Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Deep analysis debugging mode for complex issues. Activates a methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.
Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against deterministic fixtures or real sites, diagnosing rendering, geometry, resource, identity, or transport failures, or choosing the correct CLI, CDP, MCP, rendering, or stealth workflow.
Design and implement comprehensive testing strategies. Use when setting up tests, choosing test types, implementing TDD, or improving code quality. Covers unit tests, integration tests, E2E tests, test-driven development, and testing best practices.
Two-mode Figma design system skill — Inspect mode (read-only WCAG audit, component scoring, detached-instance detection, handoff docs) and Build mode (phased creation with variable bindings, slots, descriptions), with optional sync to tokens.css + AI rules. Needs the figma-use skill and the Figma MCP server.
Write, review, debug, and improve tests with Allure agent mode by preserving useful coverage, planning scope, creating per-run expectations, running targeted tests, inspecting existing Allure results or dumps from local or CI runs, reviewing runtime evidence, and enriching weak test evidence. Use whenever you author, modify, or review tests — including as a step inside a larger feature, bug-fix, or implementation task, not only when test work is the headline request; load it before writing assertions rather than authoring from general knowledge.
Use when profiling async/await performance, diagnosing actor contention, or investigating thread pool exhaustion. Covers the Swift Concurrency Instruments template, task visualization, actor contention analysis, and thread pool debugging
Expert-level CodeQL for static analysis, vulnerability detection, and security code scanning. Use when the user mentions static analysis, SAST, vulnerability detection, or github security, or when the task involves writing CodeQL queries, building a CodeQL database, taint tracking, or scanning for injection and hardcoded credentials
Create, view, manage, approve, and merge GitLab merge requests. Use when working with MRs: creating from branches/issues, reviewing, approving, adding comments, resolving discussion threads, checking out locally, viewing diffs, rebasing, merging, or managing state. Triggers on merge request, MR, pull request, PR, review, approve, merge, resolve thread.
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says “generate Python experiment,” “write an SDK experiment,” “create a ddtrace experiment,” “Python notebook experiment,” “use the LLM Obs SDK,” or has `ddtrace` installed and wants idiomatic SDK code.
Review MATLAB code for quality, performance, maintainability, and adherence to MathWorks coding standards. Uses check_matlab_code and matlab_coding_guidelines. Use when reviewing code, checking style, finding code smells, assessing quality, or preparing code for handoff or publication.
Guide for testing Polar payment integrations using the sandbox environment. Use this skill when: (1) Setting up the Polar sandbox for development; (2) Testing checkout flows without real payments; (3) Using Stripe test cards with Polar; (4) Writing integration tests for payment flows; (5) Testing webhooks locally with the Polar CLI (`polar listen`, `polar trigger`) and generating webhook fixtures; (6) Mocking Polar in unit tests; (7) Setting up CI/CD pipelines with Polar sandbox; (8) Debugging payment issues in sandbox.
Run a product multi-point inspection — assess a shipping product (app, website, or feature) as-built across 10 stations and produce a red/yellow/green inspection report with a prioritized work order. Use when the user asks to inspect, assess, audit, or health-check a product or experience, run the inspection or a specific station, or asks "why is my product's check engine light on?" Companion to ds-inspection — that one inspects the design system; this one inspects the products built with it.
Follow-up Signals scout for the inbox itself. Attaches a check to each newly resolved report, spot-checks a couple of settled fixes with fresh probes, answers the checks it is dispatched for, and reports when a fix didn't hold, plus a gated escalation check on dismissed reports.
You are a GitHub issue resolution expert specializing in systematic bug investigation, feature implementation, and collaborative development workflows. Your expertise spans issue triage, root cause analysis, testing, and pull request preparation.
Official Vercel agent skills for UI review and React work: Web Interface Guidelines compliance review, writing guidelines review, React/Next.js performance, component composition patterns, and React View Transitions. Lives in the vercel-labs/agent-skills collection.
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes
Expert knowledge for Azure App Testing development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when running Azure Load Testing, Playwright Workspaces, JMeter/Locust tests, private endpoint/VNet tests, CI/CD runs, and other Azure App Testing development tasks. Not for Azure Test Plans (use azure-test-plans), Azure DevOps (use azure-devops), Azure Pipelines (use azure-pipelines), or Azure App Service (use azure-app-service).
Structures and organizes Storybook files for scalability using battle-tested patterns from Cassondra Roberts' "A Storybook format that scales with you". Covers story definitions, template composition, controls/args, visual regression with Chromatic, component documentation, and CSF conventions. Activates on any Storybook question — file structure, controls, args, or component documentation.
Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.
Use when someone asks what is true of a whole project ('project audit', 'аудит проекта'): finished, broken, unexplored. Probes it, reads production evidence, leaves a JSON sidecar. Read-only. Not for: one deliverable in a run, a diff review, a skill's construction; 'без диагностики' opts out.
Review code phong cách SENIOR 10 năm — bốn mục security · performance · naming · logic, mỗi mục cho ĐIỂM/10 + LỖI NẶNG NHẤT + CÁCH SỬA, rồi một kết luận PASS-sang-bước-kế hay CẦN-SỬA. Mục logic tìm bug (null/rỗng/âm/overflow, off-by-one, race) và SINH một test-case tái hiện cho mỗi bug (đặt tên qc-*), các test đó auto-chạy qua hook tất định (0-token, không LLM). Gọi khi user nói "qc code", "review code", "soi code", "chấm điểm code", "kiểm tra chất lượng code", "/qc-code". KHÁC /orca-sec-scans (Trivy quét TĨNH — vuln/misconfig/secret) và /code-review built-in (review tổng quát): qc-code là format senior bốn-mục-chấm-điểm-verdict + sinh test tái hiện. Mặc định review DIFF hiện tại; chỉ định file khi cần.
Performs a structured security code review against OWASP ASVS 4.0.3 verification requirements and CWE Top 25. Auto-invoked on pull request reviews, when code touching authentication, authorization, cryptography, or input handling is shared. Produces findings mapped to ASVS controls and CWE identifiers with severity ratings and specific remediation guidance.
Troubleshoot and optimize Ascend C operator performance. Use when developing, reviewing, or optimizing Ascend C kernel operators, or when keywords such as Ascend C performance optimization, operator optimization, tiling, pipelining, data transfer, memory optimization, NPU, or Ascend are mentioned
Helps AI coding assistants write modern Jetpack Compose: correct state, side effects, performance-aware modifiers, Navigation 3, Paging 3 in Compose, coroutines on lifecycle, animations, UI tests, focus/keyboard navigation, Compose Multiplatform boundaries, idiomatic Kotlin, and well-shaped composable APIs. Targets the mistakes LLMs actually make in Compose code. Use when reading, writing, or reviewing Compose projects.
Checks whether a developer understands a pull request before they merge it, especially code an AI agent wrote. It reviews the author rather than the code by questioning them about changes they can't explain. Use whenever someone is about to open, submit, review, or merge a PR, branch, or diff containing AI-generated code, or wants to ensure they understand a change before shipping.
Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling into individual recordings, and turning real, corroborated issues into PostHog tasks, insights, or an investigating-replay hand-off.\nTRIGGER when: user wants to pull/read/triage Replay Vision observations, asks \"what has my scanner found\", wants to act on or summarize scanner findings, turn observations into tasks/work, or points at a /replay-vision/<scanner-id> URL.\nDO NOT TRIGGER when: creating or sizing a scanner (use creating-replay-vision-scanners), running a one-off scan you don't then analyse, or authoring a signals scout.
PR and MR workflows for GitHub (gh) and GitLab (glab). Creation, review comment handling, thread resolution, review state queries, merging, cost-aware bot review rounds (GitHub: Copilot, CodeRabbit), and Copilot code review configuration (rulesets, custom instructions, billing). Use when creating PRs/MRs, addressing review feedback, resolving threads, looping bot reviews, checking approvals, querying PR data, configuring Copilot reviews, or configuring gh/glab read-only allowlists. Not for git commits (git-commit), CI/CD status (git-ci), local pre-push CodeRabbit CLI reviews (coderabbit), or general git ops
Offline compliance and hygiene scanning of an AAB or APK with `gplay preflight` — manifest flags, restricted permissions, 64-bit and 16 KB page alignment, listing assets, secrets, billing, privacy SDKs, target API floor, and size. Use before uploading a build, as a CI gate, or when diagnosing a Play rejection. Runs entirely offline with no credentials.
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.