Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
This skill should be used when the user asks about Bootstrap helpers, Bootstrap clearfix, Bootstrap color and background helpers, Bootstrap colored links, Bootstrap focus ring, Bootstrap icon link, Bootstrap position helpers, Bootstrap ratio helpers, Bootstrap stacks, Bootstrap stretched link, Bootstrap text truncation, Bootstrap vertical rule, Bootstrap visually hidden, or needs help with Bootstrap helper classes.
Use when an idea, problem, or possible solution is not formed enough to begin architect. Explores the problem and alternative approaches, challenges assumptions during convergence, and can produce an optional architect-seed.md handoff for a later architect session. Do NOT use once the change is ready for architectural decisions — use architect directly.
Browserbase cloud-headless-browser SDK expertise for TypeScript/Node. Use when code imports `@browserbasehq/sdk`, `@browserbasehq/stagehand`, `playwright-core`, or `puppeteer-core` and connects to Browserbase; when code POSTs to `api.browserbase.com/v1/sessions`, `/v1/contexts`, `/v1/extensions`, or `/v1/projects`; when sending the `x-bb-api-key` header or using `BROWSERBASE_API_KEY`/`BROWSERBASE_PROJECT_ID`; when the user asks about Browserbase sessions, contexts, proxies, downloads, uploads, recordings, live debugger URL, captcha solving, advanced stealth, verified browsers, fingerprinting, BYOS S3 storage, regions (`us-west-2`/`us-east-1`/`eu-central-1`/`ap-southeast-1`), keepAlive, the `connectUrl` CDP WebSocket, `chromium.connectOverCDP`, `puppeteer.connect({browserWSEndpoint})`, the `browser.contexts()[0]` default-context pattern, Stagehand `act`/`extract`/`observe`/`agent` primitives, the Model Gateway, or deploying serverless via Browserbase Functions.
Control camera behavior in Decentraland scenes. CameraMode detection, CameraModeArea (force first/third person in regions), VirtualCamera (cinematic scripted cameras), MainCamera (read position/rotation), and camera-triggered events. Use when the user wants camera control, cutscenes, cinematic views, forced camera modes, or camera tracking. Do NOT use for input restriction during cutscenes (see advanced-input for InputModifier).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Create a comprehensive checkpoint commit with detailed analysis of all changes. Use this skill when the user says "checkpoint", "commit everything", "save my progress", "create a commit", or wants to stage and commit all current changes with a well-crafted message. Also use when the user says "/checkpoint" or asks to snapshot current work. This skill stages all changes and creates a descriptive commit — it does not push.
Analyze a provided resource through a Circuit lens. Use when the user provides or points to an article, pasted conversation, X thread, workflow example, GitHub repo, local codebase, product page, paper, or other outside reference and asks what Circuit can learn from it, whether it suggests a possible Circuit flow, whether Circuit can support the workflow today, what product or block changes would be needed, or whether the analysis should be added to Circuit's ideas or flow backlog.
Integrates Clerk authentication in React/Vite, Next.js App Router, and Cloudflare Workers apps. Covers ClerkProvider setup, clerkMiddleware and createRouteMatcher for protected routes, token verification with @clerk/backend verifyToken, custom JWT templates and session claims (user.public_metadata, org_id, org_role) for RBAC, Hono integration via @hono/clerk-auth, shadcn/ui auth components, and Playwright E2E testing with @clerk/testing, +clerk_test emails and the 424242 OTP. Documents 11 pitfalls: Missing Clerk Secret Key, JWKS cache races, missing authorizedParties CSRF risk, Core 2 import path changes, JWT size limits, ClerkProvider cannot be used as a JSX component, async auth() confusion, and Vite dev 431 header errors. Use when adding Clerk to a project, protecting routes, verifying tokens, shaping JWT claims, testing auth flows, or debugging Clerk authentication errors.
Build, review, debug, configure, migrate, teach, or plan ClickHouse analytics work from TypeScript with current docs and a full usage guide. Use for @clickhouse/client, @clickhouse/client-web, createClient, query, insert, command, exec, JSONEachRow, query_params, streaming, MergeTree family, ORDER BY/PARTITION BY, materialized views, projections, async_insert, FINAL, lightweight deletes and updates, 26.x server upgrades, ClickHouse Cloud HTTPS, system.query_log, and TS schema/ingest patterns. TypeScript/Node SDKs only — not Python/Go/Java clients.
(NS) Harness-aware autonomous execution engine — self-decides planning depth, resolves doubts against docs/context and docs/specs before escalating, dispatches multi-agent implementation in an isolated worktree. Use as the standalone entry point for a local plan file, a pasted execution plan, or an ad-hoc "run this autonomously" request with no GitLab issue involved. Also acts as the Phase 2 execution engine when invoked by execution-gitlab-issue — do not run the standalone pipeline in that case. Not for simple single-step edits (use code-coder) and not for GitLab issues directly (use execution-gitlab-issue, which calls this skill internally).
Reviews Node.js runtime behavior in JavaScript or TypeScript, including server entrypoints, route handlers, middleware, streams, processes, dependencies, and environment configuration. Loads alongside language and CLI checks when applicable; investigates blocking I/O, backpressure, injection, lifecycle leaks, and misleading failure signals.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
Pure CSS functional feedback effects for form inputs, buttons, loading states and text links. Triggered by :focus, :active, and state changes — not hover. Auto-matches intensity to the existing design style. Zero JS, zero dependencies, no SSR issues. Sourced from cssfx (6.1k ★).
World-class database schema design - data modeling, migrations, relationships, and the battle scars from scaling databases that store billions of rowsUse when "database schema, data model, migration, prisma schema, drizzle schema, create table, add column, foreign key, primary key, uuid, auto increment, soft delete, normalization, denormalization, one to many, many to many, junction table, polymorphic, enum type, index strategy, database, schema, migration, data-model, prisma, drizzle, typeorm, postgresql, mysql, sqlite" mentioned
Use when adding local data persistence to a Python project — caching, relational storage (simple, complex/OLTP, or analytical/OLAP), document storage, full-text search, vector/embedding search, background job queues, cron/scheduled tasks, pub/sub/event streaming, graph data, blob storage, or time-series data — and no explicit \"evaluate the best DB for this\" request was made. Gives the default technology per category, chosen for permissive licensing, pytest-local testability with no docker/cloud, and low-boilerplate LLM-agent-friendly APIs, so picks stay consistent across projects instead of drifting session to session.
Domain-driven design (DDD) modeling and architecture guidance. Used to create domain models, design bounded contexts, and implement aggregate roots, entities, value objects, domain services and domain events. Supports strategic design (context mapping, subdomain decomposition) and tactical design (aggregates, repositories, factory patterns). Use when the user needs domain modeling, microservice decomposition or complex business logic design.
Designing Data-Intensive Applications (DDIA) distilled reference guide by Martin Kleppmann. MUST be loaded when: designing database schemas, choosing storage engines, implementing replication or partitioning, handling distributed transactions, building batch/stream processing pipelines, choosing consistency models, implementing consensus, designing data flow architectures, evaluating trade-offs between availability and consistency, encoding/serialization decisions, data modeling (relational vs document vs graph), building fault-tolerant systems, or any system design and architecture discussion involving data-intensive applications. Trigger on: database design, replication, partitioning, sharding, transactions, isolation levels, consistency, consensus, CAP theorem, batch processing, stream processing, MapReduce, Kafka, event sourcing, CDC, OLTP, OLAP, B-tree, LSM-tree, data warehouse, schema evolution, encoding formats, distributed systems, fault tolerance, leader election, quorum.
Systematic debugging methodology, language-specific debuggers, and common scenario playbooks. Use for: debug, debugging, bug, crash, hang, memory leak, race condition, deadlock, bisect, reproduce, root cause, breakpoint, profiling, performance issue, segfault, stack trace, core dump.
Debug React Native issues systematically. Use when encountering native module errors like "Native module cannot be null", Metro bundler issues including port conflicts and cache corruption, platform-specific build failures for iOS CocoaPods or Android Gradle, bridge communication problems, Hermes engine bytecode compilation failures, red screen fatal errors, or New Architecture migration issues with TurboModules and Fabric renderer.
Debug TensorFlow and Keras issues systematically. This skill helps diagnose and resolve machine learning problems including tensor shape mismatches, GPU/CUDA detection failures, out-of-memory errors, NaN/Inf values in loss functions, vanishing/exploding gradients, SavedModel loading errors, and data pipeline bottlenecks. Provides tf.debugging assertions, TensorBoard profiling, eager execution debugging, and version compatibility guidance.
Reviews proposed or existing work for unnecessary complexity and triages complexity-increasing recommendations without editing the reviewed targets. Use this skill when asked to simplify or decomplex source, tests, configuration, dependencies, plans, designs, or architecture; challenge over-engineering; audit unnecessary complexity; or triage recommendations that would add complexity. Do not use for general defect review, implementation or fixes, style-only cleanup, or conceptual explanations that need no durable review report.
Structured research → plan → annotate → implement workflow for non-trivial features. Separates planning from execution using persistent markdown artifacts (.claude/research.md, .claude/plan.md). Use when explicitly invoked via /deep-plan for feature development, refactors, migrations, or any multi-file change where architecture decisions matter.
Delivers a clear goal until done — an app, a feature, or a fix. Plans a living goal.md under goals/ as an ordered list of phases the user confirms, then loops one phase-deliverer subagent per phase: load the skills the phase needs, write phase.md plus ≤7 task files (sources, steps, verification), implement each task with a commit, and adjust the remaining phases from its findings. Halts when a task is blocked or the goal's checks pass. Use only when the user names this skill (`/delivering-goal`, `$delivering-goal`, or "delivering-goal"), or references a file under a marked goals root (`@goals/01-mvp/goal.md`, a phase or task file)
Use when the user asks to update, bump, or migrate Java, Kotlin, Gradle, Maven, Node, or TypeScript dependencies; audit direct or transitive dependencies for CVEs or security advisories; or remediate a dependency vulnerability. Preserves the package manager, applies small verified upgrades, and checks vulnerability, release-age, and supply-chain risk.
Deploy a Decentraland scene to Genesis City (LAND-based). Covers pre-deployment checklist, scene.json validation, spawn points, and common deployment errors. Use when the user wants to deploy, publish, go live, or upload to parcels they own. Do NOT use for Worlds deployment (see deploy-worlds).
Design an API end-to-end — from requirements to a validated OpenAPI spec. Generates stories for review, then produces a linted spec. Emmanuel Paraskakis's method for designing APIs with LLMs. Use when user says "/design-api" or asks to design an API from requirements or stories. For a single step only, use `design-api-stories`, `design-api-spec`, or `design-api-review` instead.
Resume work from a previous session checkpoint. Uses the `resume-context` CLI to load feature, checkpoint, git state, and session history in a single call, then synthesizes a focused resumption summary before continuing. Use at the start of a new session to restore context from a previous checkpoint.
A skill that analyzes existing code (not necessarily DDD-based) and proposes a domain model (aggregates, local entities, value objects, domain services) with pseudocode. It proposes a design including properties, methods, invariants, and aggregate boundaries. Target languages: language-agnostic. Triggers: requests for existing-code analysis and domain-model extraction such as "extract a domain model from this existing code", "I want to redesign this code with DDD", "propose a domain model", "I want to find aggregates", "I want to migrate to DDD", "analyze the existing code and create a domain model", "turn legacy code into DDD".
Implement Rails nested attributes with dynamic add/remove functionality using Turbo Streams and Simple Form. Use when building forms where users need to manage multiple child records (has_many associations), add/remove nested items without page refresh, or create bulk records inline.
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.