Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Claude Code automatic advisor for security, reviews, high-risk design, substantial multi-step plans, complex refactors, recurring failures, and risky completion checks. Skip trivial work, ordinary planning, other harnesses, or sessions without an advisor tool.
Rewrites code to fix clean coding violations. Use when: acting on a violation report from clean-code-reviewer, fixing specific code-level issues (function size, naming, error handling, smells) in existing code, or as the final step in a refactoring workflow after an architect has designed the target structure. Does NOT make architectural changes — structural redesign is the responsibility of the appropriate data-engineer in Implement Mode, working from an architect's design. Supports Python, JavaScript/TypeScript, C#, and Rust. Supports both general (Clean Code) and OB (BORO Quick Style Guide) convention sets via the `standard` parameter.
Review code for bugs, security vulnerabilities, performance issues, and maintainability. Trigger with "review this code", "check this PR", "look at this diff", "is this code safe?", or when the user shares code and asks for feedback.
Research-backed code review skill with OWASP Top 10 security checks, SAST tool integration (SonarQube, CodeQL, Snyk), performance pattern detection, and automated quality standards enforcement. Auto-invoked for code review, security audit, PR analysis, and bug checking. Implements 2025 best practices with 92% faster vulnerability remediation.
Performs systematic code review with universal best practices and repo-specific standards. Auto-activates after significant code changes. Use when reviewing code, auditing files, checking PRs, examining staged changes, or when asked to "review", "check", "audit", or "examine" code. Enforces design principles (SOLID, DRY, KISS), security (OWASP), performance, concurrency safety, cross-platform compatibility, and codebase patterns.
Use when the user explicitly asks to run an iterative Codex review cycle on a non-empty git diff, including working-tree changes, current branch vs base, explicit commit/tag/branch refs, code diffs, or Markdown planning documents. Do not use for one-shot reviews, auto-hardening, background checks, plan drafting, or empty review targets.
Use this skill when a product engineer wants to audit existing code for Earth Design System (EDS, `@adaptavant/eds-core`) anti-patterns, misuse, deprecated APIs, or HTML accessibility violations. Triggers include 'audit EDS usage', 'check for EDS anti-patterns', 'review this file for EDS violations', 'is this EDS-compliant', 'lint my EDS code', or any request to scan a file or directory for design-system misuse. Detection-only — produces a findings report with suggested fixes and refers remediation to the `co-author` skill. Do NOT use this skill for authoring new EDS code (use `co-author`), reviewing PRs (use `pull-request-reviewer`), or fixing bugs inside `packages/core`.
Methodology for auditing A/B testing of consent banners to ensure compliance with equal ease of acceptance and rejection. Covers CNIL enforcement patterns including the EUR 150M Google fine, dark pattern detection methodology, manipulative design identification, and regulatory-compliant experimentation boundaries.
Automates unit test creation for C++ projects using the GoogleTest (GTest) framework, with consistent software testing patterns including In-Got-Want, Table-Driven Testing, and AAA patterns. Use when creating, modifying, or reviewing unit tests, or when the user mentions unit tests, test coverage, or GTest.
(NS) Create and maintain Cypress E2E tests in an independent tests-e2e/ Node package at product root (bootstrap when missing). DRY device-aware command architecture (shared/pages/device). Use when writing or refactoring Cypress specs, custom commands, scaffolding E2E on greenfield projects, or implementing E2E tasks — not when planning E2E task markdown (use e2e-test-generator). Read harness e2e rules when present. Mandatory discovery before writing specs.
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions "largest contentful paint", "page load speed", "CWV", or wants to improve how fast their hero image or main content renders.
Investigate failures with evidence at the layer that can answer the question. Form testable hypotheses from reports, logs and code; use reproduction, replay, fault injection or tracing without requiring the whole incident to recur. Separate observed triggers from conditional handling defects, protect affected contracts, and stop when the evidence supports the scoped decision. Use for broken, intermittent, hanging or newly slow behaviour whose cause is unknown. Not for judging an existing change or fixing an unrelated environment blocker.
Audit a design system for consistency, coverage, and quality. Use when asked to audit a design system, review a component library, assess design token coverage, or evaluate the health of a shared design system. Produces a structured audit with a health score, component coverage gaps, token inconsistencies, accessibility issues, and a prioritised remediation roadmap.
Compares a component or screen's design spec with its code and logs each gap as a build error or spec gap. Use it for design QA, handover review or sign-off: whenever someone asks if a build matches its design or spec, even for one component with the spec pasted in. For system-wide drift, use drift-detection.
Run an internal dogfooding program/sprint and produce a Dogfooding Pack (charter, scenario map, routines, dogfooding log + triage board spec, weekly report, ship/no-ship gate). Use for “dogfooding”, “eat our own dog food”, internal beta, and product teams using the product daily to find friction before shipping.
Review code according to Drupal's official coding standards. Provides AI agents with comprehensive guidelines for PHP, JavaScript, CSS, Twig, YAML, SQL, and markup files in Drupal projects. Uses dynamic context discovery to load only relevant standards based on file type being reviewed.
Breaks a feature, PRD, or requirement into TDD implementation tasks with task 0.0 as feature branch creation (MUST be first), each task uses TDD quadruplet (RED test→run fail→GREEN impl→run pass→REFACTOR), includes mandatory public API docs task, update docs task, and code review task, output with `Guidance Used` and `Relevant Files` sections saved to `tasks/tasks-[name].md`, auto-detects test command/source dir/test dir from project conventions. Ruby-first but language-agnostic. Trigger words: tdd task list, tdd tasks, generate tasks, tdd breakdown, implementation tasks, task breakdown, feature tasks, quadruplet pattern.
Design and review gRPC and Protocol Buffer APIs against Google API Improvement Proposals (AIPs). Use when adding or changing .proto resources, RPCs, standard or custom methods, pagination, filtering, field masks, long-running operations, soft delete, versioning, or when an AIP number or compliance review is mentioned. Do not use for protobuf syntax, code generation, or implementation unless AIP guidance is the task.
IntelliJ IDEA MCP for Java code analysis, testing, refactoring, and project navigation. Use when: (1) Checking Java compilation errors (get_file_problems is more accurate than LSP for multi-module Maven), (2) Performing rename refactoring across the codebase, (3) Searching code or finding files in the project. Requires IDEA to be running with MCP plugin connected.
Build a whole feature by breaking a plan into tasks and running implement-and-review on each. Given a plan or feature, decompose it into tracer-bullet vertical-slice tasks (via the to-tasks skill — acceptance contracts + gate flags + dependencies), then execute the task DAG (independent tasks in parallel) by running implement-and-review for each per-task FE/BE cross-reviewed TDD build, integrate tasks in dependency order with per-task acceptance, and finish with a feature-wide full-review, leaving tests/build green. Opus orchestrates breakdown, scheduling, integration, and final review; per-task building is implement-and-review's job. Use to ship/build a multi-task feature end-to-end. For a single scoped task call implement-and-review directly. Distinct from models-consensus (deliberation only, produces no code) and from ship — ship is the idea→PR conductor, including the interactive spec/plan phases and PR delivery, while implement-feature is the plan→built-feature DAG executor with no spec phase and no PR.
Write an infrastructure-as-code review checklist and conduct a structured review of Terraform, CloudFormation, Pulumi, or Ansible code. Use when asked to review IaC code, audit infrastructure configurations, check cloud security posture, or produce a reusable IaC review checklist. Produces a structured review report with severity-categorized findings, remediation guidance, and a reusable checklist.
Initialize the Playwright trio (@playwright/test + @playwright/cli + playwright-mcp) in a pnpm monorepo, including an e2e/visual testing skeleton, MCP configuration, AI skills generation, and AI memory updates. Includes a built-in postmortem and troubleshooting guide for headless browser CPU overload incidents: it can diagnose high CPU usage (100%) in headless mode, browser hangs, leftover Chromium processes that cannot exit, and 3D WebGL rendering performance issues on large displays; it provides emergency stop-loss steps and a long-term regression checklist. Triggered when the user mentions Playwright initialization, large-display visual testing, e2e test setup, Playwright monorepo configuration, pw_core/pw_visual MCP, and so on. Also applies to troubleshooting scenarios such as headless browser performance issues, headless CPU 100% diagnosis, cleanup of leftover Chromium processes, handling browser processes that cannot exit, and performance tuning for large-display 3D rendering.
Use this skill for ANY question about creating test or evaluation datasets for LangChain agents. Covers generating datasets from traces (final_response, single_step, trajectory, RAG types), uploading to LangSmith, and managing evaluation data.
This skill should be used when analyzing a downstream project's git diff after Lisa was applied to identify improvements that should be upstreamed back to Lisa templates. It validates the environment, captures the diff, correlates changes with Lisa template directories, categorizes each change, and offers to upstream improvements.
Write a load and performance testing plan for a service. Use when asked to create a performance test plan, write load testing documentation, define stress or soak test scenarios, or set performance regression gates for CI. Produces a complete test plan document with scenario definitions, k6/Locust script skeleton, threshold table, result interpretation guide, and CI integration steps.
A code review skill based on local git diff. Use it for a self-check review before opening a PR, strictly reusing pr-review's three dimensions (code quality standards, FastGPT style conventions, common issues checklist). Supports reviewing unstaged changes, staged changes, a single commit, or all changes on the current branch relative to a baseline branch.
Reviews embedded Rust firmware for RP2350 (Raspberry Pi Pico 2 W) and ESP32-S3 (Heltec) microcontrollers with focus on Embassy async runtime, memory constraints, LED control, CAN attachment protocols, and SLCAN bridging. Use when reviewing MCU firmware changes, debugging LED controller issues, evaluating Embassy async patterns, checking static memory allocation, validating SLCAN implementations, or assessing hardware-specific code for WS2812 LEDs, CAN peripherals, and tool attachments. Covers no_std environments, PIO state machines, RMT peripherals, and USB CDC serial communication.
Define and document performance budgets for a web service or application. Use when asked to set performance targets, define SLOs for latency or throughput, establish Core Web Vitals targets, create a performance baseline, or document performance regression policy. Produces a structured performance budget covering key user journeys, Core Web Vitals, backend latency SLOs, measurement tooling, CI enforcement, and breach response process.
Use when writing, debugging, or reviewing Playwright tests for web apps; before writing test code; when tests are flaky, slow, or brittle; when seeing timeout errors, element not found, or race conditions; when using getByRole, locators, or assertions
Formal Quality Assurance Checklist before every Merge/Deploy. 6-phase validation with Build Verification, Test Suite, No-Touch Zones, Region Check, Security Review, and QA Report generation. Activate on "merge", "deploy", "release", "production", or /qa command.
Manage the PR review iteration loop: poll for reviewer feedback, assess suggestions with evidence, implement fixes, resolve threads, and drive CI/CD to green. Works standalone on any PR (bug fix, refactor, hotfix, feature) or as a composable module invoked by /ship. Spec-aware when a SPEC.md is provided, but does not require one. Triggers: review, review loop, PR feedback, iterate on PR, resolve reviews, CI/CD resolution, green pipeline, address reviewer comments.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along four independent axes — Standards, Spec, Architecture, and Divergent design — each run as a parallel sub-agent so contexts stay clean, then verified against false positives and reported side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Use when Codex or code/plan review findings need Definition-of-Done scope triage, especially to separate must-fix issues from minimal hygiene, out-of-scope hardening, repeated noise, or self-induced refinements. Also use when codex-review-cycle invokes scope guard between validity checking and summary render. Do not use for single-shot lint or unrelated changes.
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.