Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when migrating users or authentication from another provider (Firebase, Cognito, Supabase, Clerk, or custom auth) to Auth0. Covers bulk user import, gradual migration strategies, and updating JWT validation — use even if the user says "switch our auth to Auth0" or "move our users to Auth0".
Diagnose and repair a broken Notte Function. Use when a deployed or scheduled Function has started failing or returning empty/wrong results — for example, “my function fn_... returns empty now,” “repair my scraper function,” “the Indeed function broke after the site changed,” “fix this failed function run,” or “diagnose why my scheduled function stopped working.” The user supplies the broken Function; this skill finds the root cause, re-explores the changed surface, verifies a fix in isolation, and promotes it behind a confirmation gate. Pairs with notte-functions-build, which builds Functions
Guide the design and management of trading venue connectivity and market data infrastructure. Owns the FIX session layer (logon, heartbeats, sequence number gaps, resend and gap recovery, disconnects). Use when building or troubleshooting FIX sessions for order routing or drop copy, integrating exchange protocols like OUCH, ITCH, PITCH, or Pillar, designing market data feed architecture (consolidated SIP vs direct feeds), handling trading halts or circuit breakers or LULD bands, planning co-location or failover and disaster recovery for exchange connectivity, implementing Rule 15c3-5 market access controls, or mapping symbology across venues and data sources. For order state machines and execution-report handling see order-lifecycle.
Comprehensive guide for implementing Syncfusion React button components including Button, ButtonGroup, DropDownButton, Floating Action Button, ProgressButton, SplitButton, Speed Dial, Switch, RadioButton, and Chips. Use this when adding styled buttons, toggle behavior, icon support, grouped selections, dropdown action menus, programmatic control floating primary actions, expandable speed dial menus, compact interactive elements with avatars and drag-and-drop, or single/multiple selection capabilities to a React application.
Implements Syncfusion DataManager for local/remote binding, CRUD, querying, caching, and middleware. Supports JsonAdaptor, ODataAdaptor, ODataV4Adaptor, UrlAdaptor, WebApiAdaptor, WebMethodAdaptor, RemoteSaveAdaptor, GraphQLAdaptor, CustomDataAdaptor, and CustomAdaptor. Covers Query class, filtering, sorting, paging, grouping, persistence, offline mode, caching, and error handling.
Expert patterns for 2D animation in Godot using AnimatedSprite2D and skeletal cutout rigs. Use when implementing sprite frame animations, procedural animation (squash/stretch), cutout bone hierarchies, or frame-perfect timing systems. Trigger keywords: AnimatedSprite2D, SpriteFrames, animation_finished, animation_looped, frame_changed, frame_progress, set_frame_and_progress, cutout animation, skeletal 2D, Bone2D, procedural animation, animation state machine, advance(0).
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
First-run setup for [email protected] — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via `doctor`
OpenOCD download and debugging tool for probe detection, firmware flashing, Flash erasing, GDB Server startup, target reset control, Telnet online debugging (halt/resume/step/registers/memory/breakpoints), GDB source-level debugging, and Semihosting/ITM output capture and low-level queries. Triggers automatically when the user mentions OpenOCD, ST-Link, CMSIS-DAP, DAPLink, FTDI, flashing firmware, erasing Flash, GDB Server, reset, interface/target/board configuration, openocd.cfg, online debugging, single stepping, breakpoints, viewing registers, reading/writing memory, or semihosting, and also supports explicit invocation via /openocd. Even if the user only says "flash it", "start the GDB Server", "erase the chip", "look at the registers", "single step" or "capture semihosting", this skill should trigger as long as the context involves an OpenOCD-supported open source debugger.
Project documentation lifecycle for PHP/Laravel and Node/TypeScript/React projects — bootstrapping essential docs, naming and folder conventions, freshness, and cleanup of AI-generated junk and stale files. Use when starting a new project, setting up docs/ structure, auditing markdown files, cleaning up the docs folder, or deciding which docs to keep, archive, or delete. Triggers on "set up docs", "audit docs", "clean up markdown", "what docs does this project need", "organize docs folder", "find stale docs".
strace and ltrace skill for system call and library call tracing. Use when a binary behaves incorrectly without crashing, diagnosing file-not-found errors, permission failures, network issues, or unexpected library calls by tracing syscalls and library function calls. Activates on queries about strace, ltrace, syscall tracing, library interception, ENOENT, EPERM, strace -e, or diagnosing binary behaviour without a debugger.
Comprehensive guide for implementing Syncfusion React input components including Uploader, NumericTextBox, TextBox, TextArea, CheckBox, OTP Input, Signature, RangeSlider, ColorPicker, MaskedTextBox, and Rating. Use this when building file upload UIs with async/chunk uploads, drag-and-drop functionality, numeric inputs with validation and formatting, text inputs with floating labels, custom adornments, form integration, accessibility compliance, and styling in React applications.
Reference for the Claude Code CLI itself (code.claude.com). Covers CLAUDE.md memory, settings.json (All settings, settings precedence, managed-settings.json), env-vars, model config, keybindings, statusline, terminal config, cli-reference (-p / --continue / --resume), sessions, checkpointing, worktrees, remote control, channels, deep links, and troubleshooting.
Use when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress, provider rate limits, crash-safe execution, and Agent Evals handoff. Covers AgentKit, `step.ai`, `step.run`, `step.waitForEvent`, native realtime, and when to use lower-level Inngest primitives instead of an in-memory agent loop. Use `inngest-agent-evals` with this skill when the user wants scoring, sessions, experiments, deferred scorers, or outcome-based evaluation for the agent.
LangSmith tracing and trace debugging for AgentSeek templates. Covers CLI installation, adding tracing to LangGraph apps, querying traces, and inspecting run IO. Use when debugging agent backends, investigating slow traces, or adding observability to a template.
Install, initialize, verify, and troubleshoot RTK (Rust Token Killer) for AI coding agents. Use when you need to reduce shell command token output, confirm the correct `rtk` binary is installed, choose between Homebrew, install.sh, or Cargo installation, wire up `rtk init` for Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode, or use compact wrappers such as `rtk git status`, `rtk read`, `rtk grep`, `rtk test`, `rtk lint`, and `rtk gain`. Triggers on: rtk, rust token killer, token saver cli, rtk init, rtk gain, codex rtk, gemini rtk, opencode rtk, claude hook token reduction.
AArch64 and ARM assembly skill for reading and writing ARM assembly code. Use when reading GCC/Clang output for AArch64 or ARM Thumb targets, writing inline asm in C/C++, understanding the ARM ABI (AAPCS64/AAPCS), or debugging register and stack state on ARM hardware or QEMU. Activates on queries about AArch64 assembly, ARM Thumb, NEON/SVE SIMD, ARM calling convention, inline asm for ARM, or reading ARM disassembly.
CPU cache optimization skill for C/C++ and Rust. Use when diagnosing cache misses, improving data layout for cache efficiency, using perf stat cache counters, understanding false sharing, prefetching, or structuring AoS vs SoA data layouts. Activates on queries about cache misses, cache lines, false sharing, perf cache counters, data layout optimization, prefetch, AoS vs SoA, or L1/L2/L3 cache performance.
Use this skill when adding or changing AI chat, text generation, reasoning, tools, model selection, or structured JSON output in a Customware-generated React Router and Hono app. It covers the server-only Customware AI Gateway, AI SDK with the OpenRouter adapter, AI Elements UI, supported model choices, and mandatory live model and structured-output checks.
Build React UIs with Fluid Functionalism — a shadcn/ui registry (@fluid) of animated components with a shared motion system: three spring speeds, a hover highlight that glides to the item nearest the cursor, labels that change weight without layout shift. Use whenever the user mentions Fluid Functionalism, @fluid, or fluidfunctionalism.com, asks for UI with satisfying/fluid/polished motion in a React, Next.js, shadcn, Radix, or Base UI project, builds any interface (settings dialogs, sidebars, command menus, chat UIs, forms, lists, tables) in a project with @fluid components installed, asks to review/audit existing UI motion against the system, or asks to update installed @fluid components or what changed in a release. Also use before hand-writing animation code (hover highlights, icon swaps, weight changes, enter/exit transitions, page reveals, skeleton loading) there, so custom code follows the system instead of inventing timings. Bundled scripts read the stack fresh each run and write nothing.
Use when analyzing an existing TypeScript or JavaScript codebase to decide where and how to introduce Inngest. Covers repository discovery, framework and package detection, finding durability gaps in HTTP handlers, webhooks, cron jobs, queues, long-running jobs, AI agents, Agent Evals, polling loops, eval loops, and side-effect-heavy code, then producing and implementing an incremental integration plan.
Open a pull request the bklit-ui way: stage and commit with pre-commit hooks, run ultracite from the repo root, rebuild the shadcn registry, run a production test build, fix failures, push, and create a PR with a structured summary. Use when the user asks to commit, push, open a PR, "ship it", or run the full pre-PR checklist.
Use this skill when hardening a RevenueCat integration on Android. Covers Trusted Entitlements response verification (INFORMATIONAL vs ENFORCED), why the server is always the authority, API key hygiene (public SDK key vs secret REST key), anonymous user identity, and purchase token protections RevenueCat provides automatically.
Use Prisma Next with a Supabase project via `@prisma-next/extension-supabase` — wire `extensions: [supabasePack]`, declare cross-space FKs to `supabase:auth.AuthUser`, author RLS policies (`policy_select` / `policy_update` / `@@rls`, `auth.uid()` predicates), build `db.ts` with the `supabase()` factory, bind roles per request (`asUser(jwt)` / `asAnon()` / `asServiceRole()`), query `auth.*` / `storage.*` via the `db.asServiceRole().supabase` admin root, and validate JWTs (`jwksUrl` for current projects / `jwtSecret` for legacy HS256). Use for supabase, RLS, row level security, policy, role binding, anon, authenticated, service_role, auth.users, auth.uid(), JWT, JWKS, SUPABASE_JWKS_URL, SUPABASE_JWT_SECRET, SUPABASE.JWT_INVALID, SUPABASE.CONFIG_INVALID, RoleBoundDb, session pooler, supabase:auth.AuthUser, @prisma-next/extension-supabase.
Python best practices for writing production-grade code. This skill should be used when writing, reviewing, or refactoring Python code. Triggers on tasks involving Python development, error handling patterns, dictionary operations, and code quality improvements.
A comprehensive guide to implementing Syncfusion React dropdown components, including AutoComplete, ComboBox, DropDownList, ListBox, Mention, MultiSelect, and MultiColumn ComboBox. Use when building selection interfaces, data binding, filtering, cascading dropdowns, custom templates, and accessible dropdown experiences in React applications.
Implement, fix, review, migrate, test, or debug Drift persistence in Flutter apps using SQLite, drift_flutter, type-safe Dart queries, generated tables, StreamBuilder or Riverpod StreamProvider UI, write operations, transactions, schema migrations, web assets, isolate sharing, and local database testing. Use when a Flutter task mentions drift, local database storage, SQLite, reactive database streams, CRUD, schemaVersion, build_runner, drift_dev make-migrations, migration tests, or Flutter-specific database setup across mobile, web, or desktop.
GCC embedded project build tool (CMake + arm-none-eabi-gcc) for scanning CMake-based embedded projects, listing presets, configuring, building, rebuilding, cleaning, and analyzing ELF size. It triggers automatically when the user mentions GCC, arm-none-eabi, CMake embedded builds, Ninja builds, ELF size analysis, arm-gcc, cross-compilation, cmake --build, or cmake --preset, and also supports explicit /gcc invocation. Even if the user only says "compile it" or "see how big the firmware is", this skill should trigger as long as the context involves a CMake embedded GCC project.
Best practices for building and deploying Netlify sites, covering serverless and edge functions, Netlify Blobs storage, the Image CDN, and build configuration. Use when writing Netlify Functions or Edge Functions, configuring netlify.toml or redirects/headers, managing environment variables across deploy contexts, working with Netlify Blobs, or setting up local development and deploy previews.
Blockbench plugin/extension development for the 3D modeling tool. Use when creating, modifying, or debugging JavaScript plugins for Blockbench, including actions, dialogs, panels, menus, toolbars, model manipulation, animation APIs, and custom formats/codecs. Triggers on Blockbench plugin, Blockbench extension, Blockbench API, BBPlugin, model editor plugin, or 3D modeling tool extension.
GNU Make skill for C/C++ build systems. Use when writing or debugging Makefiles, understanding pattern rules and automatic dependency generation, managing CFLAGS/LDFLAGS, converting ad-hoc compile commands into maintainable Makefiles, or diagnosing incremental build issues. Activates on queries about Makefiles, make targets, pattern rules, phony targets, dependency tracking, recursive make, or make errors.
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.