244 items · Skills 107 · MCP 129 · Plugins 4 · Subagents 2 · CLI 2
Code & testing
Better code, faster: reviews, tests, debugging and up-to-date library docs.
What you can make
- PR code review
- E2E tests
- bug fix
- module refactor
With search, filters and ratings.
All items (244)
Skills (107)
A working methodology for the agent: spec, plan, TDD, debugging and review by subagents.
25 engineering skills: from spec and plan through TDD and review to shipping.
Safely refactors C# code without changing behavior: renames, extractions, merging types.
Gives the agent up-to-date knowledge of the Claude API and Anthropic SDKs: models, tools, caching.
67 expert skills for full-stack developers: languages, frameworks, APIs, testing, DevOps and data.
Teaches the agent to write code against the current Gemini API and SDKs instead of outdated patterns.
More than 40 Go skills: style, errors, concurrency, testing, performance and libraries.
Skills for Kotlin projects: backend with Spring and JPA and build tooling.
Teaches the agent to build agents with LangChain, LangGraph and Deep Agents (Python, TypeScript).
Skills for engineering with an agent: TDD, diagnosing bugs, specs, code review and PRs.
Walks the agent through building an MCP server in TypeScript or Python, with evaluations.
Teaches the agent to build agents with Pydantic AI and to migrate code from other frameworks.
The Sentry team’s skills for commits, PRs, code review and finding bugs in changes.
Creates and improves agent skills, tests them with evaluations and refines their descriptions.
Tests local web apps with Playwright scripts: screenshots, logs and selectors.
Enforces WCAG 2.2 AA while coding: specialists, an edit gate and audit reports.
Builds Adobe Commerce apps on App Builder: events, webhooks and admin panel extensions.
Audits GitHub Actions workflows that run AI agents for prompt injection.
98 skills for AI research: training, fine-tuning, interpretability and paper writing.
Skills for Vue, Nuxt, Vite, Vitest, Pinia and UnoCSS generated from the official docs.
Sets up Appium drivers for iOS and Android and diagnoses common test failures.
Adds pricing, subscriptions and usage-based billing to your app with Autumn.
Know-how for 18 AWS services: IAM, Lambda, ECS, EKS, S3, DynamoDB, CloudFormation and more.
Writes AWS infrastructure in CDK and SST, designs serverless systems and optimizes costs.
Azure AI Transcription (Python)
Real-time and batch transcription in Python with the Azure AI Transcription SDK.
Builds real-time voice apps with Azure AI Voice Live.
Generates podcast-style audio from text with the Azure OpenAI Realtime API.
Plans, validates and deploys apps on Azure, diagnoses resources and keeps an eye on costs.
Integrates the Cartesia API in code: Sonic TTS, Ink STT, voices and access tokens.
Integrates Chargebee: subscriptions, customers, payments, invoices and webhooks.
Builds and reviews WooCommerce plugins ready for the Marketplace and safe upgrades.
Clerk authentication in Next.js, React, Vue, Nuxt, Astro and more – setup and patterns.
Your agent writes, fixes and explains Cypress tests following guidance from the tool’s creators.
Official Dart skills: tests, static analysis, package conflicts and FFI.
Teaches the agent Databricks: the CLI, SQL, Genie, dashboards, jobs, pipelines and Lakebase.
Guides the agent through dbt models, tests, the semantic layer and dbt Mesh.
Teaches the agent the Deepgram API: transcription, speech synthesis, voice agents and audio analysis.
DevOps Skills (cc-devops-skills)
Generates and validates Terraform, Helm, K8s manifests, Dockerfiles, CI pipelines and PromQL.
Differential Review (Trail of Bits)
Reviews code changes for security and writes an evidence-backed report.
Writes and optimizes Dockerfiles and Compose files, runs agents in Docker Sandboxes.
Documentation Writer (Diátaxis)
Writes technical documentation following Diátaxis: tutorials, how-to guides and reference.
Integrates Dodo Payments: checkout, subscriptions, webhooks, billing and license keys.
Builds real-time voice and video apps on the Gemini Live API.
Finds leaked secrets in code and history, installs hooks and plants honeytokens.
Integrates Gladia transcription in apps: recordings, real time and speech analysis.
Writes, tests and refactors Terraform code the way HashiCorp recommends, including providers.
Teaches the agent to build durable functions, events and AI agents on Inngest in TypeScript.
Writes correct Kubernetes manifests: no deprecated APIs, with limits, RBAC and probes.
Builds, tests and deploys voice agents with LiveKit Agents (Python and Node.js).
Creates marimo notebooks, converts from Jupyter and Streamlit and builds widgets.
Builds stores on Medusa: modules, workflows, API routes, admin dashboard and storefront.
Designs usage-based billing in Metronome: events, rate cards, credits and invoices.
Sets up, writes and publishes technical documentation in Mintlify, including from OpenAPI.
Adds MLflow tracing to GenAI apps, analyzes traces and runs evaluations.
Suggests modern browser APIs instead of heavy libraries and outdated patterns.
Reviews and fixes Terraform module PRs against the terraform-aws-modules family rules.
Helps write MongoDB queries, design schemas and use Atlas Search.
Teaches the agent the Mubert Music API: generation, streaming and a royalty-free music library.
Cypher, graph modeling, drivers, imports, GraphRAG, GDS and Aura provisioning.
Teaches the agent the Neon platform: branching Postgres, Auth, object storage and functions.
Turns a Notion spec into an implementation plan with tasks and progress tracking.
OpenTelemetry Agent Skills (OllyGarden)
Instruments apps with OpenTelemetry and configures the Collector, OTTL and conventions.
Instruments apps with OpenTelemetry: SDKs, semantic conventions, Collector and OTTL.
Implements Paddle Billing: products, checkout, customer portal, subscriptions and webhooks.
Postgres best practices plus search across the PostgreSQL, TimescaleDB and PostGIS docs.
Guides you through Pinecone indexes, search, Assistant, the CLI and n8n workflows.
Scaffolds Pipecat voice bot projects, deploys them to Pipecat Cloud and starts voice chats.
Know-how for MySQL, Postgres, Vitess and Neki: schemas, indexes and query tuning.
The agent writes and runs its own Playwright scripts – from a page test to complex flows.
Implements Polar payments: products, checkout, customer portal, webhooks and migration.
Posit skills for R and Python: Shiny, Quarto, ggsql, testthat and package releases.
Writes and debugs Pulumi infrastructure and migrates from Terraform, CDK, CloudFormation and ARM.
Analyzes R8 keep rules and flags redundant or overly broad ones to shrink the app.
Writes React Native component tests with React Native Testing Library v13 and v14.
Redis best practices: data structures, connections, search and semantic caching.
Teaches the agent to send email through Resend, build it with React Email and keep it deliverable.
Helps build the Runway API into apps: video models, characters, recipes and workflows.
Saleor know-how: storefronts, apps, webhooks and store configuration as code.
Writes safer code using Semgrep’s rules: OWASP Top 10, IaC and LLM security.
Builds Slidev presentations in Markdown: code, animations, diagrams, math and export.
Scans dependencies with Socket, patches and replaces risky packages, ships releases safely.
Checks the quality gate, lists and fixes SonarQube issues and analyzes dependency risks.
39 skills for Spree Commerce: products, checkout, payments, promotions and deployment.
Plans a sprint: scope, team capacity including time off, goal, priorities and carryover.
Builds your daily standup from commits, PRs and ticket moves: yesterday, today, blockers.
Static Analysis (Trail of Bits)
Runs CodeQL and Semgrep scans and turns SARIF results into a list of vulnerabilities.
Points the agent to the right Stripe APIs: Checkout, PaymentIntents, Connect, subscriptions and tax.
Recommends a Stripe Connect setup for platforms, marketplaces and split payments.
Builds SumUp payments: card terminals and online checkout, with testing and debugging.
Teaches the agent Supabase and Postgres rules: RLS, indexes, auth, connections, schema.
Reports risks in npm, PyPI and Go dependencies: advisories, abandoned projects, install scripts.
Safe concurrency in Swift 6: data races, isolation, actors and migration.
Swift Testing in practice: XCTest migration, parameterized tests, tags and async.
Teaches the agent Sylius 2.x idioms: resources, TwigHooks, admin grids and events.
Builds, tests and deploys apps and agents for Microsoft Teams and Copilot.
Helps build and debug durable Temporal workflows in eight SDK languages.
Terraform and OpenTofu best practices: testing, modules, state, CI/CD and security.
Cuts agent hallucinations with Terraform and OpenTofu while keeping token use low.
Teaches the agent to write background jobs, scheduled tasks and AI agents on Trigger.dev.
The agent reviews branches, finds the changeset that introduced a bug and merges changes in Unity VCS.
Guides upgrades of the Stripe API version, SDKs, Stripe.js and webhook endpoints.
The Vercel team’s rules for React and Next.js: performance, composition and UI audits.
Visa Acceptance Best Practices
Guides Visa Acceptance integrations: payments, fraud, PAX terminals and Click to Pay.
Teaches Visa Developer Platform integrations and agent purchases with Visa Intelligent Commerce.
Creates and searches Weaviate collections, imports data and helps build AI apps.
Benchmarks Xcode builds, finds the bottlenecks and plans how to speed them up.
Writes Zoho CRM integrations: REST API, Deluge scripts, ClientScript, widgets and COQL.
MCP (129)
Creates issues and pull requests, reviews code and tracks Actions workflows on GitHub.
Clicks, fills out forms and tests pages in a real browser through Playwright.
Searches errors and issues in Sentry, reads stack traces and Seer root cause analyses.
Searches code by its syntax structure (AST) and helps write ast-grep rules.
Reads repositories, pull requests, work items, builds and wikis in Azure DevOps.
Tests websites and apps on real browsers and devices in BrowserStack.
Debugs pages in Chrome: console and network traffic, performance measurement, screenshots.
Searches an entire codebase by meaning using an index in a vector database.
Pulls quality and security issues, test coverage and PR analysis from Codacy.
Indexes a project and gives the agent fast code search and file summaries.
Indexes code into a local graph and answers questions about calls, dependencies and changes.
Turns local code into a graph and shows the agent calls, inheritance and dependencies.
Scores Code Health in CodeScene and makes sure the agent’s changes don’t degrade the code.
Searches documentation from the docsets installed in the Dash app on macOS.
Debugs code in VS Code: sets breakpoints, steps through execution and inspects variables.
Checks status, diffs and history of a local Git repository, makes commits and branches.
Connects Git with pull requests and issues from GitHub, GitLab, Jira and Azure DevOps.
Reads and creates issues and merge requests, checks the repository and pipelines in GitLab.
Handles projects, merge requests, issues, pipelines and wikis in GitLab with a token.
Builds a knowledge graph of your code: calls, dependencies, change impact and safe renames.
Google Developer Knowledge MCP
Searches and reads up-to-date Google developer documentation, such as Google Cloud.
Gives the agent Go language server tools: symbols, references and diagnostics.
Finds and edits Grafana dashboards, queries data sources, alerts and incidents.
Searches code in about a million public GitHub repositories through grep.app.
Indexes library documentation for the versions your project uses and searches it locally.
Gives the agent JetBrains IDE tools: inspections, search, refactoring and a debugger.
Manages Kubernetes and OpenShift resources: pods, logs, events and Helm charts.
Creates and updates issues, projects and comments in Linear right from the editor.
Gives the agent knowledge of an Nx monorepo: project graph, tasks, generators and docs.
Researches code on GitHub and npm – repositories, pull requests and packages – and optionally local code.
Searches and reads up-to-date OpenAI developer documentation: the API, Codex and models.
Manages collections and environments in Postman and generates client code from API definitions.
Searches large codebases with ripgrep plus syntax trees and returns whole functions and classes.
Packs a local or remote repository into a single AI-friendly file and searches the output.
Finds and edits code at the symbol level through language servers, like an IDE.
Pulls code issues, quality gate status, metrics and test coverage from SonarQube.
Searches code and history across every repository indexed in Sourcebot.
Searches and navigates code across all of a company’s repositories through Sourcegraph.
Guides the agent through a spec – requirements, design and tasks – with a progress dashboard.
Writes IaC against up-to-date provider and module schemas and supports HCP Terraform.
Deploys projects to Vercel, reads build logs and searches the platform documentation.
Drives apps on iOS, Android and other platforms through a CLI or an MCP server.
Creates, changes and deletes Aiven services: PostgreSQL, Apache Kafka and applications.
Serves Google’s official Android skills over MCP: listing, search and full content.
Gives the agent AOSP and AndroidX source code so it doesn’t guess from stale knowledge.
Lets the agent use the Angular CLI: docs, best practices, workspace projects and migrations.
Automates iOS and Android app tests through Appium, including on real devices.
Jira, Confluence and Bitbucket Data Center for the agent, on your own servers.
Jira and Confluence from chat: searches, summarizes, creates issues and pages.
Validates CloudFormation templates, troubleshoots deployments and searches CDK documentation.
Builds, deploys and monitors serverless apps on AWS Lambda with the SAM CLI.
Manages Azure resources: Storage, Cosmos DB, Key Vault, AKS, App Service and monitoring.
Searches and cites the BigCommerce developer docs while you write an integration.
Console, network, screenshots and Lighthouse audits from your Chrome session, straight to your agent.
Reviews app errors, performance and releases in BugSnag, with OAuth sign-in.
Browses Buildkite pipelines, builds, jobs, logs and tests and retries failed jobs.
Guides your Checkout.com integration and handles payments, refunds and payment links.
Diagnoses failed CircleCI builds, reads logs and reruns or cancels workflows.
Long-term agent memory built on a knowledge graph: remember, recall and forget.
Gives the agent up-to-date library docs instead of the ones from its training data.
Your agent asks Cypress Cloud about test runs, failures and flaky tests.
Analyzes Dart and Flutter code, runs tests, hot reloads and reads the widget tree.
Runs SQL on Postgres, MySQL, MariaDB, SQL Server, Oracle and SQLite from a single server.
Knows the models, lineage and metrics of a dbt project and runs build, run and test.
Answers questions about public GitHub repositories based on their wikis.
Runs terminal commands, manages processes and edits files on your computer.
Generates and edits diagrams and technical docs in Eraser from a description.
Your agent opens pages in Firefox and inspects them with developer tools.
Inspects and drives a running Flutter app: screen snapshots, taps and hot reload.
E2E tests without test code: the agent taps through Flutter, React Native, iOS or Android apps.
Searches GameAnalytics docs: SDKs for Unity, Unreal, iOS and Android plus the API.
Lets the agent analyze binaries in Ghidra: decompilation, renaming, imports and exports.
Detects leaked secrets in code and manages GitGuardian incidents and honeytokens.
Agent memory that learns from experience: it retains, recalls and reflects.
Sends events, invokes Inngest functions, tracks runs and reruns failed ones.
Taps through the iOS Simulator, reads UI elements and takes screenshots and recordings.
Edits and runs Jupyter notebook cells live, and reads charts too.
MCP, guidelines and skills for agents in Laravel projects: database, logs and docs.
Creates and changes LaunchDarkly feature flags, their targeting and release plans.
Reads crashes, hangs, bug reports and app reviews from Luciq (formerly Instabug).
Runs Maestro E2E tests on Android, iOS and the web, reads the screen and takes screenshots.
Browses Mastercard Developers services, docs and API specs while you build an integration.
Connects the agent to SQL databases through SQLAlchemy: structure, relations, queries and reports.
Searches, creates and updates Jira issues and Confluence pages.
Persistent memory for agents: a knowledge graph, semantic search and a web dashboard.
Queries BigQuery, AlloyDB, Spanner, Cloud SQL and many more databases with prebuilt tools.
Helps you integrate Mercado Pago payments: docs, applications, webhooks and testing.
Validates and renders Mermaid diagrams to PNG and saves them to Mermaid projects.
Searches official Microsoft and Azure documentation and code samples.
Creates diagrams, docs and tables on Miro boards and reads context from them for coding.
Drives iOS and Android apps: taps, scrolls, types text and installs apps.
MobileBuildMCP (XcodeBuildMCP)
Builds, runs and tests iOS and macOS apps from Xcode on simulators and devices.
Explores MongoDB collections, runs queries and aggregations, and manages Atlas clusters.
Reads schemas and runs queries in MySQL; writes only when explicitly enabled.
Creates Neon projects and branches, runs SQL and tests migrations on a temporary branch.
Draws draw.io diagrams from your project’s files, with a live preview in the browser.
Connects the agent to a running Next.js 16+ server: errors, logs and page metadata.
The agent sees the Android emulator in dp, taps, toggles dark mode and RTL and reads logcat.
Writes, runs and fixes custom FeatureScript features in Onshape documents.
Searches the OpenTofu Registry: providers, modules, resources and configuration examples.
Issues PayPal invoices and handles orders, refunds, disputes and subscriptions from chat.
Creates Pinecone indexes, upserts and searches records and looks up the docs.
Gives a coding agent a voice: spoken conversation and screen viewing through Pipecat.
Manages projects, work items, cycles and modules in Plane.
Diagnoses a Postgres database, reads EXPLAIN plans and picks indexes for the workload.
Queries PostHog in HogQL, manages feature flags and experiments, and reviews errors.
Creates Prisma Postgres databases, runs SQL and restores backups from chat.
Browses Pulumi stacks and resources and checks policy violations and Registry schemas.
Searches API and library documentation and returns only what is needed.
Fetches Rollbar errors and occurrences, checks deploys and updates items.
Queries Salesforce with SOQL and edits records, objects, fields and Apex code.
Starts sessions on Sauce Labs real devices, installs apps and reviews test results.
Scans code with Semgrep static analysis and catches security issues before they ship.
Gives the agent a tool for breaking a problem into steps, with revisions and branches.
Scans code and dependencies with Snyk and helps the agent fix the vulnerabilities it finds.
Scores the security of npm, PyPI and other ecosystem dependencies before you use them.
Searches and reads Apple documentation, Human Interface Guidelines and WWDC transcripts.
Manages Stripe products, prices, payment links, customers and subscriptions from chat.
Designs tables, runs SQL and migrations, generates types and reads Supabase logs.
TestMu AI MCP (formerly LambdaTest)
Failed test analysis, SmartUI visual regressions and accessibility checks in TestMu AI.
Your IDE agent has TestSprite plan, write and run tests for your app.
Triggers and deploys Trigger.dev tasks, tracks runs and searches the docs.
Works with Redis, QStash, Workflow, Vector and Search in Upstash, with OAuth sign-in.
USD Code MCP (NVIDIA Omniverse)
Gives the agent OpenUSD API help: modules, classes, methods, code examples and a knowledge base.
Voice conversations with Claude Code: you speak into the mic and the agent talks back.
Drives browsers and iOS and Android apps through WebdriverIO and Appium.
Connects Claude Code or Codex to a project open in Xcode: project changes and builds.
Edits .xcodeproj files: targets, files, build settings, build phases and dependencies.
Analyzes crashes, sessions and network traffic of mobile apps from XCOR RUM (Embrace).
Plugins (4)
Teaches the agent to build and deploy on AWS: CDK, CloudFormation, serverless, containers.
Workers, Durable Objects and Wrangler skills plus an MCP server for Cloudflare’s full API.
Reviews pull requests with several agents at once and filters out false positives.
Catches vulnerabilities in code written by Claude: injection, XSS, SSRF and secrets.
Subagents (2)
94 plugins with over 200 subagents, 185 skills and commands for various stacks.
Over 160 ready-made Claude Code subagents in 10 categories – from languages to DevOps.
CLI (2)
Opens pages, clicks, types and takes screenshots via Playwright – no MCP overhead.
Controls a browser from the terminal: clicks, fills forms, saves screenshots and PDFs.