Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
When a founder needs to qualify inbound leads, define their ICP, build a lead scoring model, set MQL criteria, or route prospects through pipeline stages. Activate when the user mentions lead scoring, ICP, MQL, SQL, lead qualification, inbound leads, or pipeline design.
Classify whether user intent was satisfied in a Datadog LLM Obs trace or session. Three modes: (1) session_id — classify a single CMD+I assistant session with RUM; (2) trace_id — classify a single LLM Obs trace without RUM; (3) ml_app — sample and classify multiple sessions or traces from a given LLM app. Output is compact by default (verdict + one-sentence reason). Use when evaluating satisfaction, classifying sessions/traces, labeling data, or generating signal for llm-obs-eval-pipeline or llm-obs-trace-rca.
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
Pre-member journey of a two-sided trust marketplace — from anonymous landing through onboarding, registration, and the paid-membership paywall. Covers anonymous signal inference, what pet owners specifically need to validate before paying (safety, availability, competence, effort, local cost comparison), what pet sitters specifically need to validate (opportunity, first-stay path, daily commitment, hidden costs), information-asymmetry closure, progressive profile building, social proof, conversion psychology, onboarding intent capture, identity stitching, and pre-member measurement. Triggers on tasks involving visitor-to-member conversion, anonymous personalisation, onboarding flow design, paywall timing, pre-member ranking, or any question about what a pet owner or pet sitter needs to see before paying. Use this skill BEFORE marketplace-personalisation and marketplace-search-recsys-planning.
Runs a sequenced monolith-to-modular pipeline that sizes and inventories components, finds shared domain duplication, addresses flattening and hierarchy issues, analyzes coupling, then groups components into candidate domain-aligned units, with optional embedded DDD strategic analysis for bounded contexts. Use when asking how to split a monolith, size components before extraction, find duplicated domain logic, clean up module hierarchy, measure coupling between modules, or group components into services. Do NOT use for phased extraction roadmaps or prioritization without the prior analysis steps (use decomposition-planning-roadmap after this pipeline), end-to-end legacy migration strategy writeups (use legacy-migration-planner), pure infrastructure capacity sizing, or when you only need DDD without the structural pipeline (install domain-analysis standalone).
Generate code using Nx generators — scaffold projects, libraries, features, or run workspace-specific generators with proper discovery, validation, and verification. Use when user says "create a new library", "scaffold a component", "generate code with Nx", "run a generator", "nx generate", or any code scaffolding task in a monorepo. Prefers local workspace-plugin generators over external plugins. Do NOT use for running build/test/lint tasks (use nx-run-tasks) or workspace configuration (use nx-workspace).
Olares Settings via olares-cli settings — mirror the Settings SPA: users, apps, VPN, network, backup, integrations, GPU/compute, search-index directories/rebuild, and me/whoami. Use for system or post-install app configuration; not for querying file contents with olares-search.
Apply realistic PBR textures from PolyHaven to any Blender object. Supports metals, wood, concrete, fabric, and more. Trigger when asked to texture an object, apply a material from PolyHaven, make something look like metal/wood/marble, or change object surface.
Every Trustpilot review surface, plus the local SQLite database and balanced good-and-bad agent bundle no other... Trigger phrases: `trustpilot reviews for <company>`, `what do customers say about <company>`, `good and bad reviews for <company>`, `trustscore for <company>`, `is <company> trustworthy`, `use trustpilot`, `run trustpilot`.
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.
Integration with protocols.io API for managing scientific protocols. Use this skill when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Enforces the path from a green CI run to a shipped build — pubspec `version: x.y.z+N` as the single source of versionName/versionCode (monotonic, never reused), the release artifact verified on real hardware, signing and store API keys that never enter the repo, `--obfuscate --split-debug-info` with symbols archived per build or that release's crash reports are permanently unreadable, a permission set audited from the MERGED manifest and asserted whole, store declarations (Data Safety, nutrition labels, privacy manifests) provable in the repo and read back rather than trusted, size and cold-start budgets, and a staged rollout with a halt plan. Use when cutting or tagging a release, editing `android/app/build.gradle(.kts)`, `key.properties`, `AndroidManifest.xml`, `Info.plist` or `PrivacyInfo.xcprivacy`, bumping a version, uploading to Play or TestFlight, writing store-listing or privacy copy, symbolizing a crash, chasing size, or diagnosing an upload rejection or a blocked submission.
Research and compile the latest AI news from across the industry. Use this skill when asked to find AI news, get AI updates, research what's happening in AI, check for AI announcements, or gather intelligence on AI companies. Triggers include requests for "AI news", "latest AI developments", "what's new in AI", "AI industry updates", or news about specific AI companies (OpenAI, Anthropic, Google, Microsoft, Meta, Amazon, Nvidia, xAI, Mistral, Cohere, Apple, Salesforce).
Foundational software design principles applied specifically to robotics module development. Use this skill when designing robot software modules, structuring codebases, making architecture decisions, reviewing robotics code, or building reusable robotics libraries. Trigger whenever the user mentions SOLID principles for robots, modular robotics software, clean architecture for robots, dependency injection in robotics, interface design for hardware, real-time design constraints, error handling strategies for robots, configuration management, separation of concerns in perception-planning-control, composability of robot behaviors, or any discussion of software craftsmanship in a robotics context. Also trigger for code reviews of robotics code, refactoring robot software, or designing APIs for robotics libraries.
Simplifies, polishes, and declutters code without changing behavior. Use when asked to simplify, clean up, refactor, declutter, remove dead code or AI slop, or improve readability, including analysis-only simplification reports and code pasted inline.
Diagnose and improve performance with budgets, measurement, profiling, load testing, Web Vitals, and regression analysis. Use for slowness, throughput, resource usage, bundles, or capacity; do not optimize without a baseline and hypothesis
Use when customizing the Spree 6 admin—the React dashboard (`@spree/dashboard`, Developer Preview) in `apps/dashboard/`—from inside the project. Covers `defineDashboardPlugin` in `src/plugins.ts`, sidebar/settings nav, custom pages/routes, slot widgets on built-in pages, table columns/filters, extension form fields and custom field widgets, permission gating, calling the Admin API (`adminClient`, store-scoped query keys, 422 mapping), exposing a new attribute end-to-end, theming tokens, translations, Vitest/Playwright tests and deployment. Common phrasings include “add a page to the admin”, “admin sidebar item”, “add a column to the products table”, “add a card to the product page”, “custom field on the product form”, “hide menu item by permission”, “restyle the admin”, “dashboard plugin”, “spree add dashboard”, “React admin”, “where did spree_admin go”.
Use when packaging Spree 6 React dashboard customizations as a redistributable npm plugin (optionally paired with a Rails extension gem) that other Spree stores install — scaffolding with `npx @spree/cli plugin new`, file routes and route collisions, peerDependencies against `@spree/dashboard-core`/`-ui`, prebuilt vs source publishing, `sideEffects`, the `spree.dashboard.plugin` package.json marker, auto-discovery via `virtual:spree-dashboard-plugins` vs an explicit whitelist, Tailwind class scanning, `definePlugin(config)` factories, Changesets, and the backend gem half. Common phrasings include "publish a dashboard plugin", "npm package for the Spree admin", "spree plugin new", "share admin screens across stores", "plugin not showing up", "Dashboard route collision", "plugin styles missing", "marketplace extension with admin UI".
Use when the user is working with money on a Spree 6 cart or order — how `total` is built, the typed money rows (`Spree::TaxLine`, `Spree::Discount`, `Spree::Fee`), totals columns (`item_total`, `discount_total`, `delivery_total`, `fee_total`, `included_tax_total` vs `additional_tax_total`, `adjustment_total`, `amount_due`), `Spree::Carts::RecalculateTotals`, custom adjusters (`Spree.adjusters`), fees and customs duties, manual discounts and fees on placed orders, or rendering an order summary. Common phrasings include "order total is wrong", "totals don't add up", "tax counted twice", "add a surcharge / handling fee / gift wrap fee", "add a custom fee", "where are adjustments", "Spree::Adjustment missing", "recalculate order totals", "edit a placed order's discount", "why did my discount disappear", "display_total", "money as string", "duties".
Use when the user is configuring or extending tax in Spree 6 — tax categories (`tax_code`), tax rates by `country_code`/`state_code`, VAT-inclusive vs added-on pricing (`included_in_price`, market `tax_inclusive`), per-market tax providers and `Spree.default_tax_provider`, writing a custom tax provider (`estimate`/`commit`/`void`/`refund`), `Spree::TaxLine` rows, the `carts.recalculate_totals.set_tax_line_context` hook, B2B tax identifiers (VAT numbers) and exemption certificates, or connecting Avalara/an external tax engine. Common phrasings include "tax not calculated", "tax is zero", "VAT included in price", "EU VAT", "US sales tax", "tax per state", "integrate Avalara / TaxJar / Stripe Tax", "custom tax calculation", "tax exempt customer", "reverse charge", "VAT number at checkout", "tax on shipping", "tax on fees"
Use when the user wants to run custom code inside a Spree 6 business flow—for example, vetoing an add-to-cart, blocking checkout completion, enforcing a purchase limit or B2B rule, adding data to tax or promotion calculations, reacting inside the order-placement transaction, customizing return eligibility, or writing a new multi-step operation with compensation and gateway calls. Common phrasings include "Spree.hooks.register", "workflow hook", "carts.add_item.validate", "carts.complete.before_finalize", "set_tax_line_context", "reject!", "Spree::Workflow", "step / external_step / on_flow_failure", "run_hooks", "halt!", "has_status", "add_status", "state machine replacement", "where do I put business logic", "step.spree_workflow", and "trace a workflow". Covers services vs. workflows, the three hook kinds, the hook catalog, writing your own workflow, statuses, instrumentation, and testing. Reach for this before swapping a class via Spree.dependencies or decorating a model.
Starchild Auth SDK: add OAuth login to any web app with one SDK. Use when integrating Starchild login into a project (e.g. add Starchild sign-in to my React app, set up OAuth with iamstarchild.com, implement login/logout with Starchild Auth SDK). Also use for local OAuth/CORS testing guidance (localhost:6066 web, third-party localhost origins, browser vs Node)
Use when validating a startup idea before building. Produces evidence-based GO/NO-GO decisions using a 9-dimension scorecard (problem, market, timing, moat, unit economics, founder-market fit, feasibility, GTM, risk), a validation ladder (interviews -> smoke test -> concierge/WoZ -> paid pilot), and riskiest-assumption-first experiments
Generates agent-friendly DESIGN.md files for Google Stitch that enforce premium, anti-generic UI standards: strict typography, calibrated color, asymmetric layouts, and perpetual micro-motion. The DESIGN.md then steers Stitch's screen generation away from generic AI defaults.
Set up a SendGrid account for email delivery. Covers API key creation (SG.-prefix), domain authentication (DKIM/SPF via CNAME records), Single Sender Verification for testing, SDK installation, and the relationship between SendGrid and Twilio credentials. Use before any other SendGrid skill. This skill is for SendGrid only — not the Twilio Email API (comms.twilio.com).
Diagnostic and advisory skill for email deliverability problems. Use when a developer asks why emails are going to spam, not reaching the inbox, getting blocked, bouncing, or how to improve sender reputation — with or without a specified platform. Covers SendGrid-specific tooling: SPF, DKIM, DMARC, BIMI, IP warmup, list hygiene, bounce/spam rate thresholds, and Engagement Quality Score (SEQ). Do NOT use for Twilio Email (comms.twilio.com / Account SID + Auth Token) — use twilio-email-deliverability-advisor instead. Do NOT use for general email sending questions — use twilio-sendgrid-email-send (SendGrid) or twilio-email-deliverability-advisor instead.
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.