Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use this skill when working on Biome's Salsa-backed JavaScript and TypeScript inference, including type-aware lint rules, raw collection or inferred representations, analyzer requests, tracked queries, import or cycle resolution, profiling, and Salsa invalidation tests. Do not use for standalone CSS/HTML module-graph data unrelated to JS/TS inference or for ordinary semantic binding analysis.
Vue 3 components for the Unovis data visualization framework, @unovis/vue 1.7.0. Use when writing, debugging, or updating code that imports @unovis/vue or renders Vis* components such as VisXYContainer, VisSingleContainer, VisArea, VisLine, VisStackedBar, VisCrosshair, or VisTooltip. Covers the component catalog, props, events, tooltips, colors, patterns, SSR, and the 1.7.0 API changes.
Expert guide for integrating third-party C/C++ libraries into Unreal Engine 5.x projects and plugins. Covers static linking, dynamic linking (DLL/SO/dylib), Build.cs configuration, ModuleType.External, delay loading, runtime dependency staging, wrapping patterns, cross-platform considerations (Windows/macOS/Linux), ABI compatibility, RTTI/exceptions, header inclusion with THIRD_PARTY_INCLUDES_START/END, and common pitfalls. Use when the user asks about adding external libraries, third-party code, linking .lib/.a/.dll/.so/.dylib files, Build.cs PublicAdditionalLibraries, PublicDelayLoadDLLs, RuntimeDependencies, ModuleType.External, wrapping a C++ library for UE, FPlatformProcess::GetDllHandle, cross-compiling libraries for UE on Linux, or troubleshooting linker errors / DLL load failures with third-party code.
Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; seconds of compiling before real work begins; JIT modules recompiling on every run or every CI job. Only applies when the code being optimized uses Warp kernels. Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build times.
Graphics and media API reference for Windows app development (DirectX / WinRT media). Covers Direct2D (ID2D1Factory, ID2D1DeviceContext, ID2D1Bitmap1, ID2D1Effect, D2D1 Effects, ID2D1PathGeometry), DirectWrite (IDWriteFactory, IDWriteTextLayout, DWriteCore), Direct3D 11/12 (D3D11CreateDevice, D3D11On12, DXGI SwapChain, HLSL, D3D12 PipelineState, D3D12 DRED), Microsoft.UI.Composition (Compositor, Visual, ExpressionAnimation, InteractionTracker, MicaController), camera and screen capture (MediaCapture, MediaFrameReader, GraphicsCaptureSession, Windows Studio Effects, OpenCV), and audio and video playback (MediaPlayer, MediaPlaybackSession, AudioGraph, MediaTranscoder, AdaptiveMediaSource, HLS, DASH, CastingDevicePicker, AudioPlaybackConnection).
Create a new AI Skill in an existing mini program project. Triggered when the user wants to add custom AI capabilities to an existing project (rather than installing a ready-made community Skill). Full flow: understand requirements → design interfaces → call wxa-skills-generate to generate code → pass validation with wxa-skills-validate.
Use when the user wants Terraform HCL for Alibaba Cloud (Alicloud) infrastructure — new project or extending an existing one. Covers VPC, ECS, ApsaraDB RDS, OSS, SLB / ALB, Function Compute v3, ACK, and any other `alicloud_*` resource via the provider's own documentation fetched at generation time. For AWS → Alicloud migration or importing existing resources into state, use a different skill. Triggers: "write terraform for alicloud", "generate alibaba cloud terraform", "alicloud HCL", "create alibaba cloud vpc/ecs/rds", "生成阿里云 Terraform", "阿里云 HCL", "用 Terraform 部署阿里云", "alicloud provider", "aliyun/alicloud", "terraform-provider-alicloud".
Look up ArcGIS documentation against authoritative Esri sources and verify an API exists at a pinned version. Use when the user needs an ArcGIS API reference, ArcGIS Pro, Enterprise, or Notebook Server docs, or when another skill must confirm a class, method, global, or function is available at a target version.
Use when authoring or amending developer-tool documentation — the adoption + integration narrative for an SDK, library, CLI, framework, or API platform: the guide a developer reads to install, integrate, and operate the tool. Guides the METHOD, not the outline: developer GOALS not endpoints; a signposted start-here + a fast verifiable first success; concepts before recipes; goal-named runnable recipes; an end-to-end tutorial; grounded best-practices; a troubleshooting path; archetype-aware emphasis (API/SDK/CLI/framework); POINTERS into — never a copy of — the api-reference; and amending a guide as a versioned delta that sweeps the tool's changes for stale samples. Full Diataxis correctly typed, every sample runnable + accurate to the tool, nothing fabricated. Composes with a template tool + deep-research. Consumes the handed-in feature-spec + api-reference + PRD — never a blank page. Not the api-reference catalog, the end-user user-guide, engineering docs, or reviewing one.
Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".
Provides agent-ready AXe CLI usage guidance for iOS Simulator automation. Use when asked to "use AXe", "automate a simulator", "tap/swipe/type on simulator", "set a slider", "describe UI", "take a screenshot", "record video", "batch steps", or "interact with an iOS app". Covers all commands including touch, gestures, sliders, text input, keyboard, buttons, accessibility, screenshots, video, and batch workflows.
Build a single large feature end to end — you settle the product shape, then plan it, then code it. Use when the user asks to implement a new feature or invokes /build-feature <feature>. Settles what a person can now do that they could not before and the ladder of use cases smallest to largest, writes docs/<feature>/PLAN.rev1.md derived from it, takes it through review to PLAN.final.md, then executes it in small, verifiable increments grounded in the project's principles
Close out a finished <DOC>.final.md — fold what landed into the docs that already exist, carry what is still owed into <DOC>-V2.rev1.md, and delete the planning artifacts the tree no longer needs. Use when the user invokes /close-plan <feature>, or asks to clean up or retire a small feature's docs after execute-plan or build-feature has finished. Reviews ACCEPTANCE.md check by check before calling anything landed, then triages every phase as landed, pending, deferred or dropped. The smaller sibling of close-roadmap — works for any stem (PLAN, TECHNICAL, …); a plan usually does not earn its own folder of permanent documentation, so the default is to add a paragraph to a page that exists rather than create a new one
Close out a finished roadmap or feature execution by retiring its planning docs into canonical documentation and carrying what is still owed into the next roadmap — you are the archivist and the architect of the next round, not the coder. Use when the user invokes /close-roadmap <feature>, or asks to clean up a feature's docs, retire a roadmap, prepare for the next roadmap, or tidy docs/<feature>/ after execute-roadmap or build-feature has finished. Reviews ACCEPTANCE.md check by check, triages every item of ROADMAP.final.md or PLAN.final.md as landed, pending, deferred or dropped; moves pending work into ROADMAP-V2.rev1.md; turns landed work into decision records, architecture, data-model and product docs; writes the folder's README.md; deletes revs and execution artifacts the tree no longer needs; and fixes every inbound link. Nothing disappears unaccounted for; the user settles anything that would be dropped. For a small plan whose landed work folds into pages that already exist, use close-plan instead
Guide for contributing to Trellis documentation and marketplace. Covers adding spec templates, marketplace skills, documentation pages, and submitting PRs across both the Trellis main repo and docs repo. Use when someone wants to add a new spec template, add a new skill to the marketplace, add or update documentation pages, or submit a PR to this project.
Write, debug, and optimize CUTLASS, CuTe, and CuTeDSL GPU kernels from local upstream source, examples, and headers. Use when the task explicitly involves CUTLASS/CuTe/CuTeDSL, cute::Layout, cute::Tensor, TiledMMA, TiledCopy, CollectiveBuilder, CollectiveMainloop, CollectiveEpilogue, GemmUniversal, KernelSchedule, EpilogueSchedule, CUTLASS pipelines, EVT, pycute, or CUTLASS template errors. Use cuda-skill for raw CUDA/PTX or NVIDIA architecture facts, and triton-skill for Triton or Gluon implementation work.
Process JSON with jq and YAML/TOML with yq. Filter, transform, query structured data efficiently. Triggers on: parse JSON, extract from YAML, query config, Docker Compose, K8s manifests, GitHub Actions workflows, package.json, filter data.
Modify existing DatoCMS plugins built with datocms-plugin-sdk and connect(). Use when users ask to patch or maintain an existing plugin project: config screen edits, hook additions, field extension tweaks, sidebar/page/outlet changes, validation updates, settings cleanup, dependency fixes, or other day-to-day plugin maintenance. Prefer `datocms-plugin-scaffold` when starting a new plugin from scratch.
Scaffold brand-new DatoCMS plugin projects with datocms-plugin-sdk and connect(). Use when users want to create a new plugin folder from scratch, bootstrap the Vite/React package structure, choose initial plugin surfaces such as field extensions, config screens, sidebars, pages, asset sources, or dropdown actions, and wire the first hook implementation. Prefer `datocms-plugin-builder` for edits to an existing plugin project.
Audits direct and transitive dependencies for license compliance, maintenance health, CVEs, abandoned packages, and bloat. Triggers on: "audit dependencies", "license check", "dependency health", "abandoned packages", "unused dependencies", "license compliance", "supply chain", "dependency risk".
Use when evolving aggregate invariants, value objects or domain events in an existing DDD-style Spring Boot 3 application, or when DDD is explicitly requested. Preserve existing API identifiers and architecture when changing domain behavior.
Plan a large feature as a ROADMAP.rev1 written with the user — you are the product manager first and the senior software architect second, never the coder. Use when the user asks to plan a large feature, write a roadmap, or invokes /draft-roadmap <feature>. Settles the product shape — the one sentence, and the ladder of use cases smallest to largest — then derives a roadmap of small, verifiable, delegatable milestones and plans from it, ready for review and for parallel execution
Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as "used to", "no longer", "this cut"; stack or review vantage ("a later PR in this stack", "rejected in review"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.
Execute a signed-off PLAN.final.md for a single feature yourself, phase by phase, on the current branch — you are the engineer, not a delivery lead. Use when the user invokes /execute-plan, or asks to implement, build or continue an approved plan that is small enough for one person, e.g. "/execute-plan spell-check", "/execute-plan spell-check p1-p3", "build the rest of the plan while I sleep". Resolves the requested phases against the final doc, builds each as its own verified increment, runs its verification before the next begins, and commits each landed phase without waiting for approval. Questions that need the user are recorded with a recommendation instead of blocking. For a roadmap large enough to want parallel sub-agents, use execute-roadmap instead
React feature-based architecture guidelines for scalable applications (formerly feature-architecture). This skill should be used when writing, reviewing, or refactoring React code to ensure proper feature organization. Triggers on tasks involving project structure, feature organization, module boundaries, cross-feature imports, data fetching patterns, or component composition.
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
Fix bugs and make small improvements while leaving the codebase better than it was found. Use when the user asks to fix a bug, clean something up, or make a minor improvement. Every fix explains the root cause for the reviewer, justifies the chosen solution against alternatives, and looks for the simplification the bug is pointing at — and asks before any product decision, large-blast-radius change or persisted schema/format change.
Use when debugging or preventing errors in Frappe Client Scripts. Prevents TypeError, frappe.call failures, async/await mistakes, cur_frm vs frm confusion, field not found, child table access errors, timing issues, CSRF token errors, and permission denied on frappe.call. Covers error diagnosis flowchart and debug tools for v14/v15/v16. Keywords: client script error, TypeError, frappe.call, async await, Cannot read properties of undefined, TypeError, browser console error, script not running, form not updating, cur_frm, field not found, child table, CSRF, permission denied.
Use when building Script Reports, Query Reports, dashboard charts, or Number Cards in ERPNext. Prevents empty report output from wrong column definitions, broken filters, and unoptimized SQL in large datasets. Covers Report Builder, Script Report (Python + JS), Query Report, Report filters, dashboard Chart DocType, Number Card, report permissions. Keywords: report, Script Report, Query Report, dashboard, chart, Number Card, filters, columns, execute, get_data, create report, custom report, dashboard chart, report empty, no data showing.
Use when scaffolding a new Frappe app, configuring app settings, building assets, running tests, deploying, updating, or publishing to marketplace. Prevents broken app structure from incorrect scaffolding, missing setup.py fields, and failed builds. Covers bench new-app, app directory structure, setup.py/pyproject.toml, hooks.py config, bench build, bench run-tests, app publishing. Keywords: app lifecycle, new-app, scaffolding, setup.py, pyproject.toml, hooks.py, bench build, app publishing, marketplace, create app, publish app, app structure, how to start new app, app directory layout.
Use when configuring frontend asset bundling, migrating from build.json (v14) to esbuild (v15+), or troubleshooting SCSS/CSS compilation. Prevents build failures from mixing v14 and v15 build systems and misconfigured asset pipelines. Covers esbuild configuration (v15+), build.json (v14), asset bundling, SCSS compilation, bundle.js setup, bench build flags. Keywords: esbuild, build.json, frontend build, SCSS, CSS, asset bundling, bench build, bundle.js, webpack, build error, assets not loading, CSS not updating, JS not compiling, bench build fails.
Use when upgrading Frappe/ERPNext between major versions (v14 to v15, v15 to v16), troubleshooting failed migrations, or planning rollback. Prevents broken upgrades from skipped patches, incompatible customizations, and missing pre-upgrade checks. Covers version upgrade paths, bench update, migrate command, patch troubleshooting, rollback procedures, breaking changes per version. Keywords: upgrade, migration, v14, v15, v16, bench update, bench migrate, rollback, patches, breaking changes, update failed, bench update error, migration error, patches failing, rollback after upgrade.
Use when implementing document lifecycle hooks via doc_events in hooks.py, understanding event execution order, or extending/overriding document behavior from another app. Prevents silent hook failures from wrong event names, incorrect execution order assumptions, and broken override chains. Covers doc_events hook syntax, all document events (before_insert, validate, on_submit, etc.), event execution order, extend vs override behavior, cross-app doc_events. Keywords: doc_events, hooks.py, before_insert, validate, on_submit, on_cancel, lifecycle, document events, override, extend, event order, which event fires when, before_save vs validate, document event list.
Use when building Query Reports, Script Reports, or configuring Report Builder, including chart data integration. Prevents report errors from wrong column definitions, missing permissions, and incorrect data formatting. Covers Query Report (SQL-based), Script Report (Python-based), Report Builder, report columns definition, filters, chart_data, report permissions, prepared_report. Keywords: Query Report, Script Report, Report Builder, report columns, filters, chart_data, frappe.query_report, prepared_report, report columns, how to build report, report not showing data, chart in report.
Use when creating Frappe Whitelisted Methods (Python API endpoints) for v14/v15/v16. Covers @frappe.whitelist() decorator, frappe.call/frm.call invocations, permission checks, error handling, response formats, and client-server communication. Keywords: whitelisted, API endpoint, frappe.call, frm.call, REST API, @frappe.whitelist, allow_guest, API endpoint example, frappe.whitelist syntax, how to expose function.
One-click installer for gate-cli and gate-skills on Cursor, Claude Code, Codex, or OpenClaw/mcporter. Triggers on 'install gate-cli', 'Gate skills', 'Gate Verify', 'tx check-in', 'setup Gate Cursor', 'Gate Claude Code', 'Gate Codex', 'OpenClaw Gate', 'mcporter Gate'.
Configure GrowthBook API credentials and the trusted app origin so the other skills can run and link to the UI. Use when the user says "set up growthbook", "configure my api key", "growthbook isn't working", "where do I put my key", or when another skill emits an error pointing here ("GB_API_KEY is not set", "authentication failed", "GB_APP_URL is required"). Writes ~/.config/growthbook/.env with chmod 600 and validates against the live API. For listing flags or running experiments, the domain skills handle that.
Search GitHub for real-world code examples and implementation patterns. Use when user wants to find code examples on GitHub, search GitHub repositories, discover how others implement features, learn library usage patterns, or research architectural approaches. Fetches top results with smart ranking (stars, recency, language), extracts factual data (imports, syntax patterns, metrics), and returns clean markdown for analysis and pattern identification.
Operate GitLab through the glab-axi CLI - issues, merge requests, CI/CD pipelines, projects, labels, CI/CD variables and secrets, releases, search, and raw API access. Use whenever a task touches GitLab: listing or filing issues, reviewing or merging merge requests, checking pipeline status and failed job logs, managing CI/CD variables and secrets, cutting releases, or querying the GitLab API.
Install and run GitLab Duo CLI through glab in interactive or headless mode. Use when accessing GitLab Duo Agent Platform from the terminal, running a bounded headless goal, or managing the wrapped Duo CLI binary. Triggers on Duo, GitLab Duo CLI, glab duo cli, AI assistant, headless goal, autonomous coding.
Run the managed Orbit CLI through glab for remote graph queries and local code-graph workflows. Use when installing or updating Orbit, checking graph status, querying a remote Orbit graph, indexing or searching a local code graph, forwarding Orbit help, or troubleshooting managed-binary authentication. Triggers on orbit, knowledge graph, code graph, graph query, graph status, glab orbit, orbit-cli, orbit binary.
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.