Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Design a feature architecture by analyzing existing codebase patterns and conventions, then provide a comprehensive implementation blueprint with specific files to create or modify, component designs, data flows, and a build sequence. Use this skill when the user asks for an architecture design, an implementation plan for a non-trivial feature, or when dispatched as a sub-task during feature-dev architecture phase.
Automated code review for Arduino/ESP32/RP2040 projects focusing on best practices, memory safety, and common pitfalls. Use when user wants code feedback, says "review my code", needs help improving code quality, or before finalizing a project. Generates actionable checklists and specific improvement suggestions.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Compare two folders function by function with jscpd --compare, in the same language or across languages, and explain the result. Use when asked how two codebases relate, which functions one implementation has and the other lacks, how far a port has come, whether the iOS and Android versions of an app match, or which function in one folder corresponds to a function in the other.
Skill that helps users discover and understand Dagster integration libraries. Used when users have requests related to integrating with other tools / technologies, or when have users have questions related to specific integration libraries (dagster-*).
Используй, когда просят спроектировать систему, компонент или фичу и доступны тулы Искрона: «спроектируй», «давай продумаем» (сквозное — architect), «архитектура», «нужен дизайн», design, plan the system, «жц», «крия», «эстафета», «записать в Искрон», «положить в граф». Также в моменты решений («мы решили», persist this design) и после брейнсторма — граф превращает дизайн в запись. Не для имплементации уже принятой конкретной спеки, рутинных фиксов и кодинга без открытого структурного выбора.
Use this skill when the user needs SHA-1, SHA-256, or SHA-512 digest acceleration on BlueField-2 silicon via doca_sha (absent on BF-3)—selecting one-shot `doca_sha_task_hash` versus incremental `doca_sha_task_partial_hash` for chunked input, consulting `doca_sha_cap_*` for per-algorithm digest-size limits and input alignment, or decoding DOCA_ERROR_* statuses such as BAD_STATE on a resumed partial hash. Also load it for implied asks like "accelerate SHA-256 on the NIC", "streaming digest over chunks", "digest output size mismatch", or "is SHA-512 present on this card". Refuse and route to the proper owner for cryptographic-hash theory (collision resistance, SHA-3 selection), the AES-GCM / Compress / DMA libraries, or SDK install and BFB bring-up.
ALWAYS USE THIS SKILL to create, check the status of, list, or delete scratch org snapshots. A snapshot is a point-in-time copy of a scratch org's metadata AND data, referenced by name in the `snapshot` field of a scratch org definition file. Use when the user asks to create/take a snapshot, check a snapshot's status or creation progress, list/show/view existing snapshots (including filtering for snapshots expiring soon), or delete/remove a snapshot. Requires a Dev Hub with Scratch Org Snapshots enabled. DO NOT TRIGGER for creating org shapes (use dx-org-shape-manage) or for creating scratch orgs, including from an existing snapshot via `--snapshot` (use dx-org-manage).
Build a private party RSVP dApp on Midnight Network — attendees stay private until unshielded NIGHT check-in crosses the privacy boundary. Covers private-party.compact (no witnesses, persistentCommit, DApp-specific public keys, receiveUnshielded/sendUnshielded), Next.js frontend, 1AM wallet integration, low-level deploy/call, indexer polling, and optional vitest local devnet tests. Use for teaching privacy boundaries, commitment-based guest lists, organizer access control, or unshielded entry fees. Triggers: private party, RSVP dApp, privacy boundary, persistentCommit, getDappPublicKey, unshielded check-in, example-private-party, party organizer, guest list commitment. Also use when extending locker-dapp or payment-dapp wallet/provider patterns to privacy-preserving social flows.
Use this skill to drive Compose HotSwan from an AI agent (Claude Code, Cursor, any MCP client) so the agent can edit a Kotlin file, trigger a hot reload, capture a device screenshot, evaluate the result against a design intent, and iterate without a human in the loop. Covers the seven HotSwan MCP tools (hotswan_get_status, hotswan_reload, hotswan_take_screenshot, hotswan_start_snapshot, hotswan_stop_snapshot, hotswan_select_variant, hotswan_build_and_install), the canonical edit-reload-screenshot loop, snapshot-based rollback, and when to fall back to a full install for schema changes. Use when the developer says "get the AI to tune this screen until it matches a mock", asks "can the AI see what changed?" or "can the AI screenshot the device?", sets up a Claude Code or Cursor workflow that needs MCP tool access, or wants AI-driven UI iteration.
Audit and migrate existing Markdown rendering to Markstream, or upgrade a markstream-vue 1.x integration to 2.x. Use when Codex needs to replace another renderer, classify direct vs custom vs plugin-heavy adoption, preserve behavior during adoption, migrate custom renderers into scoped Markstream overrides, decide when `nodes` streaming is worth adopting, or replace removed 1.x code-block dependencies, APIs, preview payloads, and parser types.
Build interactive web applications using HTML/JavaScript interfaces with MATLAB computational backends via the uihtml component. Use when creating HTML-based MATLAB apps, JavaScript MATLAB interfaces, web UIs with MATLAB, interactive MATLAB GUIs, or when user mentions uihtml, HTML, JavaScript, web apps, or web interfaces.
Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF events, ATIF trajectories, OpenTelemetry, OpenInference, or custom event handling.
Use when embedding `@mariozechner/pi-coding-agent` as a coding-agent runtime in Node scripts, writing pi extensions (plugins) with `pi.registerTool` / `pi.registerCommand` / `pi.on`, packaging and `pi install` from npm/git, or picking between the SDK and `pi --mode rpc` for non-Node hosts. Covers session setup, the cwd × tools factory trap, TypeBox tool schemas, and the `peerDependencies` rule. Trigger on `pi-coding-agent`, `pi.registerTool`, `pi install`, or "embed a coding agent into Node" descriptions even when pi is not named.
Guide for migrating to Polar from other payment platforms (Stripe Billing, Paddle, Lemon Squeezy, Gumroad). Use this skill when: (1) Planning a migration from another payment provider to Polar; (2) Migrating customer data and subscriptions; (3) Running parallel systems during transition; (4) Mapping products and pricing between platforms; (5) Handling payment method migration; (6) Communicating migration to customers; (7) Testing migration in sandbox before production.
Pre-flight before creating a pull request: run `greptile review` on the committed branch, VERIFY the review actually matches this branch's diff, triage its findings, apply safe fixes (propose risky ones), and only then `gh pr create`. Runs in repos where greptile is configured. Trigger ONLY on explicit PR-creation intent: "crea el PR", "create the PR", "abrí el PR", "open a PR", or immediately before a `gh pr create`. Do NOT fire on a bare commit.
Diagnose and optimize existing slow SQL queries using execution plans, indexing strategies, query rewriting, and ORM tuning. Use when the user provides a query, performance symptom, or EXPLAIN plan; use sql-query-generation when creating a new query from requirements.
Use when the user asks to review or clean up R code for tidyverse style, standardize formatting or names, remove redundant comments or wrappers, or make a behavior-preserving style pass. Also use when writing substantial new R package code if the user requests tidyverse style or the package already follows it. Not for routine small edits or general correctness, security, or test-quality reviews.
Design and review production-grade low-latency VisionCamera v5 pipelines. Use for real-time GPU, ML, CV, Skia or WebGPU overlays, Nitro frame plugins, zero-copy interop, frame budgets, and latency profiling. Use the general react-native-vision-camera skill for setup, capture, controls, basic frame outputs, or v4 migration.
Instrument, operate, and review Rust applications with tracing spans and events, structured logs, metrics, OpenTelemetry context propagation, Prometheus export, sampling, correlation, redaction, cardinality control, tokio-console diagnostics, and graceful telemetry shutdown. Use when users ask for logging, distributed traces, service metrics, request correlation, async task diagnosis, SLO evidence, or production observability architecture.
Front door of the SDD flow. When the user asks for a feature or bug fix ("implementa…", "agrega…", "arregla…", "add…", "build…", "fix…"), FIRST scan the request + codebase context for load-bearing ambiguity and ask a few targeted clarifying questions (selectable options, recommended first) BEFORE writing any spec or code — then hand a well-formed goal to /opsx:propose (small) or the sdd-feature-flow workflow (large). Skip the questions when the request is already unambiguous. Modeled on GitHub Spec-Kit's /clarify.
Author or update the project's constitution — openspec/project.md — the non-negotiable principles, conventions, and constraints the Spec-Driven Development flow must honor. Modeled on GitHub Spec-Kit's /constitution. Run once per repo when onboarding SDD, or whenever the team's principles change. The sdd-feature-flow Analyze gate checks every spec against it.
Ingest raw context the user pastes or points at — a ticket, a design doc, meeting notes, a spec, a URL, referenced files/paths — and have an agent READ and UNDERSTAND all of it, then synthesize a well-formed feature brief (goal, scope, constraints, and load-bearing unknowns) that feeds sdd-clarify and the sdd-feature-flow harness. Use at the very start of a feature when you have source material instead of a one-line goal, or whenever the user says "here's the context" / "read this" / dumps a ticket or doc.
Migrate simple Vector-type Triton operators from GPU to Ascend NPU. Use when the user needs to migrate Triton code to NPU, or mentions GPU-to-NPU migration, Triton migration, or Ascend adaptation. Note: operators with compilation issues cannot be migrated automatically.
Create a technical implementation plan from a feature spec. Documents architecture, data models, interface contracts, exceptions and the records the change affects, checked against the code as it is, without generating code. Run after spec-kit-clarify.
Control Supaterm spaces, tab groups, tabs, panes, licensing, coding-agent integrations, and task launches with `sp`. Use when an agent needs to inspect or operate Supaterm, organize tabs, handle a tab-limit refusal, guide a Supaterm purchase or activation, open commands in tabs or panes, or launch and prompt coding agents.
Connect to the Superset MCP server to create Git-worktree workspaces, launch coding-agent sessions, schedule automations, and manage tasks on a user's Superset account. Use when an agent needs to orchestrate parallel coding agents programmatically over MCP instead of the CLI.
Coordinate multiple terminal coding agents through the Superset CLI by creating isolated workspaces, launching workers, sending follow-ups, reading terminal output, tracking dependencies, and collecting structured results. Use when asked to delegate or parallelize coding work, coordinate agents across workspaces or hosts, hand work between agents, monitor worker progress, or run a multi-agent workflow with Superset. Do not use for ordinary single-agent workspace, task, or automation management.
A guide for building applications with the SUZURI REST API. Use when developing apps that create, search, or display merchandise with the SUZURI API, or services that integrate with SUZURI. When topics about SUZURI-related application development come up, such as "SUZURIのAPIで", "SUZURIで商品を", "SUZURIと連携", "スズリAPI", or "suzuri.jpのAPI", refer to this skill.
TanStack DB reactive client-side database with live queries and optimistic mutations. Use when building reactive UIs with local-first data, sync engines, or optimistic updates. Use for tanstack-db, live queries, optimistic mutations, sync engine, reactive database, local-first.
Direct advanced Three.js camera systems. Use for scale-aware chase rigs, thrust lag, side/orbit cameras, body-relative up vectors, quaternion handoffs, authored cinematic framing, floating origins, pointer-look controls, camera collision constraints, projection ownership, and lifecycle restoration.
Use when a user wants to upgrade, update, or migrate a dbt project to the latest version — e.g. "upgrade my dbt project," "migrate this off dbt 1.5," "get this project running on the latest dbt," "bump the dbt version." Upgrades a dbt v1 project (on 1.3, 1.4, 1.5, 1.6, or 1.7) all the way to 1.12, applying the required breaking, behavior, and deprecated changes from a data-driven issue corpus. Inputs — starting_version (the project's current dbt minor, one of 1.3/1.4/1.5/1.6/1.7) and adapter_type (snowflake/redshift/bigquery/databricks/spark); both are normally supplied by the caller (e.g. the dbt VS Code extension), with fallbacks described in the skill.
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.