Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to "evaluate design slop", "slop report", "is this design AI slop", "audit this landing page design", "de-slop review", or wants an objective score of how generic/machine-made a design looks. To fix text (not design), use human-ai or humanizar skills instead.
Execute implementation plans by dispatching a fresh subagent per task with two-stage review (spec compliance then code quality). Use when you have an implementation plan with mostly independent tasks and want high-quality, fast iteration within a single session.
This skill should be used to generate realistic, persona-consistent synthetic coaching and therapy session transcripts for evals, demos, and training data. It produces fictional but believable coach/client (or therapist/client) dialogue grounded in a chosen modality (ICF/GROW coaching, CBT, IFS parts work, ACT/motivational interviewing) and exports to Fathom/Granola transcript style, plain dialogue, structured JSON, or Obsidian markdown. Triggers on requests like "generate a synthetic coaching session", "make fake therapy transcripts for evals", "create demo session transcripts", "synthetic CBT dialogue", "persona-consistent coaching transcript", "test data for my session summarizer", or "mock coaching call".
Exactly ONE complete test case file (.xlsx with multiple sheets, columns Test Case ID/Description/Steps/Expected/Priority/Type) → parse into JSON, deterministically classify as ui|calc|perf|security|gap, generate a PLAN per BATCH, run through orca-graph on the user's ALREADY logged-in browser session (claude-in-chrome), record PASS/FAIL/BLOCK plus a screenshot for each TC, and export one report .xlsx tester-kit per batch (tao_report_test). Call when the user says "chạy bộ test case này", "file test case xlsx", "SIT/UAT theo file", "xuất report tester-kit", "/tc-run".
Run a read-only audit for missing, weak, stale, or mis-scoped test coverage. If the user does not name a scope, audit the full repository and identify important code paths, routes, features, services, workflows, and contracts that lack proper tests. If the user names a feature, PR, branch, route, workflow, service, bug fix, API, security-sensitive path, or risky code change, focus only on that specific scope. Use when the user asks what tests are missing, whether coverage is enough, what regression tests to add, or how to prove a change is safe. This is not a general bug audit and not a security review; it evaluates whether behavior is covered by tests.
Run and troubleshoot tests for DBHub, including unit tests, integration tests with Testcontainers, and database-specific tests. Use when asked to run tests, fix test failures, debug integration tests, troubleshoot Docker/database container issues, or add new tests. Also use when verifying code changes work correctly or when CI test failures need investigation.
Browser automation toolkit using Playwright MCP for testing web applications. Use when asked to navigate pages, click elements, fill forms, take screenshots, verify UI components, check console logs, debug frontend issues, or validate responsive design. Supports live browser interaction and accessibility snapshots.
Use when the user needs Playwright-based web application testing — screenshots, browser log analysis, interaction verification, visual regression, accessibility, and network mocking. Triggers: E2E test setup, visual regression testing, accessibility audit, Playwright configuration, page object model creation, CI test pipeline.
WordPress accessibility review for themes, blocks, plugins, and admin interfaces. Use when reviewing keyboard navigation, focus behavior, semantic HTML, ARIA usage, form labeling, screen-reader support, contrast-related implementation issues, or when user mentions "accessibility review", "a11y", "keyboard navigation", "focus management", "screen reader", "ARIA", "semantic HTML", "accessible form", or "accessible block". Detects implementation-level accessibility issues in frontend output, block markup, admin screens, and interactive UI behavior.
WordPress theme code review and block theme development patterns for WordPress 6.6+. Use when reviewing theme code, auditing theme.json schema, checking template hierarchy, validating block templates, analyzing global styles, verifying style variations, reviewing template parts, detecting hardcoded styles, checking classic-to-block migration, or when user mentions "theme review", "theme development", "theme.json", "block theme", "FSE", "Full Site Editing", "template parts", "template hierarchy", "global styles", "style variations", "classic theme", "child theme", "theme patterns", "theme.json validation", "hardcoded styles", "useRootPaddingAwareAlignments", "classic-to-block", "hybrid theme", "WordPress.org theme". Detects issues in theme.json structure, block templates, template parts, style systems, and classic theme migration patterns.
Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them only when asked. Use when the user asks to review local changes, wants a self-review before opening a pull request, asks whether a change breaks the public API or needs tests, samples or docs, or asks what is wrong with the current diff. Required for changes to public APIs, core architecture (Runner, Workflow, BaseNode), new features and major refactors. Don't use for a single style nit (use adk-style), for diagnosing a failing test or a misbehaving agent at runtime (use adk-debug), or for wording a commit message or PR description (use adk-git).
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
GitHub work via gh CLI: PRs, review conversations, CI failures, repo state. Use when inspecting a PR, reading a review (bodies, comments, inline threads), debugging CI (finding which run failed, why a check or Actions run is red, reading job logs), or composing non-trivial gh commands. Scripts cover what raw gh can't do (thread resolution state) or reliably fumbles (PR snapshots, CI log drilldown); use raw gh directly for everything else.
Use whenever writing, editing, or reviewing code that carries comments or doc blocks, in any language. Covers the test a comment has to pass to earn its place, the comments to delete (restating the code, listing fields a doc block sits above, boilerplate copied across files, a comment that drifted away from the line it explains), how to cut a four-line comment down to one without losing the reason, and what belongs in a doc block versus what the signature already says. Also covers the comments that always stay: todos, license headers, security boundaries, workarounds, and references to an external spec. Apply on every code change, not only when asked to clean up comments.
Starting from a fixed point (commit, branch, tag, or merge-base), review changes along two axes — standards (does the code follow the repo's documented coding standards?) and spec (does the code match the requirements of the original issue/PRD?). The two review lines run in parallel sub-agents and report results side by side. Use when the user wants to review a branch, a PR, in-progress changes, or asks to "review from X".
Review a shipped diff for quality and whether it matches the request. Quality checks use /taste and /architecture (keep it simple, keep jobs apart, honest names, trust the server, types tell the truth, and related rules), a correctness hunt for reachable bugs, plus a pass for stale file and symbol names after renames, mixed-parent file dumps, and new env synonyms (`FRONTEND_URL` when `SITE_URL` already exists). Parallel Standards and Spec Tasks, evidence-backed findings, and a bounded fix path. Use for branch, PR, or parent-owned review. User must invoke (not auto).
Craft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers (=========), class organization, naming conventions (services, queue jobs, records, events, enums), defineRules() and validation, beforePrepare() and addSelect(), MemoizableArray, DateTimeHelper vs Carbon, strict_types/declare(strict_types=1), short nullable notation (?string), typed properties, void returns, control flow (early returns, match over switch), CP Twig template conventions, form macros, translations (Craft::t), ECS/PHPStan config, scaffolding commands, and the verification checklist.
Provides comprehensive guidance for Cypress end-to-end testing including commands, assertions, component testing, CI/CD integration, and best practices. Use when the user asks about Cypress, needs to write E2E tests, component tests, or configure Cypress for testing.
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when: standard troubleshooting fails, systematic root cause analysis needed, complex bugs, mysterious errors.
Find deepening opportunities in a codebase, surfacing architectural friction and proposing refactors that turn shallow modules into deep ones. Use when the user wants to improve architecture, make a codebase more testable, consolidate tightly-coupled modules, or make it safer for AI agents to navigate and change.
Development workflows for WordPress ActivityPub plugin including wp-env setup, testing commands, linting, and build processes. Use when setting up development environment, running tests, checking code quality, building assets, or working with wp-env.
Compare two Kernel profile snapshots to investigate behavioral differences. Use when an issue (e.g. login failure, captcha, broken automation, vendor mismatch) reproduces on one profile but not another, or when a "good" vs "bad" profile needs to be diffed. Takes two profile IDs/names plus an issue description, downloads and extracts both profiles via the Kernel CLI, and surfaces differences in cookies, storage, preferences, extensions, and login state that could explain the issue.
Get a rigorous read-only second opinion on finished work through the host's available reviewer capabilities, preferably from a different model provider. Falls back to a fresh same-provider agent only when necessary and labels the reduced independence. Every review includes a mandatory scope-fidelity check against the original requirements — unrequested additions, unrequested removals, and deleted or weakened tests. Use when asked to double-check, verify, cross-check, or get a second opinion, and before shipping high-stakes or complex work.
Profile and improve Flutter runtime performance using profile-mode evidence, DevTools, frame analysis, rebuild inspection, memory, and app-size tools. Use for jank, slow startup, excessive work, leaks, or size regressions; route production logs, errors, and traces to flutter-observability.
Analyzes a game system against design principles — economy health metrics, difficulty curve, reward schedules, and progression cost curves. Flags imbalances with severity levels. Use after creating an MVP plan with game-architect. Extract the analysis scope (economy/difficulty/progression/rewards/all) from the user's message.
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.
Script-First design system workflow. Uses a deterministic auditor script to detect frameworks, inventory components, and detect design drift (hardcoded hex, arbitrary Tailwind). Provides a clear report for the agent to judge and implement a Kitchen Sink page.
Review and guide UI implementations using the 21 Laws of UX. Identifies usability issues in HTML, CSS, and JavaScript by applying established cognitive, visual, and behavioral principles. Use when reviewing UI code, building new interfaces, or auditing user experience.
Deploy a temporary n8n test instance (or generate a local docker run command) via the internal "Nathan" bot, from the repo instead of Slack. Use after opening a PR to offer the user a live test instance, or whenever someone asks to spin up / deploy a test instance for a branch.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
Build browser automation and web scraping with Playwright on your local machine. Prevents 10 documented errors including CI timeout hangs, extension testing failures, and Ubuntu compatibility issues. Includes stealth mode for anti-bot bypass, authenticated sessions, infinite scroll handling, screenshot/PDF generation, and v1.57 Speedboard performance analysis. Use when: automating browsers, scraping protected sites, testing with real IPs, bypassing bot detection, generating screenshots/PDFs, or troubleshooting "target closed", "page.pause() hangs CI", "permission prompts block tests", or "Ubuntu 25.10 installation" errors.
GPU kernel profiling workflow across supported kernel implementation languages. Provides commands for all 4 profiling modes (annotation, event, ncu, nsys), metric interpretation tables, bottleneck identification rules, and the output contract for returning compact results to the orchestrator. Use when: (1) profiling a kernel version, (2) interpreting profiling artifacts/reports, (3) comparing kernel versions, (4) identifying bottlenecks and optimization opportunities, (5) documenting performance in the development log.
Use when writing or reviewing tests for Python behavior, contracts, async lifecycles, or reliability paths. Also use when tests are flaky, coupled to implementation details, missing regression coverage, slow to run, or when unclear what tests a change needs. Use for multi-Python version testing (nox) and free-threaded Python thread-safety validation.
Chaos engineering principles, controlled failure injection, resilience testing, and system recovery validation. Use when testing distributed systems, building confidence in fault tolerance, or validating disaster recovery.
Orchestration skill for enterprise integration testing across SAP, middleware, WMS, and backend systems. Covers E2E enterprise flows, SAP-specific patterns (RFC, BAPI, IDoc, OData, Fiori), cross-system data validation, and enterprise quality gates.
Apply the Holistic Testing Model evolved with PACTS (Proactive, Autonomous, Collaborative, Targeted, Structured) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality 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.