Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Creates structured plans from requirements. Generates comprehensive plans with steps, dependencies, risks, and success criteria. Coordinates with specialist agents for planning input and validates plan completeness. Uses template-renderer for formatted output.
Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage. Start here to decide whether it belongs in runtime managed settings, a typed SDK contract, VS Code configuration policy, extension policy, or a split implementation. Run on every new Copilot/agent/LLM control and ANY change that adds a `policy:` field.
Router for Three.js post-processing effects domain. Use when implementing visual effects like bloom, glow, chromatic aberration, vignette, depth of field, color grading, or any screen-space effects. Routes to 3 specialized skills for bloom, effects, and composer setup.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
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, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.
Publish self-contained HTML visualizations (diagrams, architecture reviews, analysis reports) viewable directly on GitHub via gist + htmlpreview. Use when the user wants to visualize something rich that markdown can't handle — architecture diagrams, dependency graphs, before/after comparisons, performance reports.
Build chat applications with PubNub Chat SDK — direct/group conversations, typing indicators, message actions (reactions, edits, read receipts), file sharing, and threaded messages. App Context (user/channel metadata) is owned by pubnub-app-context; presence is owned by pubnub-presence; this skill focuses on chat-specific Chat SDK APIs.
Get PostHog data into a canvas correctly: the host-injected `ph` SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hierarchy (saved insights first, typed query nodes second, inline HogQL last), verifiability (insight-backed metrics link their saved insight in PostHog; ad-hoc queries expose the exact query that ran), per-insight-type result shapes, progressive per-query loading, date-range wiring, live third-party data through the viewer's own connections (ph.connectors), and event capture from a canvas. Use whenever a canvas shows metrics, charts, tables, any PostHog data, or data from GitHub or an MCP server, or needs to send analytics events.
Software reverse engineering core gateway (shared foundation). Orchestrates: initial survey → format parsing → decompilation → debugging/tracing → memory. Sub-skills: [[re-address-space]] [[re-triage]] [[re-format-pe]] [[re-format-elf]] [[re-format-macho]] [[re-imports]] [[re-ghidra]] [[re-ida]] [[re-radare2]] [[re-gdb]] [[re-x64dbg]] [[re-lldb]] [[re-tracing]] [[re-memdump]] [[re-windbg]] [[re-binaryninja]] [[re-emulation]] [[re-shellcode]] [[re-kernel]] [[re-game]] [[re-go]] [[re-rust]] [[re-plugin-dev]] [[re-hypervisor]] [[re-anti-cheat]], [[re-cpp-abi]], [[re-swift]], [[re-zig]], [[re-nim]], [[re-fp-runtime]], [[re-variant]], [[re-mips]], [[re-arm]], [[re-riscv]]. Triggers: static analysis, look at this program's logic, decompilation, reverse this binary, binary analysis.
Scalable React composition patterns. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes. Do not use for React/Next.js performance optimization (use react-best-practices instead).
Type-safe validated forms in React with react-hook-form and Zod, wired through zodResolver from @hookform/resolvers, covering useForm, register, handleSubmit, formState, Controller and useController, useFieldArray, useWatch, z.infer type inference, and shadcn/ui Form and Field components. Use when building validated React forms, sharing one Zod schema across client and server validation, handling nested objects, array fields, conditional or async validation and zod refine, building multi-step forms and wizards, adding dynamic repeatable fields, optimizing form re-renders, making error handling accessible, or debugging validation issues such as resolver not found or uncontrolled-to-controlled input warnings.
Masters Reatom v1001 async flows. Use when implementing, documenting, or reviewing Reatom async queries, mutations, wrap usage, withAsync, withAsyncData, withAbort, abortVar, sampling, take, onEvent, race, framePromise, Suspense, retry, caching, or race-prone UI workflows.
Implement Customer Portal for subscription self-service. Use when building account pages, letting customers manage subscriptions, update payment methods, view billing history, or when user mentions "customer portal", "帳戶管理", "訂閱管理", "更新付款方式", "self-service". Taiwan subscription billing via PAYUNi (recur.tw, 台灣訂閱金流).
Resolve evidence-backed `docs/follow-ups/*.md` through a bounded manual, Codex Scheduled task, or Claude Routine sweep. Use when project follow-ups should be reproduced before editing, handled by one isolated worker and branch per item, and published as independent ready-for-review pull requests without automatic merge. Do not use to invent intended behavior or merely record a newly discovered follow-up.
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.