Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
When the user wants to optimize YouTube end screens, design CTAs, improve subscriber conversion, or create a next-video strategy. Also use when the user says 'end screen,' 'CTA strategy,' 'how to get more subscribers,' 'end of video CTA,' 'what should my CTA be,' 'next video strategy,' 'playlist funneling,' 'end card,' 'subscriber conversion.' For description CTAs, see description-seo. For script-level CTAs, see script-structure.
Backlog triage protocol for Engram: audit open issues and PRs, classify each item, infer maintainer ideology from comments, and produce an actionable disposition report. Trigger: Auditing open issues or PRs, triaging the backlog, reviewing contributor submissions as a maintainer, or applying triage to any GitHub repo.
Plan, implement, review, and validate general ets_runtime changes with a planner/worker/reviewer workflow. Use when working under arkcompiler/ets_runtime, or when handling ets_runtime feature work, bug fixes, refactors, test additions, and compile-validation tasks.
World-class trade execution - minimize market impact, optimize order routing, reduce slippage. The difference between backtest and live is usually execution. Use when "execution, slippage, market impact, order routing, TWAP, VWAP, iceberg, fill rate, best execution" mentioned.
Identify and exploit insecure deserialization across Java, .NET, PHP, Python, and Ruby — recognizing serialized formats by magic bytes, finding gadget chains with ysoserial and ysoserial.net, and detecting blind cases via DNS or timing. Use when a request contains base64 starting with rO0AB or AAEAAAD, when a cookie or parameter holds a serialized object, or when reviewing readObject, unserialize, pickle.loads, or Marshal.load.
Find and exploit server-side request forgery — reaching cloud instance metadata on AWS IMDSv1/IMDSv2, Azure IMDS, and GCP, internal service discovery, filter and allowlist bypasses via DNS rebinding, redirects, and encoding, and blind SSRF confirmation out of band. Use when an application fetches a URL supplied by the user, when testing webhooks, importers, PDF or screenshot renderers, or when reviewing outbound HTTP calls in source.
Integrate or repair RevenueCat and Superwall together in an Expo React Native app. Use for their shared purchase ownership, Android offer selection, billing identity, entitlement sync, restore, or migration flows; not for web billing or unrelated paywall providers.
Used to extract and generate domain-specific terminology, industry terms, internal and product terms, repository implementation maps, technical stack, and Mermaid architecture diagrams for onboarding from a specified repository, multiple repositories, or a GitHub organization. Triggered when the user requests "create a glossary", "create a domain dictionary", "make onboarding material", "review a repo/org and compile terminology", or "create a knowledge base that the AI doesn't need to re-check".
Create or update AGENTS.md after code generation or an overall task is complete. Use this skill when you have finished writing code (adding components, changing logic, refactoring files), or when the user mentions "update docs", "update AGENTS", or "create AGENTS". Even if the user does not explicitly mention AGENTS.md, whenever you have just modified a code file you should check whether the documentation needs to be updated to match.
Sync Feishu (Lark) contacts into USER.md so the agent can identify DM senders by name. Use when setting up Feishu identity recognition, updating contacts after HR changes, or configuring multi-user agent access. Feishu DMs only include open_id (no sender name), so this skill embeds an open_id→name lookup table directly in USER.md for zero-tool-call identification.
Analyze financial data from uploaded Excel/PDF files and generate interactive reports with sparkline trend charts. Supports output to PDF, DOCX, Markdown, and HTML. Use when: (1) User uploads Excel/CSV/PDF with financial data, (2) User asks for financial analysis or company report, (3) User wants visual reports from financial statements, (4) User mentions stock ticker + financial analysis, (5) User shares a Feishu sheet/doc link with financial data.
Source b-roll for a video edit — classify each moment, scope the search, return vetted candidates, place on the word. Use when the user says "find b-roll", "/find-broll", "source clips for this edit", or wants footage/memes/screenshots to lay over a talking-head video.
Draft 2–3 firegoat evals (firegoat.yaml) for the current repo: tests that a coding agent runs locally with `npx -y firegoat@latest eval`, each with a prompt, an end_goal, and script checks. Use when the user says "write firegoat evals", "draft evals", "set up firegoat", "firegoat init", or asks for local agent-experience (AX) evals of their SDK, CLI, API, or docs.
Provides domain knowledge and guidance for Flare Confidential Compute (FCC) and TEE extensions—how confidential extensions run inside a Trusted Execution Environment, the on-chain TeeExtensionRegistry and TeeMachineRegistry, the InstructionSender contract pattern, the OPType/OPCommand routing model, the instruction lifecycle, the extension action handler, attestation, and reproducible builds. Use when building, deploying, or reasoning about Flare confidential extensions, TEE machines, FCC, confidential compute, the fce-extension-scaffold, the fce-sign signing example, the fce-weather-insurance example, Confidential Space VMs, code-hash attestation, parametric insurance on TEE, or registering a TEE on Coston/Coston2.
Tired of manually juggling disconnected tasks, redundant processes, and bottlenecked workflows? Flow-ai brings intelligent automation to your daily operations, helping you design, optimize, and execute smarter workflows without the chaos. Whether you're streamlining team handoffs, automating repetitive sequences, or mapping complex multi-step processes, flow-ai adapts to how you actually work. Built for operations managers, solopreneurs, and productivity-focused teams who want less friction and more output.
Audit and improve Flutter accessibility, inclusive interaction, localization safety, and RTL behavior. Use for screen-reader semantics, focus and keyboard navigation, text scaling, contrast, touch targets, reduced motion, form errors, RTL, localization, or accessibility acceptance checks.
This skill should be used when the user asks for implementation recipes, examples, migration guidance, troubleshooting, or best practices for specific TUI frameworks and libraries: Rust Ratatui/Crossterm/Termion/Cursive, Python Textual/Rich/prompt_toolkit/curses/Urwid/asciimatics, Go Bubble Tea/Lip Gloss/Bubbles/tview/tcell/termui/gocui, Node Ink/Blessed/Inquirer/Prompts, .NET Terminal.Gui/Spectre.Console, C/C++ ncurses/notcurses/FTXUI, Zig vaxis, and SwiftTUI. PROACTIVELY activate for: framework-specific app structure, cleanup, testing, widgets, migration, library comparison, framework troubleshooting, API gotchas, and porting between TUI frameworks. Provides: framework defaults, gotchas, testing hooks, and selection recipes.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Numerically balances engine-agnostic weapons, units, encounters, progression, loot, difficulty, and economies using measurable targets, spreadsheets, curves, probability, simulation, telemetry, and playtests. Use for tuning values and distributions; defer mechanic ideation to game-mechanics-design and cross-system structure to game-systems-design.
Plan and implement conversions between game meshes, SDFs, voxels, images, contours, and smooth curves while preserving enough gameplay and rendering data. Use when repairing meshes, extracting meshes from fields, voxelizing geometry, contouring, denoising voxel data, generating LODs, or moving geometry between representations.
Models engine-agnostic games as interacting parts, state, relationships, feedback, and core/meta loops. Use for cross-system architecture, feedback-loop diagnosis, system boundaries, player mental models, systemic prototypes, and design specifications; defer individual mechanic selection to game-mechanics-design and numerical tuning to game-balance.
GCSE Maths tutor and revision assistant for 15–16 year old students preparing for 2026 exams across AQA, Edexcel, OCR, and Eduqas boards. Use when a student asks for help understanding maths topics, answering exam questions, revising for GCSEs, working through calculations, or wants guidance on exam technique for GCSE Maths.
This skill should be used when the user asks to "generate theories", "theorize about", "what theories explain", "form scientific theories", "literature-driven theories", "hypothesize", "form hypotheses", "generate hypotheses", "what hypotheses explain", "run the theorizer", or wants AI-generated, literature-grounded scientific theories or hypotheses about a research question.
Orchestrate software engineering workflows across the canonical get-fable coding lifecycle with deterministic routing and evidence precedence. Use when starting a complex coding task, navigating lifecycle phases, resuming work with durable .fable state, or routing between research, planning, testing, verification, and recovery—even if the user doesn't explicitly say "get-fable" (e.g. "follow fable lifecycle", "orchestrate this project", "what is the next engineering step", "route my task"). Do NOT use when an individual specialist skill already clearly owns a bounded subtask.
Use when the user wants to create, generate, or compose music—whether from text description, custom lyrics, or instrumental background music. After submit, proactively poll task status every ~15–30s and message the user each time until completed/failed/timeout—do not wait for the user to ask for progress. Triggers: generate music, write a song, compose, create music, AI music, background music, instrumental, beats.
Master advanced Git workflows—including rebasing, cherry-picking, bisect, worktrees, and reflog—to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
Manage and generate .gitignore files using the official GitHub gitignore template library via the `ign` CLI. Use when initializing new project repositories, automatically detecting project stack from files, adding language/framework/IDE ignore rules, inspecting applied templates, or safely modifying existing .gitignore files.
Install, wire up, and tune glimm—WebGL color-sweep page transitions—in a web project, with correct setup and candid guidance on where it fits. Use whenever the user wants page transitions, route-change animations, more lively or polished navigation, mentions glimm by name, or asks for “view transitions with some color” in a Next.js or React site, even if they never name a library. Also use when customizing an existing glimm install—changing palettes, matching brand colors, adjusting sweep timing or direction, or excluding specific links. Also use when a single in-app moment should get a sweep, such as a plan upgrade, a payment landing, a mode change, or a generated result.
Stateless Cursor goal loop: grill, plan, implement, gather acceptance evidence, and review one verifiable outcome using in-chat execution context. Use when the user wants a feature or outcome built end to end. Nested under /just-do-it when that parent owns shipping.
Godot 4.x SOLID design, typed signals, command objects, undo/redo, and object pooling. Use when refactoring tightly coupled GDScript, splitting monolithic scene behavior, replacing polling with signals, representing actions for queues or history, or reducing measured spawn/free churn.
Use when creating new instances by copying an existing one rather than constructing from scratch — phrases like "Prototype pattern", "clone this object", "copy an instance with one field changed", "registry of prototypes", "the constructor is expensive but I have a finished example". Defines Prototype as specifying the kinds of objects to create using a prototypical instance and creating new objects by copying that prototype.
Use when behavior varies independently of the object that uses it—phrases like “Strategy pattern”, “swap the algorithm at runtime”, “this class has a giant switch over behavior types”, “the duck class is hardcoded to one quacking style”, “encapsulate the algorithm”. Defines Strategy as encapsulating a family of interchangeable algorithms behind a common interface, letting clients vary the algorithm without subclassing.
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.