Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Production-grade NestJS backend standards for writing, reviewing, and evolving NestJS/Nest-style TypeScript services. Use when a repo has modules, controllers, providers/services, DTOs, guards, pipes, or Nest-oriented boundaries, or when designing NestJS APIs, modules, migrations, auth/RBAC, multi-tenant isolation, DDD layered/hexagonal architecture, ports/adapters, use cases, repository/query patterns, N+1/slow queries, validation, pagination, caching, error handling/exception filters, BullMQ/jobs, webhooks, uploads, decorators, provider scopes, dynamic modules, circular deps, health/readiness/shutdown, observability/logging/tracing, OpenTelemetry, testing, code review, modernization/version/runtime advice, or AI backend patterns like LLM gateways, SSE streaming, usage metering, and quotas. Verify volatile versions/commands/model IDs/APIs against official docs and the repo. Plain Express/Fastify/Hono/Koa without Nest boundaries: cross-cutting guidance only. Not for non-Node backends or pure frontend work.
Guide for implementing Next.js - a React framework for production with server-side rendering, static generation, and modern web features. Use when building Next.js applications, implementing App Router, working with server components, data fetching, routing, or optimizing performance.
Use when generating or regenerating a typed TypeScript client from an OpenAPI 3.1 contract — for example a FastAPI /openapi.json — with @hey-api/openapi-ts. Produces typed models, a typed SDK (one function per operation), TanStack Query hooks, and Zod schemas straight from the spec, so the frontend stays in lock-step with the API instead of a hand-written client. Covers the openapi-ts.config.ts config, the fetch/axios/next clients, the tanstack-query and zod plugins, the regenerate-and-drift-check workflow, and the FastAPI operationId naming fix. Use when wiring an OpenAPI or FastAPI backend to a TS/React frontend, replacing a hand-maintained API client, or adding generated query hooks. Not a TanStack Query usage tutorial (compose with that skill) and not backend/OpenAPI-spec authoring.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". It also owns single-session terminal work: "session", "sub-agent", "create a session", "stop a session", "fork a session", "attach to a session", "worktree session", and troubleshooting a stuck or misconfigured agent terminal. Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use `orchestration` instead to fan out several agents at once or to supervise them. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Planning methodology and session management for software projects. Covers markdown plan creation, iterative refinement, multi-model blending, phase-based implementation docs, and cross-session progress tracking. Use when starting new projects, adding major features, breaking large work into phases, resuming after context clears, or managing multi-phase implementations.
Guide for authoring comprehensive PRDs with parallel planning support. Use for drafting technical specifications, defining requirements, and synthesizing planner outputs. Use proactively when creating PRDs, architecture designs, or implementation plans. Examples: - user: "Draft a PRD for user auth" → create PRD with purpose, requirements, and scenarios - user: "Analyze these PRD requirements" → verify SHALL/MUST usage and scenario structure - user: "Synthesize planner outputs" → merge the strongest parts of multiple generated PRDs - user: "Create a PRD template" → setup standard sections and placeholder content
Prepare React Router release notes before running the changes/versioning scripts. Use when asked to review, polish, normalize, or prepare pending change files under packages/*/.changes, remove semantic commit prefixes from release bullets, enforce imperative tense, decide whether a manual scripts/changes/whats-changed.md section is warranted, or draft long-form release notes for new features, stable future flags, or unstable flags.
Use when starting a session on an existing WordPress site, or when the user says 'prime yourself', 'what builder does this site use', or 'give me a site briefing'. Loads the active site, detects the builder, loads inline schemas, reads the stored per-site brief, and sets the do-not-write-raw-HTML rule.
Authoring and debugging scripts for Rhinoceros 3D (Rhino 8 and later). Use when asked to write RhinoScript (VBScript / .rvb / .vbs), RhinoPython, or RhinoCommon-based scripts; automate Rhino modeling tasks; build command macros; manipulate Rhino geometry, layers, blocks, or document objects; pick objects from the viewport; control redraw and undo; or load and run scripts from the Rhino Script Editor. Covers `rhinoscriptsyntax`, `scriptcontext`, the `Rhino.*` RhinoCommon namespaces (`Rhino.Geometry`, `Rhino.DocObjects`, `Rhino.Input`, `Rhino.UI`, `Rhino.Display`, `Rhino.FileIO`), and the Rhino 8 unified Script Editor.
Design, implement, audit, and report lossless Java-to-Rust migration tests without promoting green tests into false completion claims. Use when porting 100% of JUnit tests and concrete parameterized/dynamic cases, SHA-256-verifying source fixtures/resources/scripts/data, requiring complete per-case golden or live differential MATCH results, validating object/test ledgers, reviewing oversized Rust test files, organizing inline unit versus integration tests, adding Rust-specific obligations, comparing coverage, or building property, fuzz, mutation, concurrency, lifecycle, adapter, host, load, security, and rollback evidence. Enforces a 500-line cohesion-review threshold, an 800-line authored-file blocker, and idiomatic Rust test placement.
A heavyweight Harness skill that turns the SDD-RIPER methodology into a strictly executable process. It helps users clarify the final goal, generate a codemap/context, split out the smallest chaos unit, maintain a complete spec, enforce RIPER phase gates, block high-risk actions, and preserve a local task trail that can be resumed in a new chat.
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a `HEAL-` entry to `.learnings/HEALS.md` with proof. Use whenever a command, test, build, or lint fails or exits non-zero; on missing tooling, dependency/lockfile mismatch, wrong runtime version, venv or permission errors, port conflicts, dirty git state, or a missing `.env`; when the agent needs a helper or one-off script that doesn't exist yet; when an external API, tool, or MCP errors or rate-limits; or when a test flakes. Search `HEALS.md` by `Pattern-Key` first — most heals are recurrences, so increment `Recurrence-Count` instead of duplicating. Verify is mandatory: mark `pending-verify` honestly if sandboxed, `abandoned` if the fix can't be made to work. Pairs with `self-improvement` (which promotes recurring heals to durable memory) but owns the verify-before-persist discipline self-improvement doesn't.
Apply repository-grounded senior engineering judgment to substantial Python work and bounded Python changes with production or cross-boundary risk. Do not use for trivial syntax questions, generic tutoring, or tasks with no Python artifact unless explicitly invoked. Use for writing, review, diagnosis, design, refactoring, or maintenance where correctness, state, effects, concurrency, compatibility, security, reuse, testing, or long-term ownership materially matters.
Generate Flow metadata XML and migrate Process Builders to Flows. Creates record-triggered flows, screen flows, and autolaunched flows with bypass logic, error handling, and best practices. Use when asked about Flows, Process Builder migration, .flow-meta.xml files, or Salesforce automation. Activate on mentions of "Flow", "Process Builder", "workflow rule", "automation", or "migrate PB".
Complete guide to implementing Syncfusion ASP.NET Core Card component with layout structures, headers, images, actions, and advanced customization. Use this skill when building card-based layouts, displaying content with headers and images, creating action buttons, or organizing responsive card designs.
Implement the Syncfusion ASP.NET Core DropDownTree component to bind hierarchical and self-referential data, enable checkbox selection, customize templates, implement keyboard accessibility, and handle tree interactions when building multi-level dropdown selections.
Implement the Syncfusion ASP.NET Core Smart Paste Button for AI-powered form auto-filling using clipboard data. Use this skill when configuring OpenAI/Azure OpenAI, creating form field annotations, customizing button appearance, implementing custom inference backends, or managing intelligent data mapping from clipboard to form fields.
Implement the Syncfusion ASP.NET Core Smart TextArea for AI-powered inline or popup text autocompletion. Covers OpenAI, Azure OpenAI, Ollama, and custom IChatInferenceService backends, plus UserRole, UserPhrases, and suggestion display mode customization.
Implement Syncfusion ASP.NET Core Splitter component for building responsive multi-pane layouts. Use this when implementing splitter layouts, configuring panes, enabling resize functionality, or creating complex nested layouts with multiple split sections.
A simple toolbar component that organizes command buttons and responsive controls into a horizontal interface. Ideal for document editors, content management systems, and application headers to trigger actions and manage user workflows efficiently.
Use this skill for Blazor apps needing Excel-like UI using the Syncfusion Spreadsheet Component. Trigger for creating, viewing, editing Excel (.xlsx, .xls) files; embedding spreadsheet editors; using formulas, filtering, sorting, or cell formatting. Also trigger when users reference spreadsheet files ("open xlsx", "load Excel file", "add Syncfusion spreadsheet"). Do NOT trigger for standalone file processing without UI components.
Extract tables, form fields, barcodes, and document layout from PDFs or images (scanned PDFs, PNG/JPG) using Syncfusion Smart Data Extractor. Trigger when users ask to parse/extract/convert document data (invoices, receipts, KYC/forms) into structured output and want C#/.NET integration code using the extractor.
Implements Syncfusion WinForms SfDataGrid component for displaying and managing tabular data in Windows Forms applications. Use this when working with data grids, column management (auto-generation, stacked headers), data operations (filtering, sorting, grouping), or grid editing with validation. The skill covers data summaries, selection modes, export capabilities (Excel/PDF), conditional styling, master-detail views, and drag-and-drop functionality.
High-volume, asynchronous offline inference at up to 50% lower cost via Together AI's Batch API. Prepare JSONL inputs, upload files, create jobs, poll status, and download outputs. Reach for it whenever the user needs non-interactive bulk inference rather than real-time chat or evaluation jobs.
Operate Trau (display name Cobble) — the autonomous, ticket-driven development loop (trau.sh) — from a shell or MCP client: file, search and queue tickets, arm or pause the queue drain, watch and steer live runs, switch a run's provider, answer a PR or QA hold, settle an ADR conflict, read evidence, spend and conformance results, diagnose, resume or discard failed or quarantined runs, hand a run a secret, work a ticket's operator checklist, set config, manage QA sign-in accounts, tracker and forge connections, hosted collaborators and the local web hub. Use whenever the user mentions trau or Cobble, the trau hub, queue, drain, babysitting a drain, steering a run, a quarantined, parked, awaiting-qa or needs-human ticket, `trau doctor`, `trau forensics`, `trau update`, `trau connect`, QA accounts or proofs — or asks to start, stop, monitor, or debug autonomous ticket runs in a repo trau manages, even phrased as "queue this ticket", "what is the loop doing", "why won't the drain arm", or "why didn't COD-123 merge". Do not use for writing trau's own source code, or for general git/PR workflow questions unrelated to trau runs.
Connect third-party AI agents (OpenAI, Bedrock, LangChain, Microsoft Foundry) to Twilio's communication channels using the Twilio Agent Connect SDK. Covers identity resolution, memory and context management via Conversation Memory, conversation orchestration via Conversation Orchestrator, multi-channel handling (Voice, SMS, RCS, WhatsApp, Chat), and AI-to-human escalation. Use this skill when integrating an existing LLM agent with Twilio services.
Apply these opinionated TypeScript conventions whenever writing or reviewing TypeScript: branded types for domain modeling, discriminated unions for state, `satisfies` over `as`, const objects instead of enums, type-only imports, and the strict tsconfig baseline beyond `strict: true`. Also use for monorepo project references and incremental build setup.
Use when upgrading TYPO3 extensions to newer LTS versions (v11->v12, v12->v13, v13->v14 - v14.3 LTS is the current target), running Extension Scanner, Rector, Fractor, PHPStan, fixing deprecated APIs, or resolving compatibility issues. Also triggers on: migration, version upgrade, deprecated API, dual-version compatibility, Fluid 5 strict VHs, HashService removal, ext_tables.php split.
Unity Editor tooling, build automation, and asset pipeline customization. PROACTIVELY activate for: (1) writing custom Editor scripts, (2) custom inspectors and PropertyDrawer attributes, (3) EditorWindow creation, (4) ScriptedImporter for custom asset types, (5) build pipeline scripting (BuildPipeline.BuildPlayer, IBuildPostprocessor), (6) platform-switching automation, (7) CI/CD for Unity (GameCI, GitHub Actions, Unity Build Automation), (8) Assembly Definition (.asmdef) organization, (9) preprocessor symbols and platform defines, (10) Editor-only code with #if UNITY_EDITOR. Provides: custom inspector templates, EditorWindow examples, build script patterns, GameCI setup, .asmdef best practices, and CI YAML for Unity builds.
Reference for the uploads CLI and its stdio/hosted MCP tools — exact flags, keys, and contracts for put and attach, screenshot capture, stable PR/issue keys, the managed attachments comment, metadata and search, galleries, change feeds (repo-wide or one PR/issue), config defaults, issue artifacts, login/doctor, and output formats. Use when driving the `uploads` CLI or its MCP tools (including the hosted MCP at agents.uploads.sh for agents without local filesystem/git access), when you need a public URL for a local file ("upload this", "host this image", "give me a public URL for this file"), when the CLI itself prints a hint or nudge you need to act on (a `hint` field in `--format json`, or the stderr note suggesting `--pr`/`attach --branch`), or when you need exact flags, key layouts, or setup and auth details. For the when-and-how of getting a screenshot or recording into a GitHub PR or issue, start with the github-screenshots skill — it defers here for CLI detail
Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react, UIMessage, ChatStatus, streamText, toUIMessageStreamResponse, addToolOutput, onToolCall, sendMessage.
Verl single-async DAPO training config generator. Trigger scenarios: (1) starting single-async DAPO training (2) generating training scripts (3) configuring feature parameters (4) pre-training checks. **Feature policy**: when the user does not specify, performance features (flash_attn/dynamic_batch/remove_padding/gradient_checkpointing) are enabled by default, while memory features (offload/recompute) are disabled by default. On OOM, memory features are automatically appended and retried. **Training monitoring**: after startup, output the SwanLab link for the user to check themselves, and notify the user only on errors. **Dependent skill**: SwanLab configuration is provided through the swanlab-setup skill.
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.