Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster', 'reduce latency', 'improve performance', or points at a CodSpeed benchmark result wanting improvements. Also trigger when the user mentions a slow function, a regression, or wants to understand where time is spent in their code
Performance benchmarking expertise for shell tools, covering benchmark design, statistical analysis (min/max/mean/median/stddev), performance targets (<100ms, >90% hit rate), workspace generation, and comprehensive reporting
Reviews, writes, and refactors ReactLynx code and component libraries for Lynx dual-thread best practices. Applies when writing ReactLynx components, or handling background-only, useLayoutEffect, bindtap/catchtap, main-thread:*, runOnMainThread/runOnBackground, lazy/Suspense, globalPropsMode/__globalProps, component-library publishing (preserved JSX vs React.createElement), or render/diff/commit performance traces. Excludes vanilla Lynx Element PAPI without ReactLynx JSX (use vanilla-lynx), running-app debugging via DevTool/CDP (use lynx-devtool), or Rspeedy/tsconfig config (use lynx-typescript).
Use when you need to review, improve, or write Java unit tests — including migrating from JUnit 4 to JUnit 5, adopting AssertJ for fluent assertions, structuring tests with Given-When-Then, ensuring test independence, applying parameterized tests, mocking dependencies with Mockito, verifying boundary conditions (RIGHT-BICEP, CORRECT, A-TRIP), leveraging JSpecify null-safety annotations, or eliminating testing anti-patterns such as reflection-based tests or shared mutable state. This should trigger for requests such as Review Java code for unit tests; Apply best practices for unit tests in Java code; Write fast JUnit unit tests for Java code; Improve Mockito-based Java unit tests; Refactor Java tests to isolate collaborators. Part of Plinth Toolkit
Expert debugging and profiling for leaks, GPU/Visual Profiler, headless CI QA, orphan nodes, thread-safe logs, and custom Debugger monitors — not print/breakpoint tutorials. Trigger on OBJECT_ORPHAN_NODE_COUNT, ObjectDB growth, Visual Profiler GPU spikes, flaky headless exits, or remote device consoles. Keywords: orphan nodes, Performance.get_monitor, Visual Profiler, Time.get_ticks_usec, EditorDebuggerPlugin, headless QA, push_error, backtrace.
Playwright browser automation API, web scraping, and tooling. Covers locator strategies, assertions, API testing, stealth mode, anti-bot bypass, authenticated sessions, screenshots/PDFs, Docker deployment, configuration, debugging, and MCP integration with AI agents. Prevents documented errors including CI timeout hangs, extension testing failures, and navigation issues. Use when automating browsers, scraping protected sites, bypassing bot detection, generating screenshots/PDFs, configuring Playwright Test, troubleshooting Playwright errors, or learning Playwright API patterns. For E2E test architecture, Page Object Models, CI sharding strategies, or test organization patterns, use the e2e-testing skill instead
Advanced Python unit testing framework for customer support tech enablement, covering FastAPI, SQLAlchemy, PostgreSQL, async operations, mocking, fixtures, parametrization, coverage, and comprehensive testing strategies for backend support systems
Generates Vitest tests in JavaScript/TypeScript with Vite-native speed. Jest-compatible API with ESM support and HMR. Use when user mentions "Vitest", "vi.mock", "vitest.config". Triggers on: "Vitest", "vi.mock", "vi.fn", "Vite test", "vitest config".
Zig testing skill for writing and running tests. Use when using zig build test, writing comptime tests, using test filters, working with test allocators to detect leaks, or using Zig's built-in fuzz testing (0.14+). Activates on queries about Zig tests, zig test, zig build test, comptime testing, test allocators, Zig fuzz testing, or detecting memory leaks in Zig tests.
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization. Applies the RED-GREEN-REFACTOR cycle to process documentation by running a baseline without the skill, writing to address failures, and iterating to close loopholes.
Reviews a local diff, branch diff, or PR with file:line findings in confirmed and plausible tiers, gates any test the diff adds or changes, and in apply mode lands the fixes and diff-scoped simplifications. Use when asked to "review my changes", "code review", "tidy this", "simplify my diff", "deslop this", "structural review", "security audit", or "audit these tests in my PR". For the PR itself use pr-creator; for CI and review threads use pr-babysitter; for UI defects use ui-design; for repo architecture use codebase-architecture; for pruning the whole suite to a target use test-audit
Manage Apidog project resources through Apidog CLI. Trigger scenarios - running API automation tests/test suites, querying/creating/updating/deleting endpoints, environments, schemas, mocks, branches and other project resources, importing/exporting API documentation, viewing test reports, managing runners, scheduled tasks, notifications and CI/CD configuration. CLI output is structured JSON and often includes agentHints.nextSteps; all commands support --help.
Screenshot or record a cmux window from the CLI, for a pull request, a bug report, or to see what the app actually looks like right now. Use when a change is visual, when a drag or an animation cannot be described in text, or when a reviewer needs evidence rather than a claim.
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior. Applies the RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing.
Use when a developer wants to test, try out, smoke-test, verify, or confirm that a Slack app built with the Slack CLI (or a plain Bolt app) actually works, by running it in a developer sandbox or a Free Team, never a workspace with real users, with `slack run` and exercising its real slash commands, shortcuts, events, actions, modals, App Home, and assistant surfaces. Also covers `slack doctor` and `slack manifest validate` health checks before hands-on testing.
QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired via the SSE event stream, smoke-test the TUI under tmux, and investigate sessions in opencode's SQLite DB by id, title/name, or message text. Ships tested helper scripts (each with a --self-test) plus per-domain references. Use whenever someone wants to QA, smoke-test, verify, or debug opencode's CLI, HTTP server, plugin hooks/events, or TUI, or to find/inspect opencode sessions in the database. Triggers: opencode qa, qa opencode, test opencode, verify opencode hook, opencode session db, find opencode session by id/name/text, opencode tui test, opencode server health, opencode event stream
Set up performance benchmarks and a CodSpeed harness for a project. Use this skill whenever the user wants to create benchmarks, add performance tests, set up CodSpeed, configure codspeed.yml, integrate a benchmarking framework (criterion, divan, pytest-benchmark, vitest bench, go test -bench, google benchmark), or says “add benchmarks,” “set up perf tests,” “create a benchmark,” “benchmark this,” or wants to measure their code's performance for the first time. Also trigger when the optimize skill needs benchmarks that don't exist yet.
Run and configure oxlint — the high-performance JavaScript/TypeScript linter built on the Oxc compiler stack. Use this skill whenever working in a project that has oxlint installed (check for `oxlint` in package.json devDependencies or an `.oxlintrc.json` / `oxlint.config.ts` config file). This includes when you need to lint code after making changes, fix linting errors, configure oxlint rules/plugins, set up or modify `.oxlintrc.json`, or migrate from ESLint.
Triage and fix one microsoft/playwright issue, or do a maintainer's task, unattended inside the Issue triage GitHub Actions workflow (.github/workflows/triage.yml), which a needs-triage, needs-triage-mac or needs-triage-win label starts, or a maintainer starts by hand with an issue, a task or both. Reproduces the issue on the runner, then leaves a verified fix proposal for the workflow to open as a draft PR, or an investigation note for it to post on the issue. Only for that workflow.
Search across all timelines in an Antithesis test run to find events, correlate property failures, and answer temporal questions about ordering and causation (e.g., did event A always precede failure B? do failures occur even without a preceding fault?).
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Perform security audits on code changes, diffs, or branches to find high-confidence exploitable vulnerabilities. Use when asked to “audit security,” “review for vulnerabilities,” “security scan,” “check for security issues,” “audit this PR,” “review these changes for security,” or “find vulnerabilities in diff.” Distinct from security-review (which provides secure coding patterns/checklists)—this skill actively audits code changes using a structured methodology with false positive filtering. Includes Python scripts for GitHub Action CI integration and PR evaluation.
Expert blueprint for performance profiling and optimization (frame drops, memory leaks, draw calls) using Godot Profiler, object pooling, visibility culling, and bottleneck identification. Use when diagnosing lag, optimizing for target FPS, or reducing memory usage. Keywords: profiling, Godot Profiler, bottleneck, object pooling, VisibleOnScreenNotifier, draw calls, MultiMesh.
Use this skill when the user provides a failed Steel session ID, failed automation run, timeout, browser error, blocked page, or unexpected result and wants evidence-backed diagnosis using session metadata, browser logs, raw agent logs, semantic traces, replay links, screenshots, network failures, or errors. Do not use for first-pass bot mitigation; collect evidence here, then hand off to steel-reliability for proxy, CAPTCHA, identity, or anti-bot fixes.
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
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.