Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Generally-applicable backend/data best practices. Use whenever writing or modifying backend/data code — API routes, server actions, DB writes, background jobs, agent tools, import flows, webhooks, paste handlers, or anywhere data enters the system. Consult BEFORE writing the code so the patterns are baked in, not retrofitted. If a scenario described in the skill body matches the work, apply the pattern — don't ask, just follow it (call out the choice in one line so the user can override).
Use when choosing Bevy 0.20 Cargo features — top-level `2d`/`3d`/`ui`/`audio`, mid-level `3d_api`/`3d_bevy_render`/`ui_api`/`common_api`, headless `default_app`, input opt-ins `mouse`/`keyboard`/`gamepad`, `bevy_curve` (was `bevy_math/curve`), `compressed_image_saver_universal`, `render_dev_tools`, or debugging missing UI, audio, or window after `default-features = false`
Scans code for performance and scalability issues — N+1 queries, missing indexes, unbounded queries, memory inefficiencies, caching gaps, algorithmic complexity, concurrency bugs, and frontend performance problems. Generates severity-scored findings with copy-pasteable fix prompts. Trigger phrases: "performance audit", "performance check", "N+1 detection", "query optimization", "slow code", "performance review".
Creates comprehensive GitHub pull requests with automated quality validation and security scanning, then hands off to /github:review-pr for CI monitoring and reviewer-comment triage. This skill should be used when the user asks to "create a PR", "submit a pull request", or needs to merge completed work with full compliance checks.
NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels. MANDATORY: every optimization MUST start with NCU profiling, followed by multi-dimensional analysis, then targeted code modification, then re-profiling to verify. Supports roofline, memory hierarchy, warp stalls, instruction mix, occupancy, divergence analysis. Provides implementation-specific code modifications: Native CUDA (launch config, memory patterns, async copy, Tensor Core), CUTLASS (ThreadblockShape, stages, epilogue, schedule policy, alignment), Triton (autotune params, compiler hints, tl.* API patterns), CuTe DSL (threads_per_cta, elems_per_thread, tiled_copy, copy atom, shared memory, warp/cta reduce). Use when optimizing any CUDA kernel performance.
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs
Build and maintain Dexie.js data layers for IndexedDB-backed offline-first web applications. Use when tasks involve Dexie setup, schema/index design, CRUD/query implementation, transactions, live queries, migrations, or debugging in Vanilla JS, React, Next.js, TanStack Start, Svelte, or SvelteKit.
Automatically discover software engineering practice skills when working with code review, documentation, pair programming, production debugging, performance profiling, deployment strategies, or software engineering practices. Activates for engineering development tasks.
Extracts design data from Figma via the REST API and converts designs to React code. Use when syncing Figma tokens to CSS variables, exporting icons as SVG components, generating code from Figma designs, or automating design-to-code workflows. Use for design token extraction, icon export, component generation, and CI-based Figma sync.
Use when debugging or preventing errors in Frappe Server Scripts. Prevents ImportError (the #1 error), NameError for restricted builtins, sandbox violations, doc_events not firing, wrong script type selection, SQL injection, permission denied in scheduled scripts, infinite loops, and API scripts not returning JSON. Covers error message mapping table. Keywords: server script error, ImportError, NameError, sandbox, restricted, ImportError in server script, script not running, sandbox error, restricted function, frappe.throw, doc_events, scheduler, API script, SQL injection.
Use when implementing server-side features via Setup > Server Script: document validation, auto-fill, API endpoints, scheduled tasks, permission queries. Covers sandbox-safe coding, script type selection, testing, migration to controllers. Keywords: how to implement server script, which script type, sandbox limitation, Document Event, API script, Scheduler Event, Permission Query, migrate to controller, no-code automation, run code on save, auto-fill field, server-side validation, scheduled script.
Use when creating or customizing Workspace pages in Frappe v14-v16. Covers Workspace DocType structure, shortcuts, number cards, dashboard charts, custom HTML blocks, JSON content format, shipping workspaces with custom apps, and role-based access control. Prevents common mistakes with content/child-table desync and missing fixtures. Keywords: workspace, desk, dashboard, number card, chart, shortcut, customize desk, dashboard setup, add shortcut, module page, sidebar customize, workspace builder, module, fixtures, sidebar.
Use when configuring scheduler events and background jobs in Frappe/ERPNext v14/v15/v16. Covers scheduler_events in hooks.py, frappe.enqueue() for async jobs, queue configuration, job deduplication, error handling, and monitoring. Keywords: scheduler, background job, cron, RQ worker, job queue, async task, frappe.enqueue, scheduled task, cron syntax, how often does it run, background job example, enqueue example.
Git worktree management with tmux and iTerm2 integration. Use when creating isolated dev environments, managing parallel feature branches, switching contexts without stashing, or running multiple Claude instances. Covers worktree creation, tmux window management, iTerm2 tabs, and cleanup workflows.
Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance. Three modes: generate (new), audit (check existing), update (patch). Detects repo type and adapts sections, tone, and badges accordingly.
Create GitLab project or personal code snippets with glab. Use when sharing code or text as a new snippet from files or stdin. For viewing, editing, or deleting existing snippets, use the GitLab UI or the snippets API through glab api. Triggers on snippet, gist, code snippet, share code, create snippet.
Comprehensive code review checklist for Go projects. Evaluates code quality, idiomatic patterns, error handling, naming, package structure, and test coverage. Use when reviewing Go code, PRs, or before merging changes. Trigger examples: "review this code", "check this PR", "code review", "review Go file". Do NOT use for security-specific audits (use go-security-audit) or performance-specific analysis (use go-performance-review).
GoldRush Streaming API — real-time blockchain data via GraphQL subscriptions over WebSocket. Use this skill whenever the user needs live price feeds (OHLCV candles), real-time DEX pair monitoring (new pairs, liquidity updates), wallet activity streaming, decoded swap/transfer events, token search, trader PnL analysis, or any sub-second latency blockchain event push. This is the right skill for trading bots, live dashboards, alerting systems, copy-trading, DEX sniping, and real-time analytics. Also covers one-time GraphQL queries for token discovery and profitability analysis. If the user needs historical data, batch queries, or paginated REST results, use goldrush-foundational-api instead. If the user needs pay-per-request access without an API key, use goldrush-x402 instead.
Entry skill for the Headless Ghidra YAML-first reverse-engineering pipeline. Use when the user asks to analyze, decompile, triage, resume, or iterate on a binary target with Ghidra/headless-ghidra. Reads artifacts/<target>/pipeline-state.yaml, routes P0–P4 phase skills, runs gate checks, and manages review pauses. Performs zero analysis work itself.
Routes Meta VR and Horizon OS simulator work to the right `metavr` command group, and drives a running Meta XR Simulator via `metavr xrsim` — runtime, device, input, compositor layers and MP4 recording. Use when a goal concerns a simulated headset rather than a physical one, when choosing between `xrsim`, `ssim`, `capture` and `tapedeck`, or when a `metavr xrsim` command returns a connection error. For installing the simulator or configuring it into a Unity, Unreal or native OpenXR project, use hz-xr-simulator-install-and-configure instead.
Installs and configures the Meta XR Simulator for testing Meta VR and Horizon OS apps without a physical device. Use when installing the simulator or integrating it with Unity, Unreal, or native OpenXR projects. For controlling a running simulator, use hz-xr-simulator-control. Build paths: Unity, Unreal, and native OpenXR; route Standard Android, Meta Spatial SDK, and WebXR work through hz-quest-verify-first.
Unified GPU kernel operator generation and optimization skill. Automatically detects the target repository type (FlagGems, vLLM, or general Python/Triton) and dispatches to the appropriate specialized sub-skill. Includes operator generation, MCP-based iterative optimization, and feedback submission sub-skills. Use this skill when the user wants to generate or optimize a GPU kernel operator, create a Triton kernel, or says things like "generate an operator", "create a kernel for X", "optimize triton kernel", or "/kernelgen-flagos".
Odoo 16 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work involves Odoo 16 or custom addons—even if the user only pastes a traceback, mentions addons/ or __manifest__.py, describes form/tree/kanban/XML errors, HTTP controllers, or business rules on models—including building features, fixing bugs, refactoring, or reviewing addon code. Includes CSS/SCSS asset authoring and review for Odoo addons.
Build OpenTelemetry collector configs, instrument services, transform telemetry with OTTL, and debug missing traces, metrics, or logs. Use for OTel/otelcol collector config, OTLP export, SDK instrumentation, sampling, cardinality, TLS/PII controls, Kubernetes/Helm values.yaml deployments, collector health and alerts, and AI coding-agent telemetry (Claude Code, Codex, Gemini CLI, Antigravity, GitHub Copilot, Cursor).
Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for “instrument my code”, “add opik tracing”, “add observability”, “trace my agent”. Not for building a new app from scratch, or a review-only pass with no code changes.
Help with RAP (RESTful ABAP Programming Model) development including behavior definitions, EML statements, managed and unmanaged BOs, draft handling, actions, validations, determinations, side effects, and business events. Use when users ask about RAP, BDEF, BDL, EML, behavior definitions, behavior pools, managed BO, unmanaged BO, draft-enabled BO, RAP actions, RAP validations, RAP determinations, RAP side effects, RAP business events, create/read/update/delete in RAP, or building transactional Fiori apps with ABAP Cloud. Triggers include "create a RAP BO", "write a behavior definition", "EML syntax", "managed vs unmanaged", "enable draft", "add an action", "add a validation", "RAP handler method", or "RAP saver class".
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
General guidelines for building a robust webhook receiver/handler: verifying signatures, raw-body access, replay protection, async processing, retries and endpoint auto-disabling. Use whenever you write, review, or debug a handler that consumes incoming webhooks from any provider.
Review an existing PRD for soundness, product quality and acceptance criteria. Not for writing a PRD from scratch, reviewing technical plans or code diffs. Verify the current code, requirements, experience, UAT and phasing, and save a report by default
Use when reviewing/judging a published, consumer-facing API reference an integrating developer calls an API from — deciding if they can integrate from it. A gate, not authoring. Judges against a single-sourced 11-condition usability + contract-consistency bar: getting-started + auth reach a first call; every api-spec operation (incl. events/webhooks) is documented with purpose + typed params + a worked example + errors; errors first-class; rate-limits + pagination documented where applicable; versioning + deprecation/sunset stated; the reference is CONSISTENT WITH THE HANDED-IN api-spec (no drift, no fabricated endpoint — the load-bearing check); samples runnable; an amendment re-syncs to the changed contract. Emits exactly `VERDICT: approve|revise` plus actionable findings; approves a proportionally-sized reference, revises on a named gap. Not authoring it, not the end-user user-guide, not the developer-adoption guide, not the engineering api-spec (reviewing-api-spec).
Use when reviewing or judging a finished or amended developer guide — the adoption + integration narrative for a developer-tool product (SDK/library/CLI/framework/API platform). Decides whether a developer can install, integrate, and operate the tool from the guide alone. A gate, not authoring. Judges it against a single-sourced 14-condition adoptability + accuracy bar: a signposted start-here + a verifiable first success; concepts before recipes; how-tos cover the handed-in scenarios; samples runnable + accurate to the CURRENT tool (no fabricated/stale endpoints); LINKS INTO the api-reference, never duplicates it; Diataxis modes typed; a troubleshooting path; an amend reviewed delta-scoped. Emits exactly `VERDICT: approve|revise` + actionable findings; approves a guide meeting the bar (no false-revise on a thin one), revises only on a named gap. Not for authoring it, the end-user user-guide, the endpoint catalog (api-reference review), or engineering design docs (design-review).
Build integrations with Rocket.net's WordPress hosting API. Manage sites, domains, backups, plugins, themes, CDN cache, FTP accounts, and more programmatically. Use when: building WordPress hosting management tools, automating site deployment, creating reseller portals, managing multiple WordPress sites, integrating with Rocket.net hosting services, automating backup workflows, or building custom control panels.
Design, implement, review, and validate embedded Rust firmware, including no_std, targets, runtime and startup, embedded-hal drivers, interrupts, DMA, shared state, async executors, hardware mocks, cross-compilation, flashing, and hardware acceptance evidence. Use when users ask about MCU firmware, portable drivers, HAL versions, bare-metal targets, interrupts, Embassy, RTIC, probe-rs, or embedded testing.
When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," "breadcrumb schema," "Google rich results," "knowledge panel," "star ratings in search," or "add structured data." Use this whenever someone wants their pages to show enhanced results in Google. For broader SEO issues, see seo-audit. For AI search optimization, see ai-seo.
Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows
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.