Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Feature specification and planning guidelines for software engineers. Use when writing PRDs, defining requirements, managing scope, prioritizing features, or handling change requests. Triggers on tasks involving feature planning, specification writing, stakeholder alignment, or scope management
Expert blueprint for scene loading, transitions, async (background) loading, instance management, and caching. Covers fade transitions, loading screens, dynamic spawning, and scene persistence. Use when implementing level changes OR dynamic content loading. Keywords scene, loading, transition, async, ResourceLoader, change_scene, preload, PackedScene, fade
How to design and build modern, premium-quality frontend interfaces that look like high-end SaaS products, modern AI tools, and award-winning design websites — not generic templates. Use this skill whenever the user asks to build a frontend, create a landing page, design a dashboard, scaffold a web app UI, build a SaaS interface, create a portfolio site, or produce any user-facing web interface. Also use when the user says "make it look modern", "build me a beautiful UI", "create a homepage", "design a pricing page", "add animations", "make it cinematic", "add liquid glass", "add scroll animations", "use 2026 design trends", or mentions frontend design, UI/UX, component architecture, motion design, hero sections, responsive layouts, or CSS animation.
Classic three.js materials (non-Node): MeshStandardMaterial, MeshPhysicalMaterial, Phong/Lambert/Toon/Basic, Line/Points/Sprite materials, MeshMatcapMaterial, MeshNormalMaterial, depth/distance materials, ShaderMaterial and RawShaderMaterial. Use when tuning PBR maps, transparency, depth write, skinning flags, or writing GLSL in ShaderMaterial; for TSL/NodeMaterial/WebGPU shader graphs use threejs-node-tsl instead—not both for the same authoring path unless migrating.
Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize software structure, create C4 diagrams, or generate context/container/component/deployment diagrams. Triggers include “architecture diagram”, “C4 diagram”, “system context”, “container diagram”, “component diagram”, “deployment diagram”, “document architecture”, “visualize architecture”.
Type-safe ORM for Cloudflare D1 databases using Drizzle. Use when: building D1 database schemas, writing type-safe SQL queries, managing migrations with Drizzle Kit, defining table relations, implementing prepared statements, using D1 batch API, or encountering D1_ERROR, transaction errors, foreign key constraint failures, or schema inference issues.
Build a burning-paper ring loader whose GLSL flame is drawn by a Worker on an OffscreenCanvas started from the head, so a main thread blocked by the page build cannot freeze it, with a progress count, an even-paced run into the hand-off, and a clean fade to the page. Covers the ember thread and ember gradient, porous char, worker start-up, parallel shader compile with a waited 1-px warm-up draw, hand-off without a stall, reduced motion and hidden-tab behaviour. Use for a loading screen, preloader, page loader, splash, "kindling", burn loader, ember ring, burning paper hole, fire loader, or a loader that must keep moving while heavy JavaScript, three.js or shader builds hold the main thread.
SwiftUI interface implementation patterns aligned with the iOS 26 / Swift 6.2 clinic modular MVVM-C architecture, grounded in Creative Selection and Design Like Apple principles. Use when building new SwiftUI views/screens while respecting Domain/Data boundaries, App-target route-shell navigation, and production-grade accessibility/interaction standards
Converts architecture descriptions, module specifications, or workflow documents into Mermaid diagrams. Use to visualize brick module relationships, workflows (DDD, investigation), or system architecture. Supports flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams, and Gantt charts. Generates valid Mermaid syntax for embedding in Markdown documents.
Guides coding agents in using the 8090 Software Factory MCP and executing Work Orders reliably and traceably in a repository—covering requirements, blueprints, work orders, implementation plans, review, and verification. Read this skill first, then follow the relevant execution process.
Use SurrealKit, SurrealDB's schema-management and migration CLI, to scaffold projects from templates, sync schema in development, plan and execute production rollouts (with rollback), statically check SurrealQL without a database, generate JSON/TypeScript types, and write declarative TOML test suites for schemas, permissions, and API endpoints. Use this skill whenever users set up, migrate, type, check, or test a SurrealDB schema with SurrealKit.
three.js keyframe animation system: AnimationMixer, AnimationClip, AnimationAction, KeyframeTrack variants, PropertyBinding, PropertyMixer, AnimationObjectGroup, AnimationUtils; mixing and crossfading clips, loop modes, timeScale, weight; addon AnimationClipCreator and CCDIKSolver for procedural rigs. Use when playing glTF clips, blending actions, or authoring procedural tracks; for skin deformation rigging on meshes see threejs-objects; for math interpolants without clips see threejs-math only when not tied to AnimationMixer.
Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like—rerunning it against local code, viewing a concise diff of the old and new output, and looping (change code → replay → diff) until satisfied. Invoked as /agent-observability-replay-trace <trace-id> [changes to test]. Signals: "replay this trace"; "iterate on a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; or pasting a trace ID from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, reruns the app to emit a new trace, and diffs the two—no local server or browser. For Agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser "Replay" button (that's agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.
Build integrations with Google Workspace APIs (Gmail, Calendar, Drive, Sheets, Docs, Chat, Meet, Forms, Tasks, Admin SDK). Covers OAuth 2.0, service accounts, rate limits, batch operations, and Cloudflare Workers patterns. Use when building MCP servers, automation tools, or integrations with any Google Workspace API, or troubleshooting OAuth errors, rate limit 429 errors, scope issues, or API-specific gotchas.
Delegate a coding task to Muse Code (`muse`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Muse — phrasings like "have Muse do X", "delegate this to Muse", "run it through Muse", or "use Muse to implement/fix/refactor" — or wants to run a queue of coding tasks through Muse while staying the reviewer. Prefer it when the user will review the diff and commit it themselves. It applies only when the user wants that separate `muse exec` implementer run: if you are Muse yourself and the user simply asks you to write the code, do it directly. DO NOT USE for tasks small enough to do inline.
Selects and implements NestJS runtime features, error and API contracts, security, testing, DevOps, performance, and safe scale. Use for middleware, guards, pipes, interceptors, exception filters, typed failures/results, Problem Details, validation errors, HTTP/GraphQL/RPC/gRPC/WebSocket error mapping, deadlines, cancellation, retry classification, fatal process errors, authentication, authorization, caching, queues, schedulers, CI/CD, containers, Kubernetes, configuration and secrets, migrations, supply-chain controls, health probes, logs/metrics/traces, SLOs and alerts, incident recovery, rollout and rollback, event-loop or database bottlenecks, load tests, horizontal scaling, idempotency, backpressure, and graceful shutdown. Do not use for frontend-only performance or non-NestJS services. When other skills also apply, reconcile ownership before mutation.
Plans the port of an existing GitHub App to a Cursor Origin App. Use when the task is to bring a GitHub App to Origin or compare what it uses against the Origin API. Reads the app's needs out of its code, maps them onto the live Origin spec, and writes a porting brief with feedback for Cursor. Planning only.
Add an AI model provider to LobeHub, including runtime integration, model cards, configuration, branding, documentation, and acceptance. Also use for provider documentation updates; adding models to an existing provider does not require a new provider integration.
Identify stale feature flags in a PostHog project and clean up the code that checks them. Use when the user wants to find, audit, or remove unused, fully rolled out, or abandoned feature flags, run a feature flag hygiene review or a weekly cleanup, reduce feature flag tech debt, or asks "which flags can I remove?". When the agent can read and edit a repository it performs the code cleanup itself: tested local changes, and one draft PR per flag when the user authorizes publishing. Agents without repository access generate a tailored cleanup prompt instead. Covers staleness detection, dependency checking, retained-path rules, and the code-first ordering. This skill does not archive or otherwise change a flag in PostHog.
Create safe, reversible database migration scripts with rollback capabilities, data validation, and zero-downtime deployments. Use when changing database schemas, migrating data between systems, or performing large-scale data transformations.
Explain what Fusion PM MCP is and guide setup of the hosted HTTP+OAuth server for its GitHub project-management retrieval tools. USE FOR: setting up or troubleshooting Fusion PM MCP, understanding its issue/PR/milestone tools, filing a setup bug. DO NOT USE FOR: implementing changes to the fusion-pm-mcp service itself, GitHub issue authoring/triage workflows, or general Fusion Framework/docs/EDS retrieval — use `fusion-mcp` for that.
Expert patterns for AnimationTree, including StateMachine transitions, BlendSpace2D for directional movement, BlendTree for layered animations, root motion, transition conditions, advance expressions, and state machine sub-states. Use for complex character animation systems with movement blending and state management. Trigger keywords: AnimationTree, AnimationNodeStateMachine, BlendSpace2D, BlendSpace1D, BlendTree, transition_request, blend_position, advance_expression, AnimationNodeAdd2, AnimationNodeBlend2, root_motion
Expert blueprint for roguelikes including procedural generation (Walker method, BSP rooms), permadeath with meta-progression (unlock persistence), run state vs meta state separation, seeded RNG (shareable runs), loot/relic systems (hook-based modifiers), and difficulty scaling (floor-based progression). Use for dungeon crawlers, action roguelikes, or roguelites. Trigger keywords: roguelike, procedural_generation, permadeath, meta_progression, seeded_RNG, relic_system, run_state.
Designs, implements, refactors, debugs, reviews, and verifies production-quality NestJS and TypeScript software. Use for NestJS feature development, bug fixes, APIs, libraries, testing, maintainability, developer experience, idiomatic syntax, or syntactic sugar. It inspects the current project and official version-appropriate documentation before selecting syntax, preserves public behavior, and tests the result. When other skills also apply, reconcile ownership before mutation.
Build Python web apps with Flask using the application factory pattern, Blueprints, and Flask-SQLAlchemy. Prevents 9 documented errors, including stream_with_context teardown issues, async/gevent conflicts, and CSRF cache problems. Use when creating Flask projects, organizing blueprints, or troubleshooting circular imports, context errors, registration, streaming, or authentication.
Expert patterns for RPG/action ability systems, including cooldown strategies, combo systems, ability chaining, skill trees with prerequisites, upgrade paths, and resource management. Use when implementing unlockable abilities, character progression, or complex skill systems. Trigger keywords: PlayerAbility, AbilityManager, cooldown, SkillTree, SkillNode, prerequisites, can_use, execute, ComboSystem, ability_chain, global_cooldown, charge_system, upgrade_path
Use when babysitting a PR/MR until CI is green and all valid reviewer feedback is addressed — supports GitHub PR (gh) and GitLab MR (glab), triages comments into Valid / Discuss / Out-of-scope, addresses valid items with small commits and inline thread replies, escalates invisible findings (SonarQube/Snyk dashboards) and 3-round bot deadlocks, and reports ready-to-merge (never auto-merges). Triggers — '監看 PR', 'babysit PR/MR', 'PR 顧到 merge', 'address review feedback', 'wait until CI green', '把 PR 顧到綠'. NOT for writing PR descriptions, NOT for diff code review (use pr-review), NOT for actually merging the PR (user does that)
Rules and guidelines for working with Spring Data JDBC in the project. ALWAYS use this skill when adding, removing, or modifying Spring Data JDBC entities (@Table from org.springframework.data.relational.core.mapping), aggregates, AggregateReference links, embedded objects, @MappedCollection associations, or Spring Data JDBC repositories (CrudRepository / ListCrudRepository). Trigger on any request that touches @Table, @Column, @MappedCollection, @Embedded annotations from spring-data-relational, AggregateReference fields, @PersistenceCreator constructors, or @Query methods on JDBC repositories. Do NOT use for JPA (jakarta.persistence) entities — use the spring-data-jpa 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.