Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Playwright testing best practices for Next.js applications (formerly test-playwright). This skill should be used when writing, reviewing, or debugging E2E tests with Playwright. Triggers on tasks involving test selectors, flaky tests, authentication state, API mocking, hydration testing, parallel execution, CI configuration, or debugging test failures.
Use this skill when posting the final summary comment, including its No Verdict form when nothing could be reviewed and no inline comments exist. Otherwise apply as the LAST step of code review, after all findings are classified and inline comments are complete. Detects context (caller-declared local-file output, agent mode sticky comment, GitHub Actions MCP tool, or local file) and routes output accordingly.
Prompt engineering frameworks for building, testing, versioning, and evaluating prompts: chain-of-thought, few-shot, regression testing, and rubrics. Use when designing production prompts, running A/B tests, or building prompt libraries.
Run a comprehensive multi-perspective code review on current changes. Activates the Review Council (security, quality, documentation, domain review) and runs automated security scanning. Use before creating a pull request or when you want a thorough review of your work.
Definition-of-done checklist for shipping a new write, signal, table, edge, or query to the ax graph. Use when adding a SurrealDB table/edge/field, an ingest derive-stage, a new analytic query, or any new ax capability - before opening the PR. Ensures every write gets an on-demand read AND a proactive (agent-facing) read AND docs/distribution, not just the write. Triggers on "ship", "new signal", "new table/edge", "new lens/query", "wire this up", "is this done", or finishing an ax feature branch.
Root-cause fix discipline for a debugging session already underway. Use when about to propose or apply a fix for a bug or test failure, when tempted to patch a symptom (add a null check, wrap in try-catch, bump a timeout, add a retry), and when a previous fix didn't work. /diagnosing-bugs builds the repro; this governs the fix.
Configures and leverages the Testomat.io MCP server for test management analytics, run analysis, failure investigation, and defect triage. Use when the user needs to connect to Testomat.io via MCP, analyze test runs, cluster failures, investigate root causes.
Verify whether a live web app matches its design specification using deterministic CSS checks against the DOM, AND verify user flows by executing Gherkin scenarios via Nova Act. Translates design claims into rules and runs them via verify_* MCP tools; executes flows via act() and act_get(). Produces a combined visual + flow report with annotated screenshots and per-flow detail. Use when checking visual style, component rules, accessibility, project conventions, platform patterns, or end-to-end user journeys against a live site.
Use when reviewing or scoring AI-generated business/application code quality in any language, especially when a numeric score, risk level, or must-fix checklist is requested, or when C++ code must comply with OpenHarmony C++ and security standards
Perform code review on staged changes or a pull request. Checks for bugs, security issues, performance problems, and best practices. Use when user says "review code", "check my code", "review PR", or "is this code okay". The +check flag validates findings via a fresh-context subagent; validation also runs automatically when the review produced confidence markers.
This skill should be used when the user asks to "analyze code for security issues", "check for OWASP vulnerabilities", "review code against CWE Top 25", "find injection vulnerabilities", "do a security code review", or needs manual security analysis against OWASP Top 10, API Top 10, Mobile Top 10, or CWE/SANS frameworks.
This skill converts manual test cases into production-ready automated test scripts. It analyzes the existing automation framework, interprets manual test steps, and generates maintainable tests following automation best practices. Use this skill whenever the user wants to automate manual test cases, expand test coverage, or create end-to-end automated flows from existing test documentation.
Best practices for Bloc state management in Flutter/Dart, covering Cubit versus Bloc, event and state naming, sealed classes with Equatable, the Page/View split with BlocProvider, BlocBuilder, BlocListener, and BlocSelector. Use when writing, modifying, or reviewing code that uses package:bloc, package:flutter_bloc, or package:bloc_test. Also use for any test of a class that extends Bloc or Cubit, including "write the unit tests for this bloc", "test my cubit", "add tests for LoginBloc", mocking a repository a bloc depends on, and asserting the states an event emits. Bloc and Cubit tests must use blocTest() from package:bloc_test with package:mocktail, so prefer this over the testing skill whenever the class under test is a Bloc or Cubit. Also use when a request pushes against these rules, such as injecting one bloc into another to read its state, calling a repository from a widget or build method, or keeping a Cubit for a feature that needs an event transformer such as debounce.
Use when reviewing the code/configuration changes on a Datex Studio feature branch. Traces dependencies, reads unified diffs across all changed configs, and produces a structured review with bugs / quality / security / performance / simplification / alignment findings plus a verdict. Trigger for: "review branch X", "code review this branch", "review the changes on <branch>", "audit branch before merge", "quality check this branch". For drafting a commit message on the same branch, use `commit-message-generator`.
Validates and repairs an in-scope change, publishes its draft pull request, reconciles metadata and CI, and marks it ready for review. Use when asked to open, raise, or publish a pull request for the current change, or when the user runs /create-pr.
Use when designing a study that benchmarks AI systems against a human-expert panel, before data collection. Plans the arms, decoupled rubrics with anchors, planted calibration probes, reviewer panel, inter-rater reliability targets and LLM-as-judge versus human adjudication.
Get a PR merge-ready for Dylan: deep /dyl-review till 🟢, mark it ready, resolve conflicts, then babysit CI and comments. Use for /dyl-ready-pr, "get PR green", "make the PR mergeable", "/dyl-review till green then ready", or ready-to-merge asks under /dyl-mode.
Fix a reported bug in React Router from a GitHub issue. Use when the user provides a GitHub issue URL and asks to fix a bug, investigate an issue, or reproduce a problem. Handles the full workflow: fetching the issue, finding the reproduction, writing a failing test, and implementing the fix.
Run and inspect an app on an iOS Simulator: choose a target, install and launch, capture evidence, exercise accessibility-driven UI, and diagnose simulator failures. Use for explicit simulator testing or automation, not general iOS implementation, physical-device validation, or App Store approval.
Find out what is going wrong in LLM or agent traffic by reading sampled Phoenix traces, spans, or sessions, writing free-form notes (open coding), then grouping the notes into a few narrow annotations, one per failure dimension with a small label set and counts, that pick eval targets and fix priorities (axial coding). Use for "what's going wrong with this agent", "I just instrumented my app, where do I start", "review these traces", "the chatbot keeps losing context", "what kinds of mistakes is the model making", "what categories of failures do we have", "what should I build evals for", "how do I prioritize fixes", "group these notes", "MECE breakdown" — or any framing that needs observations or categories grounded in real traces rather than invented top-down, even without naming the technique.
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos (auto-detected). Activates on "revdiff", "review diff", "review changes", "annotate diff", "git review with revdiff", "hg review with revdiff", "review jj change", "interactive diff review", "revdiff all files", "review all files", "browse all files", "revdiff FILE", "revdiff README.md", "revdiff /tmp/notes.txt", "review this file", "annotate this file", "review file with revdiff", "open this review in revdiff", "show review in revdiff", "review in revdiff", "revdiff config", "revdiff themes", "revdiff keybindings", "how to configure revdiff", "what themes does revdiff have".
Review code changes and identify high-confidence, actionable bugs. Use when the user wants to: - Review a pull request or branch diff - Find bugs, security issues, or correctness problems in code changes - Get a structured summary of review findings
Generate comprehensive Apex test classes with @TestSetup methods, TestFactory patterns, bulk data (200 records), positive/negative/permission scenarios, and HttpCalloutMock implementations. Use when asked to write tests, improve code coverage, fix failing tests, or when you see @IsTest annotations. Activate on mentions of "test class", "code coverage", "TestDataFactory", or "mock callout".
Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, reconciliation report, production vs staging comparison. Uses mssql-python driver with Apache Arrow for fast columnar data transfer and comparison.
Generates pytest test suites with happy path, edge cases, error conditions, fixture scaffolding, mocks, async patterns. Triggers on: "generate tests", "write tests for", "test this function", "create test suite", "pytest for", "unit tests for", "mock strategy for".
Audit a UI, flow, or copy for dark (deceptive) patterns — design that manipulates users into unintended actions. Produces a prioritized findings list naming each pattern, its intent, severity, and an honest-design fix. Use when reviewing conversion flows, checkouts, paywalls, sign-ups, or cancellation flows for ethical design issues.
Help with ABAP Unit testing including test class setup, assertions, test doubles, mocking frameworks, dependency injection, CDS test environments, SQL test environments, RAP BO test doubles, and test fixtures. Use when users ask about ABAP unit tests, test classes, test methods, CL_ABAP_UNIT_ASSERT, test doubles, mocking, CDS test environment, SQL test environment, RAP testing, ABAP test injection, test seams, behavior-driven testing, TDD in ABAP, test isolation, or writing automated tests for ABAP code. Triggers include "write a unit test", "create test class", "mock a dependency", "test a CDS view", "test a RAP BO", "test double", "assertion", "test fixture", "test isolation", or "ABAP unit".
SOLUTIONING GATE — validates cohesion across planning artifacts before any implementation begins. Cross-references PRD (or tech-spec), architecture document, and epics/stories for coverage consistency and missing pieces. Returns a verdict of PASS, CONCERNS, or FAIL with specifics. Does NOT touch code. Use when the user says: - "check if we're ready to build" / "are we ready to implement?" - "validate planning" / "gate check" / "readiness check" - "run the solutioning gate" / "check implementation readiness" - "is the architecture complete?" / "do requirements match architecture?" - "sign off on planning" / "planning done, check it" - "validate PRD against architecture" / "cross-reference planning docs" Intents supported: Validate (primary). Track-adaptive: works for Quick Flow (tech-spec + architecture), BMad Method (PRD + architecture + epics), and Enterprise (all of the above + optional security/DevOps addenda).
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. This skill should be used when code-quality checks pass but the code would benefit from structural cleanup — deduplication, branching simplification, naming improvements, or dead-code removal. Invoked as a subagent from /code-quality or directly via the Task tool.
Optimize DSPy programs with dspy.GEPA — a reflective/evolutionary optimizer to consider against task-specific baselines within an authorized evaluation budget. Use when the user says optimize, compile, GEPA, reflective optimization, or "make this program better" and a DSPy program + metric + trainset exist.
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.