Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Design and audit offline sync, queued mutations, reconnect behavior, conflict resolution, local-first UX, draft persistence, tombstones, attachment sync, optimistic updates, multi-device edits, merge policies, data-loss recovery, and sync observability. Use when mobile, desktop, PWA, field, creator, or collaboration products must keep working without reliable connectivity.
Build ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI). Use when: developing ChatGPT extensions, implementing MCP servers, or troubleshooting CORS blocking (allow chatgpt.com), widget 404s (missing ui://widget/), wrong MIME type (text/html+skybridge), or ASSETS binding undefined.
Platform-agnostic OpenTelemetry reference — signal selection (traces/metrics/logs), span design, context propagation (W3C TraceContext), sampling strategies, and OTLP exporter config. Use before writing any OTel instrumentation to get design decisions right. Platform-specific skills (otel-node, cloudflare-workers-otel-utels) layer on top of this.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Node.js OpenTelemetry setup — SDK init, auto-instrumentation packages, and the esbuild ESM silent-failure gotcha (instrumentation-* packages produce no spans when bundled with esbuild --format=esm). Use when adding OTel to a Node.js/Hono/Express service or debugging missing spans after bundling. See opentelemetry for signal design decisions.
Build React web UIs with PanelUI's web collection — adding its components from the shadcn registry or from npm, colouring them from the theme, and composing them into framed panels. Applies when working in a React project that has shadcn/ui set up with a @panelui registry or has panelui-web installed, when the user mentions PanelUI on the web, or when they ask for a dotted globe, a KPI card, a kanban board, a node graph, an activity grid or a feedback dialog in React.
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch or JAX. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.
Performance issue analysis and optimization workflow, six stages. All triggers start with 性能 ("performance"): 性能分析, 性能证据, 性能定位, 性能假设, 性能监控, 性能优化, 性能验证, 性能深入. Saying one of these words alone, or using the 「trigger: description」 form, enters this workflow or the corresponding stage.
Use when modifying the BK-CI IAM RBAC permission model, such as adding resource types, designing action lists, configuring IAM resources, backfilling migration data, and validating callback chains. Prefer this when the user needs to change the permission model rather than make ordinary permission calls.
Modern PHP development best practices including PHP 8.x features, OOP patterns, error handling, security, testing, and performance optimization. Use when writing PHP code, reviewing PHP projects, debugging PHP issues, or implementing PHP features outside of WordPress/Laravel specific contexts.
Use when understanding or modifying the BK-CI pipeline Model, Stage, Container, and Element structures. Prefer this when the user mentions the pipeline model, Stage/Job/Task data structures, model extension, model validation, version compatibility, or YAML-to-Model conversion.
Brainstorming-enhanced PDCA planning with intent discovery and YAGNI review. For a single feature's plan use /plan-plus; for grouping multiple features under one scope/budget see /sprint master-plan (v2.1.13). Triggers: plan-plus, brainstorm, plan plus, intent
Plans how to execute exactly one already-selected numbered Jira or GitHub task by producing an execution brief, implementation plan, behavior-oriented test specification, and scoped refactoring recommendation. Use for Phase 5 task-execution planning with a workflow key and TASK_NUMBER. Does not decompose the parent work item, plan multiple tasks, implement code, or advance to the next task.
Designs public or private Agent Skill and plugin marketplaces for Cursor, Claude Code, Codex, Zed, Open Plugin, and npx skills—manifest layout, install matrix, and Skill Steward vs product boundaries. Use when setting up a marketplace, distributing skills/plugins to a team, private registry, .cursor-plugin, .codex-plugin, .plugin, .claude-plugin, or skills.sh publishing.
Review a diff (pull request, commit, or local changes) by comparing it against the project's BLUEPRINT.md slice catalog. Auto-detects the input format (git diff, GitHub/GitLab PR URL or number, commit SHA, pasted diff). Loads the blueprint for each project the diff touches and classifies findings as deviations from declared slices, universal anti-patterns, or improvements. Human-in-the-loop on ambiguity (slice classification, severity, ambiguous deviations). Output is ephemeral — emitted to chat or saved on request, never auto-committed. Use whenever the user asks "review this PR", "check my changes", "any anti-patterns in this commit", "is this safe to merge", "look at PR #N", "review my diff", pastes a diff, mentions a commit SHA, or wants a pre-merge sanity check on their code changes.
Use when the user asks to write, draft, generate, or update a GitHub pull request description for the current branch. Reads the branch diff and commit messages, writes a structured PR body (summary, changes, testing), and optionally creates or updates the PR via the gh CLI.
This skill should be used when conducting PRD interviews, creating product requirements documents, planning new features, documenting bug fixes, or when using commands like "/prd-builder:prd", "/prd-builder:feature", "/prd-builder:bugfix", or "/prd-builder:refine". Provides comprehensive interview frameworks and question templates for building thorough PRDs.
Product changelog and release notes that users actually read. Covers categorization, user-facing language, visuals, and distribution. Use for: release notes, changelogs, product updates, feature announcements, versioning. Triggers: changelog, release notes, product update, version notes, what's new, feature announcement, product changelog, update log, release announcement, version release, product release, ship notes
Discover the architectural slices, conventions, and patterns of a codebase by examining its structure, then output a written BLUEPRINT.md per project under docs/architecture (plus a SYSTEM_MAP.md for monorepos) that captures what the project actually does. Discovery means finding repeated structural patterns (slices) from folder shapes and naming conventions, not applying architectural theory. Detects monorepos with sub-projects, internal dimensions like voice/text verticals, and slice variants. Human-in-the-loop by design — pauses to ask about singletons vs templates, canonical reference selection, slice naming, and pre-write confirmation. Use whenever the user wants to map a codebase, onboard onto a project, document architecture, understand "how does this team add X", build a slice catalog, or generate a reference document for new contributors.
Rigorously collects and validates all fields needed to produce a complete, unambiguous prompt template for features and bug fixes. The skill asks targeted questions until the template is fully filled, consistent, and ready to paste into a Codex/GPT-5.2 coding session.
Guides FastAPI backend design using Domain-Driven Design (DDD) and Onion Architecture in Python. Use when structuring a FastAPI app (routes/handlers, Pydantic schemas, Depends-based DI), modeling domain Entities/Value Objects, defining repository interfaces, implementing SQLAlchemy infrastructure adapters, or writing use cases, based on the dddpy reference.
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python
Advanced sub-skill for Qiskit focused on executing circuits on physical quantum processing units (QPUs). Covers IBM Quantum Runtime, error mitigation techniques (TREX, ZNE), hardware-aware transpilation, and low-level pulse control (OpenPulse).
Implements the Ralph Wiggum autonomous iteration technique with deliberate context management. Use when building greenfield projects, iterating on well-defined tasks, or when continuous autonomous development is needed. Manages context like memory - tracks allocations, prevents redlining, and knows when to start fresh.
Apply React and Next.js performance optimization guidelines from Vercel Engineering — 40+ rules covering components, data fetching, bundle optimization, and rendering. Triggers on React components, Next.js pages, bundle optimization, performance improvements, refactoring React code.
Manage application state with the @virtuoso.dev/reactive-engine-* package family. Use this skill when (1) defining reactive state with Cell, Stream, Trigger, or Resource nodes, (2) wiring React components through EngineProvider, useCellValue, useCellValues, or usePublisher, (3) fetching data with Query and Mutation from reactive-engine-query, (4) routing with Route, Layout, and Guard from reactive-engine-router, (5) persisting cells with linkCellToStorage, (6) architecting a component or library on top of the engine, (7) observing or troubleshooting propagation with describeNode, observeDiagnostics, useEngineDiagnostics, or useRemoteEngineDiagnostics, or (8) any task involving Engine, pub, sub, getValue, combine, pipe, link, changeWith, the e namespace, missing or duplicate emissions, unexpected distinct suppression, or the error "No active engine found".
Receive and verify Recurly webhooks. Use when setting up Recurly webhook handlers, verifying the recurly-signature header (HMAC-SHA256), securing the endpoint with HTTP Basic Auth, or handling subscription and billing events like new_subscription_notification, updated_subscription_notification, successful_payment_notification, and failed_payment_notification.
Refactor Next.js code to improve maintainability, readability, and adherence to App Router best practices. Identifies and fixes God Components, prop drilling, inappropriate 'use client' usage, outdated Pages Router patterns, missing Suspense boundaries, incorrect caching strategies, and useEffect data fetching anti-patterns. Applies modern Next.js 15 patterns including Server Components, Client Components, Server Actions, streaming with Suspense, proper caching strategies, Container-Presentational pattern, layout composition, parallel routes, and intercepting routes.
Refactor Nuxt.js/Vue code to improve maintainability, readability, and adherence to best practices. Identifies and fixes DRY violations, oversized components, deep nesting, SRP violations, data fetching anti-patterns with useFetch/useAsyncData/$fetch, poor composable organization, and mixed business/presentation logic. Applies Nuxt 3 patterns including auto-imports, proper data fetching, single-responsibility composables, TypeScript integration, runtime config, Nitro server routes, Nuxt Layers, middleware patterns, Pinia state management, and performance optimizations.
Use when the user asks to create, debug, explain, validate, or optimize a regular expression or replacement for a specific engine. Verifies representative matches, non-matches, captures, escaping, portability limits, and backtracking risk in the target runtime.
Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable. Use for release CI, install.sh, versioning, CHANGELOGs, shipping MCP/CLI without clone, or meta repos that only ship skills via npx skills—not domain app tutorials.
Master orchestration for repository governance, North Star impact, sub-Star boundaries, and repair-first or evidence-first drift checks. Guides an agent through the complete lifecycle of making architectural decisions, documenting them, writing FAQs, and cleaning up stale plans while adhering strictly to repo ethics and brand tone. Use whenever you need to make a structural change, write an ADR, update the doc lattice, or govern repository architecture.
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.