Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Complete workflow for migrating an existing frontend application to SGDS web components. Use this skill when a user wants to migrate from another UI library (MUI, Chakra UI, shadcn/ui, Ant Design, Vuetify, Angular Material, Bootstrap, etc.) to SGDS, or asks how to start using SGDS in an existing project. Covers four phases: (1) scan the current frontend tech stack, (2) install and configure SGDS with font, foundation CSS, and utilities, (3) migrate tests (Path A: Vitest + Playwright, or Path B: patch existing Jest/RTL), (4) replace old styling systems with SGDS v3 utilities, plus a post-migration verification checklist. React fully supported.
Guide creating and reviewing skills that extend Claude with specialized knowledge, workflows, or tool integrations. Covers SKILL.md structure, frontmatter quality, trigger design, eval pipelines, and packaging. Triggers on create a skill, review this skill, new skill, optimize skill, skill quality.
Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements. Runs quick_validate.py, checks line limits, verifies cross-references, and tests hook scripts. Use when skills have been added or modified and you want to verify everything passes before committing or submitting.
Iterative playbook for bringing Node and TypeScript projects (NestJS + React in a monorepo) to compliance with SonarQube Quality Gates without breaking the build or pipelines. Use when you need to raise coverage by prioritizing New Code, eliminate new issues (Bugs, Vulnerabilities, Code Smells), review Security Hotspots, and control duplication and technical debt.
Check whether a named implementation specification is ready to hand to an implementer without forcing them to invent structural contracts. Use explicitly before implementation handoff to return READY or root-complete NOT READY blockers. Do not use as a runtime correctness or PR merge review.
Prepare Steam launch readiness for PC games including store page, capsule art, trailer, screenshots, tags, wishlist funnel, demo, playtest, achievements, cloud saves, controller support, localization, pricing, discounts, refund expectations, community hub, patch notes, reviews, and launch operations. Use when launching, auditing, or improving a game on Steam.
Agent development workflow and discipline skills. Use when developing features, debugging issues, managing code branches, writing plans, or ensuring code quality through TDD and systematic processes. Triggers on any software development task that benefits from structured workflows.
Systematic step-by-step debugging process for bugs, test failures, and unexpected behavior. Use when a test fails, something isn't working as expected, user says "this is broken", "why isn't X working", "help me debug", or when you encounter any error before proposing a fix.
Applies a modified Fagan Inspection methodology to resolve persistent bugs and complex issues. Use when several fix or debugging attempts have already failed and a methodical root-cause analysis warranting a Fagan inspection is needed. For first-pass diagnosis of a reproducible bug or regression use diagnose-hard-problem. Do not use for simple troubleshooting.
Code quality guide based on 토스 Frontend Fundamentals. Provides feedback by 4 criteria (readability, predictability, cohesion, coupling) during code review, writing new code, and refactoring. Activates on requests about frontend code quality, clean code, or code improvement.
Generate a traceability report that cross-references the acceptance criteria of an artefact — a user story (US-XXX), a maintenance task (WI-XXX), an already implemented feature (FT-XXX), or any document whose criteria have a coded identifier (AC-001, 1.1, R-3…) — against the repository's test cases and test artefacts. For each criterion, state what covers it, its status (Covered / Partial / Not covered), whether the test ran and with what result, and close with a coverage verdict. It does not run the suite: it delegates execution to quality-check. Always activate when the user asks to validate coverage, generate a traceability matrix or report, verify that acceptance criteria are tested, check whether a piece of work or a feature is covered by tests, or mentions "traceability", "coverage matrix" or "validate acceptance criteria", even if they do not name the exact format.
JS/TS style guidelines and review checklist for workerd. Covers TypeScript strictness, import conventions, export patterns, private field syntax, error handling, feature gating, and test structure. Load this skill when reviewing or writing JavaScript or TypeScript code in src/node/, src/cloudflare/, or JS/TS test files under src/workerd/.
Use when checking which TYPO3 versions an extension says it supports, when composer.json and ext_emconf.php disagree, when a version bump has left some of the files that state it behind, when reviewing a TYPO3 extension for what needs attention, or when auditing coding standards, TER readiness, deprecations and modernization to v12/v13/v14 (v14.3 LTS is the default). Raising an extension to a newer TYPO3 version is not this skill: that belongs to typo3-extension-upgrade.
UE5.6-UE5.8 debugging and validation workflow for logs, asset checks, and regression triage. Use when requests involve troubleshooting why gameplay does not work, validating expected output, narrowing minimal repro, and producing concrete fix steps.
Generate and run Unity tests (NUnit, EditMode, PlayMode). Analyzes existing code, extracts testable logic, generates fitting tests. Triggers: /test, /unity-test, 'NUnit', 'test unitaire Unity', 'PlayMode test', 'EditMode test', 'TDD Unity', 'ecrire des tests', 'tester mon code'.
Load saved Playwright storageState authentication profiles before browser automation. Activates when `.playwright/profiles.json` exists and browser work begins on authenticated pages. Trigger phrases include "use profile", "load profile", "browser as [role]", "authenticated browser", "logged in browser session".
AI agent visual feedback loop for any web app. Use when iterating on visual code (UI, canvas, 3D, SVG, charts, animations) and you need to SEE the rendered result to evaluate quality. Covers: dev-screenshot API pattern (GET trigger → SSE → client capture → POST back → file saved), parameterized rendering, metadata sidecars, visual regression with pixel diff, WebMCP tool registration, and console fallbacks. Activate on: 'take a screenshot', 'show me the render', 'visual QA', 'compare before/after', 'pixel diff', or any iterative visual work where the agent needs to inspect rendered output.
Run an extremely strict maintainability review of the current diff for abstraction quality, giant files, duplication, layering leaks, and spaghetti-condition growth. Measures with oracles before opining, applies diverse review lenses, and sweeps outside the diff for completeness. Effort tiers: low/medium → fewer lenses, highest-confidence findings only; high → all lenses + completeness sweep; ultra → fan lenses across files in parallel. Use for a deep code quality audit or an especially harsh maintainability review.
Implement a task N ways in parallel and pick the best — by OUTCOME, not by pitch. Spawns N sub-agents in isolated git worktrees, each from a DISTINCT angle, gates every candidate through a per-candidate oracle (build + typecheck + test + lint), grades survivors from the ACTUAL diff (never the self-report), runs a completeness sweep on the winner, applies it to main, and re-verifies the oracle green before declaring a winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/work-tournament", or "/bon".
Memory safety, thread safety, concurrency, and critical detection patterns for workerd code review. Covers V8/KJ boundary hazards, lifetime management, cross-thread safety, and coroutine pitfalls. Load this skill when reviewing any C++ code.
Review product accessibility and inclusive UX for web, mobile, desktop, SaaS, games, developer tools, checkout, onboarding, settings, forms, dashboards, notifications, motion, keyboard, screen reader, touch, color contrast, focus, error recovery, cognitive load, reduced motion, captions, localization, and assistive technology compatibility. Use when designing, building, or auditing product flows for accessible, usable, modern experiences.
Apidog import/export and quality gates: import OpenAPI, Postman, Swagger, and Apidog native formats; export OpenAPI, HTML, Markdown, Postman, and Apidog native formats; validate spec completeness, tag grouping, schema/body coverage, counts, modules, and resource visibility.
Operate Argos visual testing from the terminal with the `argos` CLI — inspect builds and snapshot diffs, submit reviews, request reviewers, post comments, inspect a test's flakiness and its recurring changes, ignore flaky test changes, configure a project and its contributors, manage a team's members, invites and email domains, manage automation rules, fetch analytics, upload screenshots, and manage CI builds. Use whenever running `argos` commands or working with Argos builds, snapshots, flakiness, projects, teams, or visual-regression reviews from a shell, script, or CI pipeline. Load before running `argos` — it covers the token model and JSON output contract that prevent silent failures.
Mandatory rules for running bazel tests during development. Load this skill before running any bazel test command, especially when validating fixes or verifying regression tests. Prevents false confidence from cached results, filter flags that silently match nothing, and partial test runs that miss breakage.
Triage the last N production call logs for a Cekura agent against a set of KPIs / issues / goals, report the call IDs that hit each failure WITH the percentage of overall call logs affected, and distribute the remaining calls into a mutually-exclusive outcome taxonomy (e.g. not-answered / vetted / non-vetted caller-side / non-vetted agent-issue) with per-bucket percentages. Use when the user says "flag call log failures", "analyze the last N calls for issues", "what % of calls have <problem>", "which calls broke and how often", "find failing calls", "give me the breakdown of call outcomes", "what % of answered calls can be improved", or pastes an agent / project ID and lists the problems or KPIs to measure. Applies attribution rules so caller-side endings and recovered calls are NOT counted as agent failures. This is the upstream triage step that feeds `cekura-generate-scenarios` — it does NOT create scenarios.
Clean code principles. Covers naming, functions, and readability. Use when writing or reviewing code for quality. USE WHEN: user mentions "code quality", "readability", "refactor", "clean up code", "naming", "magic numbers", asks about "how to write better code", "code smells", "DRY", "KISS", "YAGNI", "single responsibility" DO NOT USE FOR: SOLID principles - use `solid-principles` instead, Git workflow - use `git-workflow` instead, Performance optimization - use `performance` instead
Scan and analyze a software repository or project for design quality using principles from A Philosophy of Software Design by John Ousterhout. Use when user asks to review, audit, scan, or evaluate code quality, design quality, architecture, or technical debt. Also trigger for: code review, design review, complexity analysis, code health check, module depth analysis, information hiding review, information leakage, how good is my code, review my project, find design problems, what is wrong with my codebase, rate my code, audit my small project, quick code review, design check, or anything about evaluating software design quality at a structural level. This is not a linter or style checker. It evaluates deep design qualities like module depth, abstraction quality, information hiding, and complexity patterns. Adapts to project size — small projects (<20 files) get a concise review, large projects get sampled.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants, adding a feature through a walking skeleton and acceptance tests, debugging a defect with reproducible tests or bisection, threat-modelling endpoints and trust boundaries with STRIDE, planning a legacy or Strangler migration with rollback, or setting up a maintainable codebase. Covers decomposition and cyclomatic complexity, cohesion, encapsulation, outside-in TDD, separation of concerns, Git/review discipline, safe evolution, and troubleshooting. Not for language syntax, framework tutorials, production incident response, or performance profiling.
Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded passwords, or code security checks.
Source code auditing methods in CTF challenges. Use when you find a .git directory, .bak/.zip backups, or source code leaked via /proc/self/environ. Unlike real code audits — vulnerabilities in CTF source are placed intentionally and usually there are only 1-2 key points. First find the dangerous function (sink), then trace the path from the input (source) to that function. Covers dangerous functions and vulnerability patterns in PHP/Python/Node.js/Java
Review frontend UI for design quality, consistency, and taste. Use when the user asks to review, QA, audit, or check the design/UI/UX of a page, component, or app. Captures screenshots, extracts the project's design system, applies opinionated taste rules, and produces a severity-ranked report with file references and fix suggestions.
Generates desktop browser workflow documentation by exploring the app's codebase, then walking through the live app with the user step-by-step via Playwright to co-author verifications. Use when the user says "generate desktop workflows", "create desktop workflows", "update desktop workflows", or "generate browser workflows".
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.