Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
When the user wants to perform a deep dive into a company's financial performance. Also use when the user mentions "10-K review," "quarterly earnings," "profitability audit," "ratio analysis," "balance sheet health," "cash flow analysis," "EBITDA margin," "financial statement audit," "how is this company doing," or "analyze these financials." Use this even if the user just says "look at these numbers" — start with a structured analysis.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Scrape web pages to clean markdown using Firecrawl v2 — handles JS-heavy pages, site crawls, URL mapping, document parsing (PDF/DOCX/XLSX), LLM-powered extraction, autonomous agent scraping, and post-scrape browser interaction (Interact API). Free keyless mode available for search/scrape/parse/interact (no API key needed). Prefer over WebFetch for quality and completeness. Triggers on scrape URL, fetch page, crawl site, extract content, parse document, web to markdown, DeepWiki, Firecrawl.
Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity sparklines, and a top-contributors panel, all in a single self-contained HTML file with light/dark theming, hoverable chart tooltips, click-to-zoom panels, and CSV export. Use when the brief asks for a team / workspace admin dashboard, an interactive admin dashboard with charts, or names FlowAI.
Design, structure, or improve form interfaces for clarity, completion rates, and user confidence. Use when the user asks to build a form, redesign a form flow, improve form conversion, add multi-step forms, fix form UX, or structure field layouts and validation.
Use when creating, choosing, changing, or integrating game art, animation, or audio. Research comparable assets, establish a consistent direction, use suitable production tools, and inspect the result at gameplay scale and in motion. Applies to sprites, textures, models, effects, music, sound, and voice.
Uploads a local file (screenshot, image, PDF, zip, video) to GitHub user-attachments, downloads GitHub user-attachments, and embeds local files in a PR, issue, or comment. Use when asked to "attach a screenshot to the PR", "add an image to the issue", "embed before/after screenshots", "attach this file", or "download this GitHub attachment". Powered by `gh-attach`.
Use when GitHub Actions PR checks are failing on a pull request and need to be diagnosed or fixed. Inspects checks / logs via `gh`, drafts a fix plan, and implements only after explicit approval. Trigger on red checks, failing workflow runs, `pr is failing CI` reports — even if the user does not name a specific check. Out of scope: external CI (e.g. Buildkite) — report only the details URL.
Automate GitHub repository setup with CI/CD workflows, issue templates, Dependabot, and CodeQL security scanning. Includes 12 production-tested workflows and prevents 18 errors: YAML syntax, action pinning, and configuration. Use when: setting up GitHub Actions CI/CD, creating issue/PR templates, enabling Dependabot or CodeQL scanning, deploying to Cloudflare Workers, implementing matrix testing, or troubleshooting YAML indentation, action version pinning, secrets syntax, runner versions, or CodeQL configuration. Keywords: github actions, github workflow, ci/cd, issue templates, pull request templates, dependabot, codeql, security scanning, yaml syntax, github automation, repository setup, workflow templates, github actions matrix, secrets management, branch protection, codeowners, github projects, continuous integration, continuous deployment, workflow syntax error, action version pinning, runner version, github context, yaml indentation error
Official skill for generating high-quality images from text prompts using ZhiPu GLM-Image API. Excellent at scientific illustrations, high-quality portraits, social media graphics, and commercial posters. Supports multiple aspect ratios, HD quality, and watermark control. Use this skill when the user wants to generate images, create AI art, text-to-image, or convert text descriptions into visual content.
Use when an incompatible interface needs to look like an expected one — phrases like "Adapter pattern", "the third-party library's API doesn't match what I need", "wrap this legacy class to look like the new interface", "interface mismatch", "translate between two APIs". Defines Adapter as wrapping one interface to satisfy another, so client code can use otherwise incompatible classes through a uniform interface
Use when an abstraction and its implementation must vary independently—phrases like “Bridge pattern”, “I have N shapes times M renderers and don't want N*M subclasses”, “decouple the abstraction from its implementation”, “two orthogonal dimensions of variation”. Defines Bridge as separating an abstraction from its implementation so the two can vary independently—a cousin of Adapter, but designed up front rather than retrofitted.
Use when constructing an object requires many parameters or optional configuration steps — phrases like “Builder pattern”, “telescoping constructors”, “I have a constructor with 12 parameters half of which are optional”, “fluent API for construction”, “step-by-step object construction”, “type-safe builder”, “DSL builder”. Defines Builder as separating construction of a complex object from its representation, letting the same construction process create different representations.
Use when encapsulating a request as an object — phrases like "Command pattern", "undo/redo", "queue this operation", "remote control with arbitrary buttons", "macro of operations", "the invoker shouldn't know what the operation does". Defines Command as wrapping a request (target + action + arguments) into an object that can be parameterized, queued, logged, or undone.
Use when treating individual objects and groups of objects uniformly — phrases like "Composite pattern", "tree structure", "menus and submenus both behave like menu items", "I want to call `display()` on either a leaf or a branch and have it work", "part-whole hierarchy". Defines Composite as composing objects into tree structures so clients can treat individual leaves and composite branches uniformly through a shared interface.
Use when adding behavior to an object dynamically without subclassing — phrases like "Decorator pattern", "wrap this with extra behavior", "the Java I/O Streams pattern", "compose responsibilities at runtime", "I need 16 variants of Beverage and don't want 16 subclasses", "add features without modifying the underlying class". Defines Decorator as wrapping an object in another object that adds responsibility while preserving the original's interface
Use when simplifying access to a complex subsystem — phrases like "Facade pattern", "home theater example", "make this subsystem easier to use", "hide the complexity behind one method", "high-level interface to many classes". Defines Facade as a single entry-point class that orchestrates a set of subsystem classes behind a simpler interface, without preventing direct subsystem access.
Use when object creation is non-trivial enough to deserve its own abstraction — phrases like "Factory pattern", "Factory Method", "Abstract Factory", "Simple Factory", "I keep `new`-ing different concrete types", "creation logic is leaking into client code", "the constructor takes too much and is doing too much". Covers Simple Factory, Factory Method, and Abstract Factory together, with picking criteria for choosing between them
Use when the user has a design problem and is asking which GoF pattern, if any, fits — phrases like "which design pattern should I use", "is this an Observer or a Mediator", "what pattern handles this", "I'm not sure if it's Strategy or State", "help me pick a pattern for this scenario". Diagnostic mode that walks the problem statement to a candidate pattern (or rules patterns out) and hands off to the relevant pattern skill.
Use when traversing a collection without exposing its internals — phrases like “Iterator pattern”, “the menus use different internal structures but the diner shouldn't care”, “encapsulate iteration”, “hide whether it's an array, list, or hash map”. Defines Iterator as providing a uniform way to access elements of a collection sequentially without revealing the collection's underlying representation.
Use when a change in one object's state must notify many dependent objects — phrases like "Observer pattern", "publish-subscribe", "listeners", "the weather station needs to notify multiple displays", "broadcast a change", "one-to-many notification". Defines Observer as a subject maintaining a list of observers and notifying them on state changes, without the subject knowing observer concrete types.
Use when controlling access to an object — phrases like “Proxy pattern”, “lazy initialization”, “remote proxy”, “virtual proxy”, “protection proxy”, “the client should not know they're talking to a stand-in”, “wrap an expensive object with a placeholder”. Defines Proxy as a stand-in for another object that controls access to it (creation timing, location, permission).
Use when reviewing code that claims to use GoF patterns — phrases like "is this Observer used correctly", "review this for design pattern smells", "this is named *Strategy but doesn't look right", "audit this Singleton". Walks the target code through the catalog of pattern misuses with severity-tagged findings and citations to the relevant pattern skill.
Use when an object's behavior must change based on its internal state — phrases like “State pattern”, “the gumball machine behaves differently in each state”, “state machine”, “huge switch over a status enum”, “the same action does different things depending on the current state”. Defines State as encapsulating each state of an object in its own class and letting the context object delegate behavior to whichever state it currently holds.
Use when an algorithm has a fixed skeleton with variable steps — phrases like “Template Method pattern”, “the steps are the same but one varies”, “Coffee and Tea both brew via boil-brew-pour-add-condiments but differ in two steps”, “hook method”, “the Hollywood principle don't call us we'll call you”. Defines Template Method as a base class that defines an algorithm's skeleton in a final method, deferring some steps to subclasses.
Use when adding new operations over an existing object hierarchy without modifying it — phrases like "Visitor pattern", "double dispatch", "I want to add operations to this AST/tree without changing the node classes", "separate algorithm from data structure". Defines Visitor as representing an operation to be performed on the elements of an object structure — letting you define a new operation without changing the classes of the elements on which it operates.
Set up and operate the Gmail/Calendar/Contacts connector and the open-loop engine: who is waiting on the user, what they promised, and the context needed to respond. Covers painless BYO OAuth setup (exactly two user interactions), the daily `gbrain waiting` digest, loop closing/muting, and troubleshooting via the typed error catalog.
Generate, debug, and repair Kotlin + Spring Gradle builds with minimal, compatible changes. Use when `build.gradle.kts` or `settings.gradle.kts` is failing, plugins or toolchains are incompatible, dependency management is drifting from the Spring Boot BOM, test or runtime classpaths are broken, or a Kotlin DSL patch must be safe and incremental.
Relentless Socratic interview that walks down every branch of a plan or design, resolving decisions one-by-one. Trigger ONLY when the user explicitly says "grill me" or the PT equivalent "me grille". Do NOT trigger for stress-test, poke holes, devil's advocate, challenge, review, or feedback requests.
Helius Solana RPC and API expert. High-performance infrastructure for Solana including RPC nodes, DAS API for NFTs/tokens, LaserStream real-time streaming, webhooks, Priority Fee API, Enhanced Transactions, and ZK Compression. Triggers on Helius, Solana RPC, DAS API, Digital Asset Standard, NFT metadata, Solana webhooks, priority fees, LaserStream, ZK compression.
De novo and known TF motif enrichment in ChIP-seq/ATAC-seq peaks via HOMER. findMotifsGenome.pl finds over-represented patterns vs background; annotatePeaks.pl assigns context (TSS distance, gene, repeat). Use after MACS3 to identify enriched TFs, annotate peaks with nearest genes, and validate ChIP-seq via the target motif.
Design HTTP APIs for Bun + Hono backends using Clean Architecture, Zod contracts in a shared package, OpenAPI generation from Zod, and thin controllers. Supports two selectable conventions — standard REST (resource paths with GET/POST/PATCH/PUT/DELETE) and POST-only action-based paths — picking one per project. Use when defining new endpoints, auditing or refactoring existing routes, shaping request/response contracts and envelopes, establishing API standards, or mapping typed application errors to HTTP status codes. Do not use for GraphQL, tRPC, non-Hono runtimes, or frontend-only concerns.
Hunt for data exfiltration by analyzing Zeek and Suricata network telemetry for unusual data flows, DNS tunneling via large/frequent TXT queries, uploads to personal cloud storage, and encrypted-channel abuse, correlated against threat intel on destination domains. Use when hunting for data theft in a compromised environment, investigating unusual outbound data volumes, or determining what data was stolen during incident response.
LLM-driven hypothesis generation/testing on tabular data. Three methods: HypoGeniC (data-driven), HypoRefine (literature+data), Union. Iterative refinement, Redis caching, multi-hypothesis inference. Manual: hypothesis-generation; ideation: scientific-brainstorming.
Conversational intake for cold email campaigns. Interviews the user about their business, ICP (Ideal Customer Profile), offer, lead magnets, and hard vs soft filters. Outputs a structured `client-profile.yaml` that every other skill in the repo reads from. Use at the very start of a new campaign or when onboarding a new business. Triggers on "onboard me", "set up my ICP", "new client", "new business intake", "help me define my ICP".
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.