Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Generates PHPUnit tests in PHP. Covers assertions, data providers, mocking, and test doubles. Use when the user mentions "PHPUnit", "TestCase", "assertEquals", or "PHP test". Triggers on: "PHPUnit", "TestCase PHP", "assertEquals PHP", "PHP unit test".
Enforces minimum quality thresholds in CI, including code coverage, linting, type checking, and security scanning. Provides required checks, PR rules, and automated enforcement. Use for “quality gates,” “CI checks,” “code quality,” or “PR requirements.”
Systematic hardware debugging guide for Arduino/ESP32/RP2040 circuits. Use when user reports: circuit not working, components getting hot, no power, intermittent failures, unexpected behavior, sensor not responding, LED not lighting, motor not spinning. Guides through power checks, continuity testing, signal tracing, and component isolation using multimeter techniques.
Deep audit of a Frappe app for security, correctness, and customization defects. Runs every security scope and every quality rule in a separate agent, verifies each candidate in a fresh context, and compiles one report. User-invoked only - run /deep-app-audit [app path] [options].
Diagnoses and fixes flaky tests by identifying root causes (timing issues, shared state, randomness, network dependencies) and provides stabilization strategies. Use for "flaky tests", "test stability", "intermittent failures", or "test debugging".
Use when encountering BUILD FAILED, test crashes, simulator hangs, stale builds, zombie xcodebuild processes, "Unable to boot simulator", "No such module" after SPM changes, or mysterious test failures despite no code changes — systematic environment-first diagnostics for iOS/macOS projects
Debug and inspect PostHog implementations on any website. Use this skill when a user wants to understand how PostHog is implemented on a page, troubleshoot tracking issues, verify configuration, check what events are being sent, or audit a PostHog setup. Works with Chrome DevTools MCP and Playwright MCP to inspect live websites.
Plan and run usability tests on existing or prototype designs including test design, task scripts, moderation, observation, and findings synthesis. Use this skill whenever the user wants to test usability, run a moderated test, run an unmoderated test, validate a design, find usability issues, or improve task completion. Triggers on usability test, usability testing, moderated test, unmoderated test, task script, think aloud, prototype testing, user testing, design validation, task completion. Also triggers when the user has built something and wants to know if real users can use it before shipping.
This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing", or needs guidance on API security assessment techniques.
Generates Cucumber BDD tests with Gherkin feature files and step definitions in Java, JavaScript, or Ruby. Use when user mentions "Cucumber", "Gherkin", "Feature/Scenario", "Given/When/Then", "BDD". Triggers on: "Cucumber", "Gherkin", "BDD", "Feature file", "Given/When/Then", "step definitions"
Code quality patterns and guidelines for ToolUniverse tool development. Apply when writing, fixing, or refactoring tool Python code in the ToolUniverse project. Encodes lessons from 80+ debug rounds. Use alongside devtu-fix-tool and devtu-self-evolve. Triggers: implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug fixes
Analyzes Meta VR and Horizon OS VR performance using Perfetto traces — frame timing, CPU/GPU bottlenecks, render pass analysis. Use when profiling frame drops, jank, or thermal issues on Meta VR devices. Build paths: all Meta VR app stacks; use hz-quest-verify-first if the build path is unclear.
The meta skill. Turns any raw feature into a properly skilled, tested, resolvable unit of agent capability. Idempotent: running it on an existing skill improves it (bug fix, new input, quality pass) instead of starting from scratch. Every skill declares an EVAL CONTRACT (its goal + skill-specific dimensions + hard-fails) so the cross-modal eval judges THIS skill's real purpose, not generic slop. Cross-modal eval runs BEFORE tests: 3 frontier models from different providers critique the output against the contract; you iterate to quality, THEN write or update tests that lock in the proven-good behavior. NO-REGRESSION LAW: any edit to a skill must score >= the previous iteration's eval — forward only, never back. For skills that back a scheduled job, an edit MUST re-run a representative task and eval it before shipping.
Automatically review latest Alibaba Cloud product docs and OpenAPI docs by product name, then output detailed prioritized improvement suggestions with evidence and scoring. Use when user asks to audit product documentation quality, API documentation quality, or wants actionable doc/API optimization recommendations.
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities". Do NOT use for accessibility (use web-accessibility), SEO (use seo), performance (use core-web-vitals), or comprehensive multi-area audits (use web-quality-audit).
Assesses technical debt by identifying, classifying, and prioritizing maintainability problems to help teams build a refactoring roadmap, drawing on twelve classic engineering books. Triggers when the user asks about technical debt, refactoring priorities, what to clean up first, or asks “why is this so hard to change?”, “what should we fix first?”, or “how do I justify refactoring to management?”. Do not trigger for server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime—“health” in those contexts refers to infrastructure, not code quality. Also not for single-function refactoring questions.
Review code architecture for maintainability and catch structural issues before they become debt. Use when reviewing pull requests with structural changes, planning refactoring work, evaluating new feature architecture, assessing technical debt, before major releases, or when code feels "hard to change". Triggers: architecture, code-review, refactoring, design-patterns, technical-debt, dependencies, maintainability
Creates a DevOps Center quality gate with associated rules (PASS_PERCENTAGE, SEVERITY, ESSENTIAL) and links it to a pipeline-stage suite assignment, after showing a mandatory impact preview and obtaining explicit confirmation. Use this skill when a user wants to set or configure a quality gate, change a coverage threshold, or establish testing benchmarks on a pipeline stage. TRIGGER when: the user wants to set/configure a quality gate, change a coverage threshold, or set testing benchmarks on a stage. DO NOT TRIGGER when: only re-running an existing gate (use running-devops-test-suite in retrigger mode).
Comprehensive data quality assessment against business rules, schema constraints, and freshness expectations. Activate when validating data pipeline outputs before production use, auditing a dataset against defined business rules, or producing a quality scorecard for a data asset.
Bootstrap a reproducible LLM Observability experiment through the Python ddtrace SDK or the Node dd-trace SDK. Use for experiment, dataset, evaluator, benchmark, regression, or LLM-as-a-judge scaffolding. The legacy Python invocation remains supported.
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
Generates Insomnia collection export files from Express, Next.js, Fastify, or other API routes. Creates organized workspaces with request groups, environments, and authentication. Use when users request "generate insomnia collection", "export to insomnia", "create insomnia workspace", or "insomnia import"
Triggers async execution of one or more DevOps Center test suites on a pipeline stage (Pre-Promote, Post-Promote, or Review event) via the Connect API, after an explicit user confirmation gate, then hands off to result polling via the `polling-test-results` skill. Also re-runs (retriggers) a quality gate after fixes — but only once validation confirms the coverage threshold is now met. TRIGGER when: the user wants to run, kick off, or launch test suites on a pipeline stage; execute tests before or after a promotion; trigger a Pre-Promote, Post-Promote, or Review-event run; re-run a quality gate after fixing failures; retry a failed gate once coverage is met; or unblock a blocked promotion after adding tests. DO NOT TRIGGER when: running sf apex run test directly (use running-apex-tests); or configuring a NEW gate or threshold (use configuring-quality-gate).
Validate the environment before any DevOps Center pipeline testing action: confirms an authenticated Salesforce org, the Agentforce DX plugin, an authenticated DevOps Center org, and an identified pipeline (and optionally a pipeline stage). Use this FIRST, internally, from any DevOps testing skill (running a test suite, polling results, syncing tests, configuring or retriggering a quality gate, assigning/mapping suites, creating fix work items, recommending tests, explaining coverage, analyzing failures). TRIGGER when another DevOps testing skill needs to confirm org/pipeline context before a query or system call. DO NOT TRIGGER for non-DevOps-Center work.
Installs and configures Prettier, ESLint, EditorConfig, and other code quality tools to enforce consistent code style across the team. Generates config files, npm scripts, editor settings recommendations, and CI integration suggestions. Use when users request "setup prettier", "add eslint", "configure code formatting", or "enforce code style".
Generate ABAP Unit tests for classes with dependency analysis, interface-based test doubles, and method-level surgical insertion. Use when asked to "generate unit tests for this class", "add ABAP Unit tests", "write tests for this method", or "create test doubles for ZCL_X".
Crash-hunting skill for iOS 26 / Swift 6.2 clinic-architecture codebases that finds and fixes concurrency, memory, and I/O bugs using TDD. Covers data races, actor isolation, retain cycles, SwiftData context misuse, and sync-related failures in Domain/Data/App boundaries. Use when debugging crashes or hard-to-reproduce failures in ios-* and swift-* clinic modules.
Polls a DevOps Center async test execution by runId until it completes, fails, or times out — using read-only SOQL on the execution record at provider-specific intervals (Apex 15s/5m, Code Analyzer 10s/3m, Provar UI 60s/20m, Flow 20s/8m) — then surfaces results. Use this skill when a test suite run is in progress and the user is waiting on results, or immediately after running a suite. TRIGGER when: a test suite run is in progress and the user is waiting on results, or immediately after running a suite and a runId is available. DO NOT TRIGGER when: there is no active runId.
Intelligent interaction performance analysis with automated workflows for INP debugging, scroll jank investigation, and main thread blocking. Includes decision trees that automatically run script attribution when long frames detected, break down input latency phases, and correlate layout shifts with interactions. Features workflows for complete interaction audit, third-party script impact analysis, and animation performance debugging. Cross-skill integration with Core Web Vitals (INP/CLS correlation) and Loading (script execution analysis). Use when the user asks about slow interactions, janky scrolling, unresponsive pages, or INP optimization. Compatible with Chrome DevTools MCP.
Audit a package of custom code and bucket every Z/Y object into Clean Core Levels A–D based on the SAP APIs it uses — the "is this cloud-ready?" assessment. Use when asked to "classify this package for clean core", "clean core readiness report", "Level A-D audit", or "is this code cloud-ready".
Generate and maintain the system recap block in a PR description—a GitHub-rendered visual summary of which system primitives a change touches, how risky it is, and what changed. Prefer Mermaid sequence diagrams for the change; choose another graph type when it explains the diff better. Use when planning a non-trivial change (plan mode), creating or updating a pull request (recap mode), or when the user asks for a visual recap, visual plan, system review, or PR recap.
Inspect, verify, interact with, or profile a live Vite app by running temporary scripts in its browser page. Use for runtime state, physical input, browser logs, screenshots, recordings, and performance artifacts; prefer static inspection for questions the source can answer
Intelligent loading performance analysis with automated workflows for TTFB investigation (DNS/connection/server breakdown), render-blocking detection, script performance deep dive (first vs third-party attribution), font optimization, and resource hints validation. Includes decision trees that automatically analyze TTFB sub-parts when slow, detect script loading anti-patterns (async/defer/preload conflicts), identify render-blocking resources, and validate resource hints usage. Features workflows for complete loading audit (6 phases), backend performance investigation, and priority optimization. Cross-skill integration with Core Web Vitals (LCP resource loading), Interaction (script execution blocking), and Media (lazy loading strategy). Use when the user asks about TTFB, FCP, render-blocking, slow loading, font performance, script optimization, or resource hints. Compatible with Chrome DevTools MCP.
Intelligent media optimization with automated workflows for images, videos, and SVGs. Includes decision trees that detect LCP images (triggers format/lazy-loading/priority analysis), identify layout shift risks (missing dimensions), and flag lazy loading issues (above-fold lazy or below-fold eager). Features workflows for complete media audit, LCP image investigation, video performance (poster optimization), and SVG embedded bitmap detection. Cross-skill integration with Core Web Vitals (LCP/CLS impact) and Loading (priority hints, resource preloading). Provides performance budgets and format recommendations based on content type. Use when the user asks about image optimization, LCP is an image/video, layout shifts from media, or media loading strategy. Compatible with Chrome DevTools MCP
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Design, test, create, and attach LangSmith online evaluators for production traces or conversation threads. Use for workspace evaluators, run or thread rules, sampling, filters, backfills, and evaluator monitoring; use eval-engineering for Harbor tasks and agent benchmarks.
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.