Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Guides senior software engineering across languages and stacks—system and service design, RFCs, code review, refactoring, reliability patterns, testing strategy, performance analysis, technical decomposition, and engineering leadership on delivery teams. Use when designing services or modules, writing technical specs, reviewing PRs for architecture and correctness, improving legacy code, choosing trade-offs (coupling, consistency, latency), estimating complex work, or mentoring engineers—not for stack-specific full-stack UI delivery (senior-fullstack-developer), deployment rollout strategy (deployment-strategist), infrastructure/IaC (infrastructure-engineer), dedicated perf profiling and load testing (performance-engineer), org-wide security programs (cybersecurity), or cross-system ADRs and architecture review (senior-system-architecture).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across iterations. Runs multiple trials per eval for statistical reliability, aggregates results into benchmark.json, and generates comparison reports between skill versions. Use when user says "benchmark skill", "measure skill performance", "skill metrics", "compare skill versions", "skill performance", "track skill improvement", "skill regression test", or "skill A/B test".
Create or improve Claude Code and Codex skills. Use only when the request is explicitly about the skill itself: creating a new skill, editing a SKILL.md file, testing a skill draft in .claude/skills/.../SKILL.md or .agents/skills/.../SKILL.md, improving an existing skill, debugging why a skill is not triggering, running evals or benchmarks for a skill, or turning an already-described workflow into a reusable skill. Trigger on phrases like existing skill, skill draft, SKILL.md, skill trigger, skill eval, make this into a skill, or turn this workflow into a skill. Do not use for ordinary implementation work unless the user explicitly mentions a skill, SKILL.md, or converting the task into a skill. That exclusion includes generic coding tasks, generic automation/workflow setup, CI setup, GitHub Actions workflows, debugging, code review, database migrations, schema changes, and production incident response when the user is just asking for help with the task itself.
Audit and validate existing Claude Code skills for quality, triggering accuracy, structure compliance, and best practices. Scores skills on a 0-100 scale and provides prioritized improvement recommendations. Use when user says "review skill", "audit skill", "check skill", "validate skill", or "skill quality".
Coding rules generator — Extract and generate coding-rules.md from project conventions. Scans CLAUDE.md, AGENTS.md, config files, existing source code, and installed skills to produce a unified coding-rules.md that spec-implement uses as a quality gate. English triggers: "Generate coding rules", "Create coding-rules.md", "Extract project rules" 日本語トリガー: 「コーディングルールを生成」「coding-rules.mdを作成」「プロジェクトルールを抽出」
Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patterns. Essential reference for code reviews and Spring Boot application development.
Guides technical support engineering—customer ticket investigation, reproduction, log and API analysis, root-cause isolation, workaround communication, engineering escalation with evidence, and knowledge-base fixes for product bugs and integration issues. Use when debugging a customer-reported issue, writing a repro for engineering, analyzing API errors, drafting technical replies, or improving support runbooks—not for CS program design, renewals, or billing ops (customer-ops-specialist), production incident command (incident-management-engineer), building product features (fullstack-software-engineer), or company-wide crisis statements and launch announcements (communication-lead), or exec/VIP and community escalation program design (community-executive-escalations-program-manager). Product how-to, macros, and ticket triage without deep debugging: product-support-specialist.
Code review and design support based on the "Tell, Don't Ask" principle. It converts patterns that query an object's state and decide externally into patterns that tell the object directly. It promotes designs that strengthen encapsulation and concentrate responsibility in the object that holds the data. Use when code review, new implementation, or refactoring requires fixing getter abuse or Feature Envy. Target languages: Java, Kotlin, Scala, TypeScript, Python, Ruby, Go, Rust. Triggers: OOP design requests such as "I want to reduce getters", "improve encapsulation", "fix Feature Envy", "I want objects to take on responsibility", "Law of Demeter".
Write automated tests using RSpec, Capybara, and FactoryBot for Rails applications. Use when implementing features, fixing bugs, or when the user mentions testing, specs, RSpec, Capybara, or test data. Avoid using rails console or server for testing.
Design test strategies and test plans. Trigger with "how should we test", "test strategy for", "write tests for", "test plan", "what tests do we need", or when the user needs help with testing approaches, coverage, or test architecture.
Find and report ThreadWave failures safely. Use this skill whenever a user reports a ThreadWave error, blocker, repeated repair failure, unknown mutation result, asks whether a failure is a bug, asks for a known solution, or wants a Markdown issue report. It classifies report-worthy failures, searches the public ThreadWave error repository without requiring a GitHub account, and renders a sanitized bilingual copy/paste report when needed.
One-stop mobile review — the umbrella for the thumb-first suite. Runs a design-judgment pass AND a platform-technical pass over a mobile app/screen/PWA, then merges them into ONE prioritized report that keeps design forks (opinions) and platform defects (objective, P0–P3) visually distinct. Use when the user wants to review, audit, critique, or design a mobile app, screen, or PWA — 'review my mobile app', 'is this good mobile UX', 'audit this screen', 'check my PWA'. Routes to: full review (default), design-only (thumb-first-design), or platform-only (thumb-first-platform). Platform-agnostic on judgment; web/PWA-deep on technical, with native handoff.
Invoked by /tidy-project. Read-only, four-phase audit of PROJECT STRUCTURE — directory and file layout plus statically auditable config, dependency, and build hygiene (nested codebases, missing lockfiles, committed build artifacts, over-nesting, misplaced files, config sprawl, vestigial scaffolding, hardcoded environment values, convention drift). Code-semantics concerns are out of scope. Produces a single consolidated execution plan at `docs/YYYY-MM-DD-tidy-project-plan.md` (or repo root if no `docs/`); modifies no source files. Skips traversing dot-directories and build/vendor output, though it may still flag their tracked presence via `git ls-files`. Does not auto-activate on natural-language requests.
Use when running UnoPim tests, linting, static analysis, or asset builds, or when asked whether a change is ready to be called done. Trigger phrases include “run tests,” “pest,” “pint,” “larastan,” “phpstan,” “playwright,” “build assets,” and “is this done.”
Use a repo-root `.editorconfig` to configure free .NET analyzer and style rules. Use when a .NET repo needs rule severity, code-style options, section layout, or analyzer ownership made explicit. USE FOR: the repo needs a root .editorconfig; analyzer severity and style ownership are unclear; the team wants one source of truth for rule configuration. DO NOT USE FOR: choosing analyzers with no config change; formatting-only execution with no config ownership question. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Control Android devices from AI agents using the Another MCP server. Use when asked to interact with, test, automate, or take screenshots of an Android device. Provides tools for touch input, text entry, button presses, screenshots, app launching, shell commands, and swipe gestures.
Use the open-source free `ArchUnitNET` library for architecture rules in .NET tests. Use when a repo needs richer architecture assertions than lightweight fluent rule libraries usually provide. USE FOR: the repo uses or wants ArchUnitNET; architecture testing needs richer modeling than simple dependency checks. DO NOT USE FOR: the lightest possible architecture rule checks. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Write, split, rename, or repair an agent skill so it activates when it should and can be proved rather than believed: a new skill, a description that never fires or fires on everything, a rule that has grown two decisions, an index that routes nothing an agent can see, a file too dense to read in one pass, or a check suite nobody has watched fail. Covers the activation surface, the routing gate, rule anatomy, page shape, naming, portability, and the invariant and mutation scripts. Use when the user says "write a skill", "this skill never triggers", "split this skill", "standardise these skills", or "how do I check this skill". Not for authoring product documentation, and not for deciding whether a task needs a skill at all.
Use when monitoring a PR (or a full Graphite stack of PRs) that needs CI fixes or review comment responses. Runs as a long-running session with intelligent sleep intervals. Handles failing checks, reviewer feedback, and pushes verified fixes autonomously.
Backend code quality for clean, production-ready, maintainable code. Adapts to the existing language, framework, and style. Covers functions, reusability, modern syntax, error prevention, readability, and security awareness. Use when writing, reviewing, or refactoring backend code for quality, maintainability, or production readiness.
Designs and executes tabletop breach simulation exercises for testing organizational breach response capabilities. Covers scenario creation with realistic inject timelines, participant role assignment, communication testing across internal and external channels, decision-point evaluation, and after-action report generation. Keywords: tabletop exercise, breach simulation, incident response testing, scenario design, after-action report.
Test Cherry Studio PRs by resolving and checking out a PR, statically inspecting its changes, running interactive UI tests against a safely tracked Electron instance through CDP, producing a structured report, cleaning up only the owned test instance, and restoring the original branch.
CI/CD pipeline patterns with GitHub Actions, release automation, and testing strategies. Use for: github actions, workflow, CI, CD, pipeline, deploy, release, semantic release, changesets, goreleaser, matrix, cache, secrets, environment, artifact, reusable workflow, composite action.
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.