Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Runs a second-pass cleanup over AI-written code using the repo's style guide in style.md. Prefers parallel subagents to simplify recently modified files without changing behavior. Use when the user says "deslop", "clean this up", "make this less AI", "apply my style guide", "second pass", or asks to simplify generated code after implementation
Use this skill whenever the user asks to build, create, design, redesign, polish, audit, animate, improve, fix, or "make prettier/cleaner/nicer" ANY frontend interface — landing pages, dashboards, portfolios, SaaS apps, marketing sites, components, hero sections, navbars, footers, pricing tables, posters, mobile UIs, or any web/React/Next.js/Vue/Svelte UI work. Also use when the user mentions Tailwind, shadcn, Framer Motion, 21st.dev, React Bits, animations, typography, color palettes, design taste, "make it look premium," "fix the look," or "make this less generic." Enforces production-grade design discipline (typography, color, motion, layout, accessibility, copy) and bans generic AI aesthetics like Inter font, purple-to-blue gradients, three-card feature rows, h-screen heroes, John Doe placeholder data, and "elevate/seamless/unleash" filler copy. Generates a project DESIGN.md to lock in tokens across sessions. Consolidates rules from UI/UX Pro Max, Framer Motion, 21st.dev Magic, React Bits, Anthropic frontend-design, Impeccable, and design-taste-frontend.
SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this variant) — prefer that skill unless you explicitly want this one. Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy terms, stress-testing with concrete scenarios, cross-referencing code, and updating CONTEXT.md + ADRs inline as decisions crystallise. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-with-docs-codex", "grill me against the docs then have codex review", "stress-test this against our domain model then get a second model on it", or is about to build something high-stakes in a project with established terminology/ADRs and wants alignment, documentation, AND a cross-model sanity check. Builds on Matt Pocock's grill-with-docs (MIT). NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes
Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints. Use when the user asks "why do I have so many TypeError issues that look the same?", "merge these duplicates", "stop splitting this error into new issues", or wants to clean up fingerprint sprawl. Decides between a one-shot merge of existing issues and a durable grouping rule that keeps future events from creating new fingerprints. Does NOT group conceptually similar bugs across different runtimes, SDKs, or call sites.
Upgrades Meta VR apps to newer Horizon OS SDK versions with migration guides, deprecated API replacements, and changelogs. Use when updating SDK versions or fixing deprecated API warnings. Build paths: all Meta VR app stacks; use hz-quest-verify-first if the build path is unclear.
Apply Justin's detailed Git and pull-request workflow. Use when planning or performing branches, commits, rebases, history cleanup, pushes, pull requests, or GitHub work. Do not use for read-only Git inspection or when a repository's own workflow documentation already covers the task.
Style Swift code for JWW projects. Use when generating, editing, or reviewing application, package, extension, or test code that must match Justin's conventions; do not use for non-Swift work or as a substitute for platform-specific implementation skills
Post a comment (or a formal PR review) to a GitHub issue or pull request in mariadb-operator/mariadb-operator. Use whenever the user wants to publish something to GitHub for this repo — "comment on issue #123", "post this as a PR comment", "leave a note on #456", "reply on the PR" — and especially when they want the output of the mariadb-operator-pr-review skill delivered to GitHub instead of just shown in chat, e.g. "review PR #1234 and post it as a comment" or "post the review results to the PR". Always confirms the exact comment text with the user before publishing — never posts autonomously.
Guide developers through creating and updating MCP Apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a MCP App, MCP server or use the Skybridge framework.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Pino high-performance JSON logger for Node.js with worker thread transports, child loggers, redaction, and framework integrations. Use when setting up structured logging, configuring log transports, adding request correlation IDs, redacting sensitive data, or integrating with Fastify, Hono, or Express. Use for pino, logging, structured-logs, request-id, correlation, redaction, transports, pino-http, pino-pretty.
Safely manage Proxyman certificates and destructive recovery workflows on macOS. Use for generated or custom root certificates, custom server or client certificates, Copy Debug Info, Debug Mode, Reset Network Proxy, or Factory Reset. Do not use for ordinary display preferences or device-specific CA setup.
Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task lists from UI designs, (3) Batch analyzing multiple app screens, (4) Conducting competitive analysis from visual references.
Implementar e revisar aplicações Next.js com App Router, Server e Client Components, data fetching, cache, mutations, routing, metadata, segurança e deploy. Use quando houver dependência next ou next.config e a tarefa tocar rota, layout, Server Action, cache ou runtime; use também para decidir a fronteira server/client; não use para lógica de estado/efeito React independente de framework — aí use a skill React; confirme sempre o router (App ou Pages) e a versão antes de recomendar, pois cache e defaults mudam entre gerações.
Interactive discovery and implementation workflow that gathers requirements through picker-based questions (intent, scope, constraints, preferences), scans the codebase for what it can already infer, then writes an AWS architectural scaffold and implementation directly into the project. Use when the user wants to build a new app, scaffold a project, or expand/refactor an existing one on AWS — anything that calls for a structured discovery flow followed by code changes, not a one-off lookup. Do not use for: factual lookups about AWS Activate / programs / credits, requests for a single copy-paste prompt, non-AWS architectural work, architecture advice/recommendations without code changes (see architect-for-startups), a new idea centered on an AI agent — runtime selection, agentic architecture, or an agent POC (see agent-advisor), or migrating an existing GCP/Azure/Heroku workload or an LLM SDK rewrite (see gcp-to-aws / azure-to-aws / heroku-to-aws / llm-to-bedrock).
Create PostHog error tracking suppression rules to drop high-volume, low-value errors at ingestion. Use when the user asks "stop capturing this error", "drop browser extension errors", "ignore ResizeObserver loops", "suppress bot-driven errors", or wants to reduce ingestion cost from noisy unactionable errors. Identifies suppression candidates, scopes the filter tightly, decides between full suppression and sampling, and confirms the rule before creating it. Suppressed errors are dropped permanently — this skill defaults to caution.
Implements and configures the Syncfusion .NET MAUI AI-Powered Smart Text Editor (SfSmartTextEditor). Use when working with SfSmartTextEditor, AI-powered text input, predictive text suggestions, inline or popup suggestions, or UserRole/UserPhrases configurations. Covers suggestion display modes, custom AI services (Claude, DeepSeek, Gemini, Groq), Azure OpenAI integration, and customization options.
This skill provides comprehensive documentation for all 23 Vercel AI Elements components organized by category (Message, Conversation, Input/Interaction, Content Display, AI Processing, Advanced Features). Use when users ask about building AI chatbots, need component documentation, want API references for Vercel AI Elements, or need integration examples with the AI SDK.
Use when you need to create a new Maven-based Quarkus 3.x project using SDKMAN-managed Java and Quarkus CLI tooling. This should trigger for requests such as Create a Quarkus Maven project; Bootstrap Quarkus project with SDKMAN; Generate a new Quarkus service; Create Quarkus 3 Maven project; Scaffold Quarkus service with Java 25. Part of Plinth Toolkit
C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagent_desktop_ffi.{dylib,so,dll} and call `ad_*` functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: ad_init → ad_adapter_create[_with_session] → ad_snapshot → read qualified refs (@s8f3k2p9:e5) → ad_execute_by_ref → ad_free_string → ad_adapter_destroy.
Use when the user needs to design or evaluate system architecture—service boundaries, data models, API contracts, infrastructure topology, database selection, or dependency analysis. Also activate for “design the system,” “how should I architect this,” “monolith vs microservices,” or architecture decision records.
Use when you see 'actor-isolated', 'Sendable', 'data race', '@MainActor' errors, or when asking 'how do I use async/await', 'my app crashes with concurrency errors', or 'how do I fix data races'. Covers Swift 6 concurrency, @concurrent, and actors.
Load this skill when you are required to check source code outside of this codebase, or users give you a GitHub repo spec follows <owner-name>/<repo-name> spec. Use it when the current directory is not the target project, when another local project is needed, or when multiple projects are involved.
Reviews Go code for idiomatic patterns, error handling, concurrency safety, and common mistakes. Use when reviewing .go files, checking error handling, goroutine usage, or interface design. Covers generics (Go 1.18+), errors.Join and slog (Go 1.21+), and Go 1.22 loop variable semantics
Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.
HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.
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.