Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Reverse-engineer a Stitch-compatible DESIGN.md design system from existing frontend source code. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens in React, Vue, Svelte, Angular, or plain HTML/CSS, and writes a structured document that can be version-controlled, shared with the team, and used to keep future UI consistent.
Build and edit Google Slides through the google-slides MCP tools - slides, grids of cards and columns, text boxes, shapes, images, tables, styling, layout inspection, and per-slide PNG rendering. Use when creating a deck, laying out slide elements, matching a template, or verifying how a slide looks.
Based on Huawei Cloud COC (Cloud Operations Center) APIs for script management and remote execution. Supports creating custom scripts (Shell, Python, Bat) and batch execution on target host instances via UniAgent. Applicable to cloud operations automation and batch script deployment scenarios. Trigger keywords: L-instance, COC script, script management, script execution, cloud operations, custom script, batch execution; COC, script management, script execution, cloud operations (中文触发词：L实例执行脚本).
x402-gated agent inbox — send paid messages to any agent's inbox, read received messages, check inbox status, and auto-reply to paid messages with an AIBTC Inference Marketplace model. Sending requires an unlocked wallet with sBTC balance (100 sats per message); sponsored transactions mean no STX gas fees.
Sets up and manages Postgres using the clickhousectl CLI — runs a local Docker-backed Postgres for development, and creates and operates managed ClickHouse Cloud Postgres services (connections, TLS, runtime config, read replicas, failover, point-in-time restore). Use when the user wants a Postgres or PostgreSQL database for their application, a local Postgres dev environment, psql access, or a managed/production Postgres in ClickHouse Cloud, or mentions moving a local Postgres to production. Also use when migrating an existing Postgres database (Neon, Supabase, RDS, Aurora, Cloud SQL, self-hosted) into ClickHouse Cloud Postgres.
Reports bugs and feature requests against the right Infrahub-ecosystem GitHub repository. Classifies the request, routes it (with the main `opsmill/infrahub` repo as the safe fallback when in doubt), searches for existing duplicates, gathers conservative environment info for bugs, and prepares the issue for the user to review before any submission. TRIGGER when: user wants to report a bug, file an issue, request a feature, open a ticket, or escalate a problem in any opsmill/infrahub-* project (SDK, Ansible, VS Code, MCP, Helm, schema-library, sync, backup, nornir, skills). DO NOT TRIGGER when: the user wants to fix the bug themselves locally, write a test, or debug code without filing.
Provider-independent lighting direction for AI-generated images, video clips, ads, film scenes, avatars, product shots, interviews, beauty work, and social content. Use when an agent must specify, translate, maintain, troubleshoot, or QA motivated lighting, key/fill/back/rim/practical lights, hard or soft light, color temperature, exposure, contrast, time-of-day, continuity, reference strategy, or safety/accessibility risks in generated media.
Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource. Use when the user says "remind me to…", wants a one-off or recurring nudge (daily/weekly/monthly/yearly, a cron schedule, or a specific date/time), wants to be reminded to look at a dashboard, insight, experiment, feature flag, survey, notebook, replay, or error, or wants to list, change, or cancel their reminders. Covers when to pick a reminder over an alert or subscription, the one-off vs recurring vs cron schedule field mappings, timezones, and attaching a resource.
Build and deploy a Next.js, Bigfish (@alipay/bigfish), or Vite project to the Morphe service (https://morphe.zenmux.app), targeting a linux-x64-gnu runtime. Use when the user asks to deploy, ship, publish, or release a Next.js, Bigfish, or Vite app to Morphe, run "morphe deploy", or otherwise push a build to the Morphe / zenmux platform. Handles login, framework detection, Next.js standalone validation / config fixing, Bigfish static-server wrapping, Vite SPA static wrapping or custom-server (server.ts/js) esbuild bundling, building, zipping, OSS upload, CRC64 checksum, .morphe.json management, and the deploy API call.
Set up and run mutation testing with Stryker, including full-project and focused diff runs against the current review base, then use surviving mutants to strengthen weak or missing tests. Use as the end-of-phase PR-readiness gate after implementation and refactoring are complete, not inside each RED-GREEN increment. Also use when the user explicitly asks for mutation testing, Stryker, mutation score, or surviving-mutant analysis. For writing the tests themselves, see testing
Nano Banana Pro (nano-banana-pro) image generation skill. Use this skill when the user asks to "generate an image", "generate images", "create an image", "make an image", uses "nano banana", or requests multiple images like "generate 5 images". Generates images using Google's Gemini 2.5 Flash for any purpose - frontend designs, web projects, illustrations, graphics, hero images, icons, backgrounds, or standalone artwork. Invoke this skill for ANY image generation request.
(NS) Generate and adapt .gitlab-ci.yml for SaaS products with backend and frontend — test, build, E2E gate, deploy by branch. Use when the user asks for GitLab CI, pipeline setup, or CI/CD bootstrap for a monorepo product. Uses references/templates/gitlab-ci.template.yml as baseline. Out of scope for pure agent-runtime repos without backend+frontend layout.
Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents. Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename.
Olares ControlHub K8s runtime view via olares-cli cluster — inspect pods, containers, workloads, logs, jobs, cronjobs, namespaces, nodes, and middleware; exec, scale, restart, or delete K8s objects. Use for raw runtime objects and logs, not app lifecycle (market), resource metrics (dashboard), or host install.
Olares Files via olares-cli files — browse known paths; upload or download file bytes; edit, share, mount SMB/NFS, compress/extract archives, and manage Seafile sync across Drive/cache/external/cloud. Use for Olares Files and LarePass Files operations, not URL/yt-dlp/torrent download tasks (olares-knowledge).
Olares Market via olares-cli market — install, upgrade, uninstall, clone, stop, resume, restart apps; catalog, status, chart upload/download, --watch. Use for Olares app store, my apps, 我的应用, install app, restart app, upload chart, download an app chart.
Use when someone shares a mobile subscription or purchase screen and wants to know what to change, fix, test or improve — "here's my paywall", "roast this", "what should I test", a competitor screenshot, a design in progress, or an image with almost no text. Also use whenever YOU are the one designing or generating a paywall screen and were given no design reference to follow — no reference image, no existing screen to copy, no layout spec — as in "make me a paywall", "make one that converts", "will this convert?", "is this any good?"; this library is the reference in that case, and it evaluates and corrects the screen you produce. Also use when reviewing a paywall render or flow config produced by the flow-generator skill. Do not wait to be asked for a "teardown" by name.
Identify short- to medium-term opportunities worth tracking in post-earnings drift, assessing expectation revisions, price continuation, and invalidation boundaries. Suitable for post-earnings trend trading, earnings surprise tracking, and post-event watchlist management.
ONLY for Pi Agents — all other agents have their own web tools. How Pi accesses the web via the pi-web-access package — search, fetch URLs/PDFs/YouTube/GitHub. Use whenever a Pi task needs current info, docs, news, prices, or content from a specific URL.
Research and qualify onboarding team referral leads for PostHog. Use this skill when a TAE receives a lead from the onboarding team and needs a full research brief before deciding how to engage. Triggers on “research this onboarding lead”, “onboarding team referred [company]”, “look into [company] from onboarding”, “qualify this onboarding referral”, “what do we know about [company] from onboarding”, or requests to research a company from the onboarding pipeline. Also trigger when a TAE pastes a company name and says it is from the onboarding team, or says “onboarding sent me [company]”, “got a handoff for [company]”, or “[name] from onboarding sent me [company]”. This skill conducts in-depth research and qualification, then drafts outreach when the recommendation is to engage.
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
Expert-level React development with hooks, performance optimization, state management, and modern patterns. Use when the user mentions frontend, hooks, JSX, TypeScript, or Next.js, or when the task involves Modern React, State Management, Forms, or Performance Optimization.
Validates answers that depend on current external facts, including prices, versions, policies, rankings, recommendations, documentation, and availability. Use when the user asks for current, latest, verified, fact-checked, or up-to-date answers. Coordinates recency-checker and claim-verifier subagents to produce a current, qualified final answer.
Understand the defense-in-depth security architecture of Secure Vibe Coding OS. Use this skill when you need to understand the overall security approach, the 5-layer security stack, OWASP scoring, or when to use other security skills. Triggers include "security architecture", "defense in depth", "security layers", "how does security work", "OWASP score", "security overview", "security principles".
Analyze social media data for individual posts, series, weekly or monthly periods, and produce actionable reviews. Use to read platform dashboard screenshots, CSVs, spreadsheets, public links, or user-provided data; calculate follow efficiency and deep engagement; compare against same-platform baselines; attribute results to topics, titles, covers, openings, structure, publishing time, tags, and calls to action; and recommend whether to double down, repackage, adapt, stop, or keep collecting samples.
Save creative milestones from self-media work as files, manage versions, verify paths, generate complete publishing packages, and update the content index. Use to save a complete first draft for a platform, a multi-platform collection, short-video scripts, storyboards, final drafts, publishing packages, and retrospective reports, or when the user says “save this,” “organize the deliverables,” “archive,” or “generate a publishing checklist.” Do not save title tweaks, sentence deletions, or temporary alternatives as separate versions.
Signals scout for PostHog distributed tracing (APM / OpenTelemetry spans). Watches per-service RED metrics for error-rate and latency regressions, new error signatures, and traffic cliffs, and audits for standing performance issues: N+1 calls, expensive query shapes, and caching candidates
Use when a solo founder is building their GTM motion, wants to scale without hiring, or needs to design an AI agent team for go-to-market. Also use when the user mentions “solo founder,” “one-person startup,” “solopreneur,” “bootstrapped,” “no team,” “AI agents as team,” “scaling without hiring,” “founder-led sales,” “lean GTM,” “one-person company,” or “no employees.” This skill covers the complete solo founder GTM playbook, from stack selection through agent team design, revenue-stage transitions, time allocation, and when to finally hire.
Diagnosticar bugs, regressões, falhas intermitentes e problemas de performance por reprodução, minimização, hipótese e instrumentação. Use quando o usuário pedir diagnóstico ou relatar algo quebrado; não implementar correção quando o pedido for somente diagnóstico.
Use when working with post-purchase flows in Spree 6 — returns (money back), exchanges (different items), and claims (damaged / missing / wrong item, refund or replacement without the goods coming back). Covers Spree::Return / Spree::Exchange / Spree::Claim, their statuses and workflows, return windows per market and staff overrides, custom return policy via the returns.create.validate hook, receiving and restocking (resellable), refunds to the original payment vs store credit, prepaid return labels, return and claim reasons, events, and the Store/Admin API endpoints. Common phrasings include "RMA", "return window", "30-day returns", "final sale items can't be returned", "restock returned items", "refund a return", "store credit refund", "exchange for a different size", "item arrived damaged", "send a replacement", "return label", "ReturnAuthorization", "CustomerReturn", "Reimbursement"
Universal Strava API integration for fitness data management. Use when working with Strava activities, athlete profiles, segments, routes, clubs, or any fitness tracking data. Triggers on requests to get, create, or update activities, analyze training stats, export routes, explore segments, or interact with Strava data programmatically
SwiftUI skills for iOS 26: Liquid Glass, a UI/UX review engine, component patterns, on-device AI (Foundation Models), and vendored Pro skills for SwiftUI review, Swift Testing, Swift concurrency, and SwiftData. The author states they were verified against WWDC 2025 docs and Xcode 26.3. Different from swiftui-patterns, which focuses on general SwiftUI best practices.
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.