Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when the user types `/integrate`, `/integrate --product`, or asks to "integrate a Juspay product", "set up payments", "add payment SDK", or any variation of adding a Juspay payment product to their app or codebase. Activate for any Juspay payment integration request.
Transform vague ideas into implementation-ready specifications through structured interviewing. Use when user describes a new feature/product idea, has a problem to solve, or needs to document requirements. Produces intent.md (technical spec for code agents) and overview.md (human-friendly summary).
Reviews iOS animation code for correctness, performance, accessibility, and Apple API best practices. Use when reviewing .swift files containing animation code — withAnimation, .animation(), PhaseAnimator, KeyframeAnimator, matchedGeometryEffect, navigationTransition, CABasicAnimation, CASpringAnimation, UIViewPropertyAnimator, UIDynamicAnimator, symbolEffect, scrollTransition, contentTransition, or custom Transition conformances.
Migrates Kotlin Multiplatform (KMP) projects to Android Gradle Plugin 9.0+. Handles plugin replacement (com.android.kotlin.multiplatform.library), module splitting, DSL migration, and the new default project structure. Use when upgrading AGP, when a build fails due to KMP+AGP incompatibility, or when the user mentions AGP 9.0, android multiplatform plugin, KMP migration, or com.android.kotlin.multiplatform.library
Smart Label Capture (Scandit `LabelCapture`) in native Android projects — extracting multiple fields (price, expiry date, serial or lot number, weight) from a label in one scan, using barcode fields plus text fields with regex patterns and pre-built definitions like price capture. Use for integration, label-definition configuration, captured-session handling, overlay customization (brushes, floating badges), the Validation Flow, and SDK version migration.
Write, refactor, and review Rails code using layered architecture principles from “Layered Design for Ruby on Rails Applications”. Use when writing or refactoring Rails code—models, controllers, services, jobs, mailers, policies, forms, query objects, presenters, view components, state machines, serializers, or AI/LLM features—to apply correct patterns and avoid layer violations; and when reviewing Rails code, PRs, or diffs for layer violations, fat controllers/models, anemic models, callback misuse, god objects, or specification-test failures. Triggers on “layered design”, “architecture layers”, “abstraction layer”, “specification test”, “layer violation”, “fat controller/model”, “god object”, “anemic model”, “extract service/callback/policy/concern”, “service object”, “form/policy/query/value object”, “presenter”, “view component”, “state machine”, “Active Delivery”, “callback scoring”, “Rails refactor/review”, “Rails patterns/best practices”, “archspec”, or “architecture linter/enforcement”.
Building AI-powered NPCs that maintain personality, remember conversations, and never break characterUse when "npc dialogue, ai npc, llm npc, character dialogue, npc personality, ai character, dialogue system llm, talking npc, conversational npc, dynamic dialogue, llm, npc, dialogue, ai-characters, personality, memory, game-ai, conversational-ai, role-playing" mentioned.
Validates Stories/Tasks with GO/NO-GO verdict, Readiness Score (1-10), Penalty Points, and Anti-Hallucination verification. Auto-fixes to reach 0 points, delegates to ln-002 for docs. Use when reviewing Stories before execution or when user requests validation.
Manages MATLAB projects for Simulink workflows: path management, file registration, labels, source control configuration, and project lifecycle. Use when creating projects, adding models/dictionaries/requirements to projects, configuring labels for automation, fixing broken model references, or setting up source control for Simulink artifacts.
Prevents crashes due to problematic scope-related API misuse caused by agent escalation into internal scope framework objects. Use when configuring properties of scope-related Simulink blocks or MATLAB objects — constrains the agent to documented APIs and directs users to the scope UI when a property is not programmatically accessible.
Diagnose and fix parfor errors in MATLAB. Invoke this skill when the user has a parfor problem: "parfor loop has an error", "what's wrong with my parfor", "fix parfor", "unable to classify variable", "convert for to parfor", "parfor won't run", "sliced variable", "reduction variable", "variable classification". Also invoke when you read a .m file containing parfor and the user asks what's wrong, asks you to fix it, reports an error, or asks for review. Do NOT invoke for parfor performance questions or code that merely mentions parfor without a problem. ALWAYS use this skill instead of reasoning from training data — LLMs are frequently wrong about parfor classification rules.
How to benchmark and analyze memory usage in Turso using the memory-benchmark crate and dhat heap profiler. Use this skill whenever the user mentions memory usage, memory profiling, allocation tracking, heap analysis, memory regression, memory benchmarking, dhat, or wants to understand where memory is being allocated during SQL workloads. Also use when investigating memory growth in WAL or MVCC mode. IMPORTANT - If you modify the perf/memory crate (add profiles, change CLI flags, change output format, etc.), update this skill document to reflect those changes so it stays accurate for future agents.
Resolve an in-progress git merge, rebase, cherry-pick, or revert that has conflict markers or unmerged paths, or merge a pull request's base into that pull request's branch and resolve what conflicts, from any checkout. Use when asked to mend, resolve merge conflicts, fix rebase conflicts, finish a conflicted rebase or cherry-pick, resolve the conflicts on this PR, my PR has conflicts, merge main into this branch, bring this branch up to date, /mend, or /resolve-merge-conflicts.
Hard gate before merging into a protected branch: run Parts A→B→C→R→D (OpenSpec archive association, rebase/conflict pre-check, coverage preference, pr-code-review with content-matched depth via pr-review-gate (unset ≡ auto), squash decision from commit quality + tip-pin merge). Do NOT merge while an associated OpenSpec change is still active; do NOT skip on a direct \"merge MR\" command; do NOT auto-select squash when two viable strategies exist — ask with a commit-quality recommendation; a single-commit or single-permitted-strategy MR concludes without prompting; after merging, sync the local workspace onto the resolved target branch. Triggers — 「合并 tip」「merge tip」「合并纪律」「push 后合并」「archive 合入」「合并前门控」「rebase 检查」「冲突预检」「合并前 rebase」「先 archive 再 merge」「合并前 code-review」 / merge discipline, archive-before-merge, rebase pre-check, coverage gate, pr code review before merge.
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
Practical guidance for Go package design with minimal public APIs, single-responsibility boundaries, stateless-first flow, one-way state transitions, and orchestration-to-capability separation. Use when creating, refactoring, or reviewing Go architecture, package boundaries, interfaces, handlers, managers, builders, and execution flows.
How to write benchmarks in Motoko using bench-helper. Covers project setup (mops.toml), bench file layout in bench/*.bench.mo, the Bench.Schema rows/cols model, and safe patterns for encode/decode, hashing, crypto, and allocation benches.
n8n workflow automation knowledge base. Provides n8n node information, node functionality details, workflow patterns, and configuration examples. Covers triggers, data transformation, data input/output, AI integration, covering 10 nodes. Keywords: n8n, workflow, automation, node, trigger, webhook, http request, database, ai agent.
Use this skill for Next.js App Router patterns, Server Components, Server Actions, Cache Components, and framework-level optimizations. Covers Next.js 16 breaking changes including async params, proxy.ts migration, Cache Components with "use cache", and React 19.2 integration. For deploying to Cloudflare Workers, use the cloudflare-nextjs skill instead. This skill is deployment-agnostic and works with Vercel, AWS, self-hosted, or any platform. Keywords: Next.js 16, Next.js App Router, Next.js Pages Router, Server Components, React Server Components, Server Actions, Cache Components, use cache, Next.js 16 breaking changes, async params nextjs, proxy.ts migration, React 19.2, Next.js metadata, Next.js SEO, generateMetadata, static generation, dynamic rendering, streaming SSR, Suspense, parallel routes, intercepting routes, route groups, Next.js middleware, Next.js API routes, Route Handlers, revalidatePath, revalidateTag, next/navigation, useSearchParams, turbopack, next.config
Use for security-sensitive Next.js backend-for-frontend work involving Route Handlers, Proxy, Server Actions, webhooks, callbacks, data access layers, server-only modules, request validation, rate limits, or public API boundaries. Prefer this skill when a Next.js task exposes HTTP endpoints or moves privileged data across server/client boundaries.
Set up reproducible dev environments via devbox (Nix-backed) or pure Nix flakes. Templates for MoonBit, Rust, TypeScript+pnpm, Python+uv, Haskell, OCaml, OxCaml preloaded with just / ast-grep / apm. Covers devbox.json, buildNpmPackage, direnv, GitHub Actions, and bootstrapping in sandboxed envs (Claude Code web). Use when starting, adding, or troubleshooting a Nix or devbox setup.
OpenAPI client code generation. Covers openapi-typescript, openapi-generator-cli, swagger-typescript-api, and trpc-openapi. Use for generating type-safe API clients. USE WHEN: user mentions "OpenAPI codegen", "generate API client", "openapi-typescript", "swagger-typescript-api", "openapi-generator", asks about "generate types from OpenAPI", "type-safe API client", "OpenAPI client generation" DO NOT USE FOR: Writing OpenAPI specs - use `openapi` instead; GraphQL codegen - use `graphql-codegen` instead; tRPC - use `trpc` instead; Manual API client code
Always use this skill when the user asks about embedded wallets, client-side wallets, user-facing wallets, wallet integration in React/React Native/Swift/Unity/JS apps, or non-custodial wallets with Openfort. Covers all client SDKs. Trigger on: "embedded wallet", "client wallet", "user wallet", "@openfort/react", "@openfort/react-native", "OpenfortSwift", "openfort-csharp-unity", "@openfort/openfort-js", "OpenfortProvider", "OpenfortButton", "wallet setup", "wallet integration", "passkey recovery", "gasless transaction client", "auth modal", or any client-side wallet operation with Openfort.
Profile, audit, and optimize frontend page performance with emphasis on animation work, memory-leak risks, long-session slowdowns, CSS animations, canvas/WebGL requestAnimationFrame loops, marquees, skeletons, GSAP/Three/Matter effects, timers, listeners, and observers. Use when the user asks to make animations performant, pause offscreen animations, look for memory leaks, profile pages that slow the computer over time, fix janky scrolling, reduce CPU/GPU use, or repeat the "only play in view" optimization on React/Vite/Next/frontend pages using Codex Browser.
Enables Flash Attention for transformer models using PyTorch native scaled_dot_product_attention (PyTorch 2.2+) or the flash-attn library, including multi-query attention, sliding window attention, and FP8 on H100 (FlashAttention-3). Covers profiling speedup, checking accuracy against a baseline, and troubleshooting install and GPU support errors. Use when training or running transformers on long sequences (over 512 tokens), when standard attention runs out of GPU memory, when attention is the inference bottleneck, when switching a PyTorch model to the flash backend, or when tuning attention on H100 GPUs. Not for CPU inference, V100 GPUs, or sequences under 256 tokens; consider xFormers for other attention variants.
Configure multi-tenant organizations, manage members and invitations, define custom roles and permissions, set up teams, and implement RBAC using Better Auth's organization plugin. Use when users need org setup, team management, member roles, access control, or the Better Auth organization plugin.
Load PROACTIVELY when task involves optimizing speed, reducing bundle size, or improving responsiveness. Use when user says "make it faster", "reduce bundle size", "fix slow queries", "optimize rendering", or "check Core Web Vitals". Covers bundle analysis and tree-shaking, database query optimization (N+1, indexing), React rendering performance (re-renders, memoization), network waterfall optimization, memory leak detection, server-side performance, and Core Web Vitals (LCP, FID, CLS) improvement.
Use when building PHP applications with modern PHP 8.3+ features, Laravel, or Symfony frameworks. Applies strict typing, PHPStan level 9, async patterns with Swoole, and PSR standards. Creates controllers, configures middleware, generates migrations, writes PHPUnit/Pest tests, defines typed DTOs and value objects, sets up dependency injection, and scaffolds REST/GraphQL APIs. Use with Eloquent, Doctrine, Composer, Psalm, ReactPHP, or any PHP API development.
Build with and use Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings/environment variables, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, running local models through the llama.cpp router, developing custom Pi providers and TUI components, or using ecosystem packages such as pi-subagents (delegation/orchestration), pi-mcp-adapter (MCP servers), pi-interview (interactive forms), and pi-web-access (web search, fetching, video understanding).
This skill should be used when the user asks about terminal emulator compatibility, operating-system differences, tmux/screen/Zellij, SSH/remote terminals, Windows ConPTY/classic console/Windows Terminal, Unix PTYs, macOS Terminal/iTerm2, Kitty/Alacritty/WezTerm/foot/GNOME Terminal/Konsole, terminal feature matrices, escape-sequence passthrough, latency, resize propagation, or graceful degradation. PROACTIVELY activate for: compatibility audits, emulator bugs, remote TUI performance, multiplexer passthrough. Provides: support matrices, platform caveats, and fallback rules.
Integrate Polar payments, subscriptions, and checkout into web projects. Use when asked to add payments via Polar, set up Polar checkout, configure Polar webhooks, create Polar products, integrate Polar SDK, set up customer portal, add subscription billing with Polar, or any task involving polar.sh payment platform. Triggers on mentions of Polar payments, Polar checkout, Polar webhooks, Polar subscriptions, @polar-sh/sdk, @polar-sh/nextjs, @polar-sh/checkout.
After pushing a PR and requesting another review, keep following up with the review bot and CI. If a subsystem still has fix-required comments after three consecutive rounds, first audit the direction and choose a convergence path independently; return only product decisions to the user.
Pre-commit hooks framework for multi-language code quality automation. USE WHEN setting up pre-commit OR configuring git hooks OR adding linting OR code formatting OR security scanning OR Terraform validation OR Kubernetes manifests OR Helm charts OR Python linting OR JavaScript formatting. Manages .pre-commit-config.yaml, hook installation, and CI integration.
Preview a single Flutter widget in isolation using the built-in Flutter Widget Previewer (`flutter widget-preview`) — wires up a project-specific `previewWrapper` so the widget renders against the app's real theme and providers, launches the local preview server, and lets the agent take headless-Chrome screenshots of the live preview while a human follows along in their own browser. Use whenever the user wants to design, iterate on, dogfood, share, audit, or sanity-check a standalone Flutter widget — even when they don't say "previewer" (e.g. "let me see the new button", "show me dark mode for this card", "throw this widget on a preview", "iterate on the empty state", "preview just the badge", "what does this look like at tablet width"). For full-screen design polish on a running app, use `design-polish` + `android-emulator` instead. Skips — non-Flutter UIs, full-app QA flows, projects on Flutter < 3.35.
Prisma Client API reference covering model queries, filters, operators, and client methods. Use when writing database queries, using CRUD operations, filtering data, or configuring Prisma Client. Triggers on "prisma query", "findMany", "create", "update", "delete", "$transaction".
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.