and feel, building out a creative concept, writing a creative brief, or deciding which format best serves a messaging angle and awareness stage. Trigger when the user asks “what format should this be,” “how should we execute this,” “give me concept ideas,” or any time a creative concept needs a production structure. Always pair with creative-mechanics to fully flesh out the concept — format defines the vessel, mechanic defines the cognitive move inside it. Either can come first; they work in both directions.
Zephyr RTOS skill for embedded development. Use when building Zephyr applications with west, configuring boards and targets, working with Kconfig and devicetree, using the Zephyr shell and logging subsystem, or running on the native_sim target. Activates on queries about Zephyr, west build, Kconfig, devicetree, Zephyr logging, west flash, board targets, or native POSIX simulation.
Build React chat interfaces with Vercel AI SDK v6. Covers useChat/useCompletion/useObject hooks, message parts structure, tool approval workflows, and 18 UI error solutions. Prevents documented issues with React Strict Mode, concurrent requests, stale closures, and tool approval edge cases. Use when: implementing AI chat UIs, migrating v5→v6, troubleshooting "useChat failed to parse stream", "stale body values", "React maximum update depth", "Cannot read properties of undefined (reading 'state')", or tool approval workflow errors.
Anonymize and sanitize customer-provided log files. Performs a line-by-line review and replaces all sensitive values inline, preserving log structure and format exactly — never reformats, re-indents, or restructures content. Use when sanitizing customer logs, sample events, or test fixtures. Invoke manually with /anonymize-logs.
Forces a business to pick ONE of the three self-consistent pricing strategies — More for More (the best, priced to match), More for Less (what you need at a reasonable price), or Less for Less (minimal but incredibly affordable) — then align the whole company behind it. Three gated phases: (1) collect the current reality — what you charge, what your marketing promises, which segments you serve; (2) map that onto the three strategies, surface where you're mixing them, and interrogate the trade-offs until you commit to one with its consequences accepted; (3) audit every signal (pricing page, homepage, support, roadmap) into a keep / stop / start plan ordered by how much each contradicts the story. Load when the user asks which pricing strategy fits them, whether to go premium / value / budget, why their pricing feels confused or mixed, or how to align product-price-marketing. Do NOT load to set the actual price number, write a price-increase announcement, define the ideal customer, or rewrite marketing copy.
Helps a founder build the case for raising prices and the moves that justify it; it drives toward a higher price and does not debate whether to raise. Three gated phases: (1) collect the reality (what you charge, what you promise, who buys) and diagnose which market the price has selected (the $1/$10/$100/$1,000-per-month ladder), the profit stakes (a 10% rise can be ~100% more profit), and whether the low price is strategy or fear, landing on a rough higher target; (2) brainstorm, judgment off, moves that justify a higher price — move up a market rung, price on value created not cost saved, build Love and Utility drivers, differentiate, repackage; (3) select, grilling each move down to a few that are good, strategy-consistent, buildable, and wanted. Load when the user asks how much to raise prices, what it would take to charge more, or why their price feels too low. Do NOT load to set the exact price, write the increase letter, define the ideal customer, or choose among the three pricing strategies.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Build creator lead lists for TikTok, Instagram, and X by turning normalized platform datasets into outreach-ready leads with contact signals, shortlist logic, and draft outreach messages. Use this when the user wants creator discovery, contact extraction, shortlist building, or outreach prep.
Diagnoses and fixes issues in Atlassian Forge apps. Use this skill whenever a Forge app has errors, crashes, shows blank UI, fails to deploy, doesn't appear after installation, has permission issues, or produces unexpected output. Trigger on any mention of forge logs, forge deploy errors, resolver errors, blank panels, missing scopes, Custom UI not rendering, production vs dev discrepancies, or any Jira/Confluence app that "stopped working". Also trigger when the user asks to debug, troubleshoot, investigate, or fix a Forge app issue — even if they haven't used the word "Forge" but describe a Jira panel or Confluence macro acting up.
Your CFO. Builds the unit economics of a business before money is spent: what one unit earns after its direct costs, the real profit margin at the planned volume, the break-even point in units a day, year 1 month by month, the cash needed before it pays for itself, how long the startup spend takes to earn back, and what happens if the price drops, sales come in low or costs rise. Every number traces to an input the user can check. Use when the user says "find the profit margins", "do the numbers", "is this profitable", "break-even", "unit economics", "how much do I need to start", or "run the CFO".
The consumer panel. Spins up a swarm of buyer sub-agents (default 100, --quick for 20) trained on the user's target customer, each with a different income, age, buying behaviour and objection, shows every one the same pitch, and runs the business through 100 buyer scenarios to see who buys, who doesn't, and why. Tallies the answers into buy rates by segment, the reasons people pass in their own words, what would flip a no, and price answers for founder-pricing. Use when the user says "would people buy this", "test it on customers", "run the consumer panel", "simulate buyers", "who is my customer", or "validate demand".
Finds the price buyers will actually pay. Reads the consumer panel's four price answers per buyer into a Van Westendorp price-sensitivity range (too cheap, a bargain, getting expensive, too expensive), sets it against what competitors really charge and against the CFO's margin, and recommends a price, a price ladder (good / better / best) and an opening offer to test. Use when the user says "how much should I charge", "price this", "is $X too expensive", "pricing strategy", "what price", or after the consumer panel.
Token-reduction skill for coding agents. Compresses JSON tool output, build logs, grep/ripgrep search results, source code, and conversation history the same way the Headroom proxy does — but in-context, with no binary install. Use this skill whenever an agent is about to paste a large tool result (a 1000-row JSON array, a 5000-line pytest log, a 200-result grep, a 1000-line source file) into its next message, or when the agent's conversation is approaching the context limit, or when the user complains about token cost or latency. Also use it to shape the agent's own output: skip ceremony, don't restate code already on screen, drop reasoning on routine turns. Triggers: "compress this output", "this is too long", "trim", "summarize the log", "reduce tokens", "context is full", "running out of context", "too many tokens", "make it shorter", "be terse"
Corporate event-driven analysis via Longbridge Securities — captures and classifies events that create pricing dislocations: major-shareholder increases/decreases, equity incentives, private placements, rights issues, buybacks, M&A/restructuring, index rebalancing, and management changes. Combines filings, corporate actions, and shareholder data to produce event signals. Triggers: "corporate event", "event-driven", "share buyback", "equity incentive", "major shareholder increase", "rights issue", "M&A arbitrage", "index rebalancing", "insider buying", "corporate action analysis".
Elliott wave theory signal engine — detects swing points via Zigzag, matches the 5-wave impulse (1-2-3-4-5) and 3-wave corrective (A-B-C) structures, validates with Fibonacci relationships, and generates wave positions, target price levels, and risk levels. Triggers: "艾略特波浪"、"波浪理论"、"推动浪"、"调整浪"、"斐波那契"、"1浪"、"3浪"、"5浪"、"abc浪"、"艾略特"、"波浪計數"、"推動浪"、"調整浪"、"斐波那契"、"Elliott wave"、"wave theory"、"impulse wave"、"corrective wave"、"fibonacci retracement"、"wave count"、"wave 3"、"wave 5".
Drive RevenueCat from the terminal with the `rc` CLI, an alternative to the RevenueCat MCP server for humans, CI, and agents. Covers install, authentication, command discovery, and output conventions. Use for uploading paywall images to the Media Gallery (`rc media-assets upload`) or custom paywall fonts (`rc fonts upload`) — MCP has no upload tools for these. Referenced by the other RevenueCat skills whenever they offer a CLI path.
Use when creating or revising finished video thumbnails or cover images with Scenario: game trailers, boss reveals, patch updates, devlogs, or community videos needing readable composition, exact headline text and consistent characters. Not for title ideas or critique alone, in-video title cards, or a generic image without a thumbnail deliverable
Create and manage APM service remapping rules — rewrite service names at ingestion time to collapse noisy inferred entities, clean up auto-generated names, handle org renames, or normalize naming conventions. Use for any request involving service renaming, service mapping, inferred service cleanup, peer.service normalization, or collapsing fragmented service names.
Upgrade React Navigation to a new major version (6.x to 7.x or 7.x to 8.x), applying the required breaking changes — peer-dependency and tooling bumps, and renamed or removed navigate, linking, theme, navigator, and screen-option APIs — while preserving navigation behavior.
Generates professional infographics with 20 layout types and 17 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", or "可视化".
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Help Chinese Gaokao students make application choices through an Agent conversation: start with scientifically grounded personality and career-interest assessments, research suitable careers, majors, and industries, then combine province, subject choices, score/rank, and official admissions data to generate an HTML report with traceable sources. Use when users mention Gaokao applications, college application, choosing a university or major, personality tests, career direction, industry prospects, admission cutoffs, admission probability, reach/match/safety choices, or application simulations.
Use when creating a new Elastic integration package, scaffolding data streams, answering package layout or structure questions, or running the end-to-end integration build workflow. Covers package topology, scaffold commands, post-scaffold edits, and full orchestration of CEL/pipeline/test subagents.
Formula 1 data — race schedules, results, lap timing, driver and team info. Powered by the FastF1 library. Covers F1 sessions, qualifying, practice, race results, sector times, tire strategy. Use when: user asks about F1 race results, qualifying, lap times, driver stats, team info, the F1 calendar, or Formula 1 data. Don't use when: user asks about other motorsports (MotoGP, NASCAR, IndyCar, WEC, Formula E). Don't use for F1 betting odds or predictions — use kalshi or polymarket instead. Don't use for F1 news articles — use sports-news instead.
Expert blueprint for hierarchical finite state machines (HSM) and pushdown automata for complex AI/character behaviors. Covers state stacks, sub-states, transition validation, and state context passing. Use when basic FSMs are insufficient OR implementing layered AI. Keywords state machine, HSM, hierarchical, pushdown automata, state stack, FSM, AI behavior.
Govern how the design system evolves (SemVer for tokens/components, the contribution workflow, deprecation policy, and change communication). Use when the user wants to add/promote/deprecate a component or token, decide a version bump, set up a contribution process, or keep the system from fragmenting
Interactive learning system for NetSuite SDF development. Features six modes (learn, review, explain, annotate, quiz, and final) with SAFE Guide integration. Produces compliance-reviewed learning documentation. Learn topics like governance, N/cache, and security directly from SAFE Guide principles. Generate quizzes from code or SAFE Guide content.
Transform a PRD into a technical SPEC document covering architecture, API design, data model, error handling, and implementation contracts. Triggers on: prd-to-spec, prd to spec, prd转spec, 需求转设计, 需求转规格, generate spec from prd, design from prd, 技术方案, 设计方案
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.