Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and user media, or producing a clearly labeled documentation-derived planning estimate when representative media is absent. Also use for a video request limited to PSNR or SSIM, to apply the terminal scope response.
Sense-check agent-generated code for junior software engineer readability, maintainability, and safe modification. Use whenever Codex makes code changes, reviews code, reviews diffs, or evaluates implementation plans created by an agent; after code changes, run this review in a loop until all findings are resolved or 10 total review loops have completed. Ensure the result is simple, intuitive, locally understandable, easy to debug, explicit in control flow, appropriately abstracted, and explainable by a reasonably capable new team member without hidden context.
Platform-oriented writing assistant for long-form serialized web fiction. Handles new project setup, chapter continuation, single-chapter revision, project memory maintenance, long-work volume governance, and chapter quality checks. Built-in three-layer writing principles (chapter/scene/language) fit mainstream genres such as wish-fulfillment, romance, and power struggles, supporting the whole process from premise to ultra-long works. For more information follow 抖音君黎.
Scan a product codebase for activation, engagement, and retention moments and recommend lifecycle messaging opportunities. Use when finding onboarding, churn, trial, or habit-forming notification candidates without creating Knock resources.
Add a new book to the mmontes11/knowledge-base `books/` section: create the book-shaped entry (entry README, one numbered file per chapter, the source PDF), summarize each chapter faithfully and attribute it, add mermaid diagrams where they clarify a mechanism, and register the book in the root README's Tracked books table. Use whenever the user wants to add, create, or import a book into the knowledge base — "add this book to the knowledge base", "summarize <book> for the KB", "create a books/ entry for <title>", "work through chapter N of <book>" — even if they don't say "knowledge base" explicitly.
Use when work surfaces something epistemic worth keeping — "we're assuming / proceeding as if X", "we decided X over Y", "open question worth outliving this session", "we're bound by X", "evidence for/against X", "testable hypothesis", or a stable concept worth naming — and when settling, relating, or surveying such records. Routes capture, settle, and survey intent to the correct `doctrine knowledge` verb.
Implement multi-agent coordination patterns (supervisor-subagent, router, orchestrator-worker, handoffs) for LangGraph applications. Use when users want to (1) implement multi-agent systems, (2) coordinate multiple specialized agents, (3) choose between coordination patterns, (4) set up supervisor-subagent workflows, (5) implement router-based agent selection, (6) create parallel orchestrator-worker patterns, (7) implement agent handoffs, (8) design state schemas for multi-agent systems, or (9) debug multi-agent coordination issues.
Read, write, and manipulate LAS (Log ASCII Standard) well log files for borehole geophysical and petrophysical data. Use when the agent needs to: (1) Read/parse LAS 1.2 or 2.0 files, (2) Extract well headers or curve data, (3) Convert LAS to DataFrame/CSV/Excel, (4) Create new LAS files from arrays, (5) Modify existing LAS files, (6) Handle problematic or malformed LAS files, (7) Batch process multiple well files.
When the user wants to optimize last-mile delivery operations, urban logistics, or final-mile fulfillment. Also use when the user mentions "last mile," "final mile," "urban delivery," "home delivery," "same-day delivery," "delivery density," "delivery windows," or "doorstep delivery." For general route optimization, see route-optimization. For fleet management, see fleet-management.
Use this skill to test a `Fragment` in isolation using `FragmentScenario`, `launchFragmentInContainer<F>()`, and `launchFragment<F>()`. Covers the `androidx.fragment:fragment-testing` + `androidx.fragment:fragment-testing-manifest` artifact split, the `EmptyFragmentActivity` host (`android:Theme.WithActionBar` parent — not AppCompat), the `themeResId` override, the `FragmentFactory` survival across `recreate()` via the ViewModelStore-backed holder, the `containerViewId = android.R.id.content` vs `0` distinction (in-container vs headless), and the `findNavController()` limitation. Use when the user reports `You need to use a Theme.AppCompat theme (or descendant)`, `Fragment ... does not have a NavController set`, `Cannot set initial Lifecycle state to DESTROYED for FragmentScenario`, or asks "how do I test a fragment in isolation" / "headless fragment test".
Pre-send quality scorecard for any lead list. Grades duplicate rate, title diversity, bad-title patterns, catch-all domain density, ICP fit, email verification coverage. Outputs a letter grade + action items BEFORE you send. Catches bad lists before they burn inboxes. Run after email enrichment, before Smartlead upload.
Build a source-grounded map of a research topic by comparing papers, benchmarks, code, and genuine disagreements. Use whenever the user wants to understand a research area, not just find papers — including phrasings like "what's the current state of X", "what should I read on Y", "is X still SOTA", "are there good baselines for Z", "what does the field believe about W", "survey this area for me", "what are the key papers on X", "compare these two approaches", or "is this claim actually well-supported". Also use when the user is about to build on a method and should first verify the evidence base is solid. If the user already has a source map and wants polished Related Work prose, use related-work-writer instead. The skill's main job is preventing hallucinated consensus — confidently synthesized positions that aren't grounded in the actual sources.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
When the user wants to run a geogrid scan, check existing scan reports, track ranking trends over time, monitor GBP changes via Falcon Guard, or analyze reviews. Also use when the user says "run a scan," "check my rankings," "Local Falcon," "how am I ranking," "ranking heatmap," or "scan this keyword." This is the execution tool — for interpreting results, also load geogrid-analysis.
Multi-language support, resource files, culture formatting, and globalization patterns for ASP.NET Core Razor Pages applications. Use when implementing multi-language support in ASP.NET Core applications, managing resource files for translations, or formatting dates, numbers, and currencies for different cultures.
Generate complete business proposals for client projects. Takes client requirement documents (docx/pdf/md) or verbal descriptions as input, outputs a professionally formatted proposal with technical architecture, budget, timeline, risk analysis, and team introduction. Automatically calls illustrate for images and any2pdf for final PDF delivery. Trigger when user mentions "商务方案", "合作评估", "项目评估", "报价方案", "proposal", "需求评估", "给客户出方案", or wants to generate a client-facing project proposal from requirements.
Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.
Spiral inductors, interdigital capacitors, baluns, resonators, phase shifters for impedance matching, DC blocking, and bias tees. TRIGGER: user asks to design or create a spiral inductor, interdigital capacitor, balun, resonator, phase shifter, or other passive RF component. Invoke BEFORE writing code — class names and property patterns are non-obvious. SKIP: filter design (use matlab-design-pcb-filter), coupler/splitter design (use matlab-design-pcb-coupler), transmission line design (use matlab-design-pcb-transmission-line), EM analysis (use matlab-analyze-em), material setup only (use matlab-manage-pcb-material).
Export conversation MATLAB code to a clean, runnable .m script. Use when asked to save or export session work. TRIGGER: user asks to save, export, or generate a script from the current session's MATLAB code. Also when asked for a reproducible script or clean version of what was run.
Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection, classification in CT, MRI, X-ray, ultrasound, or pathology imaging. Triggers on requests for "review paper", "survey", "literature review", "综述", "systematic review", or mentions of writing academic reviews on deep learning for medical imaging.
Create evidence-based medical newsletters for interventional cardiologists in Eric Topol's authoritative Ground Truths style. Use when the user wants to analyze trending medical topics with engagement predictions, conduct data-driven topic selection, research medical literature using PubMed, or write comprehensive well-referenced newsletters that build professional authority. Handles complete workflow from trend analysis to final draft.
End-to-end MegaETH development playbook (Feb 2026). Covers Foundry project setup with MegaETH-specific config, wallet operations, token swaps (Kyber Network), eth_sendRawTransactionSync (EIP-7966) for instant receipts, JSON-RPC batching, real-time mini-block subscriptions, storage-aware contract patterns (Solady RedBlackTreeLib, transient storage), MegaEVM multidimensional gas model, WebSocket keepalive, bridging from Ethereum, Privy headless signing for ultra-low latency, debugging with mega-evme, x402 Permit2 payments on MegaETH (standard flow via x402ExactPermit2Proxy/x402UptoPermit2Proxy at canonical addresses), legacy Meridian x402 payments, and Warren Protocol for on-chain website hosting. Use when building on MegaETH, using Foundry, managing wallets, sending transactions, deploying contracts, integrating Privy embedded wallets, ERC-7710 delegation framework for scoped on-chain permissions, MetaMask Smart Accounts Kit for smart account creation and delegation management, integrating x402 Permit2 payments or Meridian/x402 paid APIs or agent actions, hosting websites on-chain with Warren, or integrating MegaNames (.mega naming service) for name registration, resolution, subdomains, subdomain marketplace (selling/buying subdomains with token gating), and text records.
Migrate a GitHub Actions workflow to RWX. Translates triggers, jobs, steps into an optimized RWX config with DAG parallelism, content-based caching, and RWX packages. TRIGGER when: the user asks to migrate, convert, or translate a GitHub Actions workflow to RWX.
Use this skill to migrate a codebase off the deprecated `android.test.*` testing classes that ship in the Android platform SDK onto AndroidX Test. Covers `InstrumentationTestRunner` → `AndroidJUnitRunner`; `InstrumentationTestCase`/`AndroidTestCase` → `@RunWith(AndroidJUnit4)` + `InstrumentationRegistry`/`ApplicationProvider`; `ActivityInstrumentationTestCase2` → `ActivityScenario`/`ActivityScenarioRule` + Espresso; `ServiceTestCase`/`ProviderTestCase2` → `ServiceTestRule`/`ProviderTestRule`; `MoreAsserts` → Truth/Hamcrest; `ViewAsserts`/`TouchUtils` → Espresso matchers/actions; `android.test.UiThreadTest`/`FlakyTest`/`suitebuilder.annotation.*` → `androidx.test.*`; `android.test.mock.*` → real test contexts or Mockito; and JUnit3 `extends TestCase` → JUnit4 `@Test`. Use when the user sees `@Deprecated` on `android.test.*`, asks how to replace `ActivityInstrumentationTestCase2` / `InstrumentationTestCase` / `MoreAsserts` / `TouchUtils`, or "old Android tests won't run on AndroidJUnitRunner".
Use when the user asks to build iOS screens, SwiftUI views, UIKit layouts, mobile components, or any iOS app UI. Also use when styling, redesigning, or beautifying any iOS interface. Covers iOS 26 Liquid Glass design language, hierarchy, motion, and platform-native patterns.
Use when connecting an agent or integration to Mochi, choosing interactive OAuth, an unattended API key, an existing MCP connection, or a registered OAuth application, discovering current Public API docs and OpenAPI, using the read-only CLI, or planning safe direct API writes.
This skill should be used when the user asks to expose Modal.com functions as APIs or schedule Modal jobs. PROACTIVELY activate for: FastAPI endpoints, @modal.fastapi_endpoint, @modal.asgi_app, @modal.wsgi_app, webhooks, WebSockets, custom domains, endpoint timeouts, modal.Cron, modal.Period, scheduled ETL, cron timezones, deploy-vs-run schedule behavior, and endpoint debugging. Provides: endpoint decorator selection guide, scheduling patterns, timezone/cron rules, and debugging recipes for endpoints and schedules.
Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to model, define, or compute a conversion rate, funnel, step completion, drop-off, activation-funnel, signup-to-paid, or any "what % of users who did A went on to do B (within N days)" metric. Covers the funnel model (ordered steps, the conversion-window time-box, strict vs any-order), the person-vs-group aggregation unit, overall vs step-to-step conversion (two different numbers), breakdown attribution, and when a saved funnel insight beats a warehouse view. On PostHog, model funnels in HogQL with windowFunnel; in dbt, stage the event stream and compute an fct_conversion mart with tests. Read modeling-warehouse-foundations first for the view-vs-dbt mechanics; pairs with query-funnel for interactive analysis.
Plan and review MySQL/InnoDB schema, indexing, query tuning, transactions, and operations. Use when creating or modifying MySQL tables, indexes, or queries; diagnosing slow/locking behavior; planning migrations; or troubleshooting replication and connection issues. Load when using a MySQL database.
[Hyper] Use when working on Next.js projects, especially App Router or App Router migration work. Enforces current official Next.js architecture rules for project/folder structure, Hypercore local `src/modules` / `src/services` / `src/db` organization, Drizzle boundaries, hooks, Server and Client Component boundaries, Cache Components and data freshness, Server Actions, Route Handlers, Proxy, and platform/env safety.
Complete Next.js caching system with 'use cache' directive (Next.js 16). PROACTIVELY activate for: (1) Understanding 4 caching layers (Request Memoization, Data Cache, Full Route Cache, Router Cache), (2) Cache Components with 'use cache' directive, (3) fetch() caching options, (4) cacheLife() and cacheTag() functions, (5) Time-based revalidation, (6) On-demand revalidation with revalidatePath/revalidateTag, (7) Static generation with generateStaticParams, (8) Cache debugging. Provides: 'use cache' patterns, Cache Components, caching strategies, revalidation patterns, ISR setup, cache headers. Ensures optimal performance with correct cache invalidation.
Complete Next.js advanced routing system. PROACTIVELY activate for: (1) Dynamic routes with [slug], (2) Catch-all routes [...slug], (3) Route groups for organization, (4) Parallel routes with @slot, (5) Intercepting routes for modals, (6) Private folders with _prefix, (7) Route Handlers (API), (8) Search params handling, (9) Programmatic navigation. Provides: Dynamic routing patterns, parallel route slots, modal interception, API handlers. Ensures flexible routing with proper URL structure.
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.