Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Finalizes a hotfix and merges it into main and develop using git-flow, then prunes stale branches and worktrees. This skill should be used when the user asks to "finish a hotfix", "merge hotfix branch", "complete hotfix", "git flow hotfix finish", or wants to finalize a hotfix.
Triage and fix failing Buildkite CI checks for RisingWave pull requests by extracting concrete failing tests, diffs, and error messages from Buildkite build/job logs and artifacts, then applying focused code or test fixes. Use when users ask to diagnose red Buildkite checks, investigate flaky/failing CI jobs, understand why a Buildkite build failed, or provide Buildkite/GitHub check URLs and want a concrete fix.
Provides general domain knowledge about the Flare network—what it is, its core protocols (FTSO, FDC, FAssets, Smart Accounts, FCC/TEE), networks (Mainnet, Coston2, Songbird, Coston), RPC endpoints, block explorers, faucets, chain IDs, native tokens, consensus, and developer tooling. Use when answering general Flare questions, helping developers get started, or when no more specific Flare skill applies.
Guide users to build charts and data visualizations using the Graphic Flutter library. Use when users ask how to create charts, configure chart options, add interactivity, customize appearance, or need help with any aspect of the Graphic charting library.
Receive and verify Google Gemini API webhooks. Use when setting up Gemini webhook handlers for batch jobs, video generation, or Interactions API function-calling LROs, debugging signature verification, or handling events like batch.succeeded, batch.failed, video.generated, or interaction.completed.
Use when performing a GitHub operation programmatically — creating an issue or pull request, managing repos, releases, labels, Actions runs, Projects, secrets, or any github.com task — preferring the `gh` CLI and falling back to `gh api` (REST) or `gh api graphql` only where no command exists. Every call is authenticated per-invocation with `GH_TOKEN`; it never runs `gh auth switch` and never prints the token. Uses `gh`'s high-level commands (which also encrypt secrets client-side) for coverage and ergonomics; for the REST long tail it builds a `gh api` call from a bundled OpenAPI spec via an endpoint index + a `$ref`-resolver. github.com Cloud; consumes caller-injected credentials (host + a token resolved by variable name) — it does not provision or resolve them.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
GitHub Projects management via gh CLI for creating projects, managing items, fields, and workflows. Use when working with GitHub Projects (v2), adding issues/PRs to projects, creating custom fields, tracking project items, or automating project workflows. Triggers on gh project, project board, kanban, GitHub project, project items.
Safe refactoring workflow for Go: behavior-preserving steps, compiler-checked renames, extracting packages, breaking circular dependencies, and strangler migrations — always behind green tests. Use when: "refactor this", "rename across the codebase", "extract a package", "break this circular dependency", "split this god package", "migrate callers", "clean up without changing behavior". Not for: choosing the target architecture (go-architecture-review), adopting new language features (go-modernize), performance rewrites (go-performance-review).
Receive and verify Hugging Face webhooks. Use when setting up Hugging Face webhook handlers, debugging X-Webhook-Secret verification, or handling events on models, datasets, and Spaces — repo updates, new commits and tags (repo.content), config changes (repo.config), discussions, Pull Requests, and discussion comments.
Use when writing Python code that imports from `inkbox`, uses `pip install inkbox`, or when adding email, mailbox imports, phone, text/SMS, iMessage, A2A task/message history, contacts, notes, contact rules, vault, tunnels, mailbox storage, mail clients (IMAP/SMTP), or agent identity features using the Inkbox Python SDK.
Receive and verify Intercom webhooks. Use when setting up Intercom webhook handlers, debugging X-Hub-Signature verification, or handling customer messaging events like conversation.user.created, conversation.admin.replied, contact.user.created, or ticket.created.
Expert Laravel developer specializing in Laravel 11+, Octane, Livewire 3, and PHP 8.3 features. Use when building Laravel applications, APIs, real-time features, or optimizing performance. Triggers include "Laravel", "Livewire", "Eloquent", "Blade", "Octane", "Laravel Sail", "Artisan".
Orchestrates the entire E2E Looker developer onboarding journey. This is the MUST-READ parent skill that coordinates the overall process. Start here when beginning a new Looker setup. It guides you to act as an informative, transparent guide, leading the user in sequence through: Pre-flight, Discovery, CLI, Auth, Connect, Project, Model, Dashboard.
Diagnoses TCC denials, Local Network access issues, and stuck Keychain dialogs: Full Disk Access, Screen Recording, Microphone, Camera, Accessibility, and Automation. Use for repeated prompts, background-only LaunchAgent/uv failures, broken grants, or FDA automation (权限弹窗 / 授权了没用 / 完全磁盘访问 / 本地网络权限). Checks requester and grants first. Not for launchd design (macos-watchdog) or app permission UX (developing-ios-apps).
This skill should be used whenever the agent creates, edits, reviews, or debugs any web UI such as pages, components, layouts, sections, forms, navs, cards, tables, or modals. It guarantees the output is mobile-friendly and responsive across the full range of devices (small phones at 320px through large desktops), prevents horizontal overflow, and makes the result look intentional and beautiful rather than merely "not broken". It also enforces visual consistency: new UI must match the spacing, type, breakpoints, and component patterns already in the project, and remain coherent with components added later. Trigger on phrases like "make this responsive", "mobile friendly", "works on phones", "fix the layout on mobile", "it's overflowing", "looks broken on small screens", or any request to build/style web UI where no responsive behavior was specified. Use it proactively whenever generating new web markup.
Deploy trained machine learning models as production-ready services using REST APIs, containers, serverless functions, and orchestration platforms. Use when the user requests model deployment or provides relevant inputs for this workflow.
Builds Nango Functions (TypeScript createAction/createSync) with checkpoint-first sync patterns, action and sync references, project/root checks, deletion strategies, and a docs-aligned dryrun/test workflow. Use when creating or updating Nango actions or syncs.
Next.js 16 App Router performance optimization guidelines (formerly nextjs-16-app-router). This skill should be used when writing Next.js 16 code, configuring caching, implementing Server Components in Next.js, setting up App Router routing, or configuring next.config.js. This skill does NOT cover generic React 19 patterns (use react-19 skill) or non-Next.js server rendering.
Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.
Use when deciding which documents a software or product project needs to produce — classifies across 10 dimensions, identifies product capability areas (4-signal algorithm), and produces a proportional, capability-scoped manifest with all five sections populated (documents, roles, skills, tools, capabilities). Re-tailors when the project changes (amend). Covers the full SDLC universe (seven lifecycle bands + four domain overlays). Returns a three-key JSON payload; caller writes two files from it (capability-map.yaml + manifest.yaml) — never assumes scope_root. Discovery only: decides which documents and what it takes to produce them, not how to author them. Keywords: document discovery, documentation plan, SDLC documents, document manifest, capability map, proportional docs, manifest completeness.
Set up and maintain a structured project memory system in docs/project_notes/ that tracks bugs with solutions, architectural decisions, key project facts, and work history. Use this skill when asked to "set up project memory", "track our decisions", "log a bug fix", "update project memory", or "initialize memory system". Configures both CLAUDE.md and AGENTS.md to maintain memory awareness across different AI coding tools.
Comprehensive R package for command-line interface styling, semantic messaging, and user communication. Use this skill when working with R code that needs to: (1) format console output with inline markup and colors, (2) display errors, warnings, or messages with cli_abort/cli_warn/cli_inform, (3) show progress indicators for long-running operations, (4) create semantic CLI elements (headers, lists, alerts, code blocks), (5) apply themes and customize output styling, (6) handle pluralization in user-facing text, (7) work with ANSI strings, hyperlinks, or custom containers. Also use when migrating from base R message/warning/stop, debugging cli code, or improving existing cli usage.
Resolve an in-progress git conflict without a silent drop. Use when the worktree is mid-merge, mid-rebase, mid-cherry-pick or mid-stash-pop: `CONFLICT (content)`, `<<<<<<<` markers, `Unmerged paths`, or `fix conflicts and then commit the result`.
Use Riverpod code generation (@riverpod, riverpod_generator) and hooks (hooks_riverpod, HookConsumerWidget, flutter_hooks with Riverpod). Use when the user asks about @riverpod, code generation, riverpod_generator, when to use codegen, or using flutter_hooks with Riverpod (HookConsumerWidget, HookConsumer).
Rust language patterns and ecosystem covering ownership, borrowing, lifetimes, error handling (Result/Option, thiserror, anyhow), async with Tokio, traits, generics, serde serialization, Cargo workspaces, and testing. Includes axum web framework, ratatui terminal UI, clap CLI parsing, criterion benchmarking, cargo-deny supply chain security, cargo-dist binary distribution, and release-plz changelog automation. Use when writing Rust code, designing ownership models, building async services with Tokio/axum, creating terminal UIs with ratatui, setting up CLI applications with clap, configuring CI/CD pipelines for Rust, benchmarking with criterion, auditing dependencies with cargo-deny, or distributing binaries with cargo-dist.
Receive and verify Scrapfly webhooks. Use when setting up Scrapfly webhook handlers for async scrape, extraction, screenshot, or crawler jobs, debugging X-Scrapfly-Webhook-Signature verification, or routing on X-Scrapfly-Webhook-Resource-Type.
UI components with shadcn-svelte and bits-ui. Component patterns, trigger snippets, dialog handling, and accessibility. Keywords: shadcn-svelte, bits-ui, Button, Dialog, Sheet, Popover, DropdownMenu, Tooltip, Form, Input, Select, child snippet, trigger pattern, cn utility
Procedural noise functions in GLSL—Perlin, simplex, Worley/cellular, value noise, FBM (Fractal Brownian Motion), turbulence, and domain warping. Use when creating organic textures, terrain, clouds, water, fire, or any natural-looking procedural patterns.
System architecture guidance for Python/React full-stack projects. Use during the design phase when making architectural decisions — component boundaries, service layer design, data flow patterns, database schema planning, and technology trade-off analysis. Covers FastAPI layer architecture (Routes/Services/Repositories/Models), React component hierarchy, state management, and cross-cutting concerns (auth, errors, logging). Produces architecture documents and ADRs. Does NOT cover implementation (use python-backend-expert or react-frontend-expert) or API contract design (use api-design-patterns).
TanStack Pacer for rate limiting, throttling, debouncing, and async queuing. Use when controlling execution frequency, managing API rate limits, debouncing user input, or queuing async tasks. Use for pacer, throttle, debounce, rate-limit, queue, async-throttle, rate-limiting.
Expert technical advisor with deep reasoning for architecture decisions, code analysis, and engineering guidance. Masters complex tradeoffs, system design, security architecture, performance optimization, and engineering best practices. Use when making critical architecture decisions, after implementing significant work, when debugging complex issues, encountering unfamiliar patterns, facing security/performance concerns, or evaluating multi-system tradeoffs. Provides comprehensive analysis with clear recommendations and rationale.
Implement stable, scalable directional-shadow systems for Three.js. Use for large procedural worlds, city scenes, terrain, moving cameras, WebGPU/TSL shadow nodes, cascades, cached clipmaps, texel stabilization, update budgets, and targeted invalidation.
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.