Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use for bug, regression, broken behavior, or production issue reports that need expected behavior, reproduction evidence, root cause analysis, or a fix plan before code changes. Trigger when the report is incomplete, high-impact, user-facing, or likely tied to recent changes. Do not trigger for new feature work, security scan remediation, documentation-only requests, or tiny direct fixes where the user explicitly asks to patch now.
Use this skill to install, uninstall, list, inspect, and reset Android apps via `adb install` (with `-r` reinstall, `-d` allow-downgrade, `-t` allow test packages, `-g` grant all runtime permissions, `--user` per-user install, `adb install-multiple` for split APKs) and the on-device `pm` tool (`pm list packages [-f|-d|-e|-s|-3|-i|-u]`, `pm path`, `pm clear`, `pm grant` / `pm revoke`, `pm enable` / `pm disable`, `pm uninstall [-k]`, `cmd package dump-profiles`). Calls out the canonical hermetic-reset pattern (`pm clear` wipes data; `am force-stop` does NOT) and the common install errors (`INSTALL_FAILED_USER_RESTRICTED`, `INSTALL_FAILED_VERSION_DOWNGRADE`, signing-conflict). Use when the user mentions "reset app between tests", `pm clear`, `am force-stop` confusion, install fails after debugger, split APK install, runtime permission grants, multi-user profile installs, or "how do I list third-party apps".
Collaborative workflow for handling GitHub issues. Use when a user receives an issue that needs analysis and a reply. Through the four-step method "diagnose → classify → decide → reply", it produces an accurate root-cause analysis and a professional user reply from a single issue, avoiding misjudging the problem type or giving an unprofessional reply.
Apply this opinionated workflow when modernizing legacy systems: strangler fig pattern, branch by abstraction, characterization tests, incremental monolith decomposition, framework upgrades, feature-flagged migration with rollback.
The step-by-step procedure for running this repo's Promptfoo evals with a generator and a judge over provider APIs. Use when starting a new skill and needing a baseline before writing content, when a run stalls or returns no data, when a provider rate-limits, or when deciding whether an edit needs a retest.
Use when: preparing for launch after risk control is complete, needing a launch checklist and rollback plan, or running the formal release process. Do NOT use when: the launch process is already standardized and automated by operations, or a simple release needs no checklist
Onboard prek (Rust-powered pre-commit) into any project and suggest hooks tailored to the language/framework. Use when the user says "add prek", "set up pre-commit hooks", "configure prek", "what hooks should I use", or when you notice a project without a prek.toml that would benefit from pre-commit checks. Also trigger when the user wants to add new hooks to an existing prek.toml, audit their hook config, or migrate from pre-commit to prek. Covers Rust, Python, TypeScript/JavaScript, Go, Ruby, and Shell projects. Do NOT use for husky, lint-staged, or CI pipeline hook configuration — this skill is specifically for prek.
Audit UI/UX in a SENIOR style — four sections: accessibility · visual-hierarchy · consistency · antipattern, each giving a SCORE/10 + MOST SEVERE ISSUE + HOW TO FIX, then a conclusion of PASS-to-next-step or NEEDS-FIXING. The MEASURABLE part (WCAG contrast, tap-target, geometric overlap/misalignment, missing-label) runs deterministically through the visual-qa engine (headless, 0-token, NO LLM); the part needing EYES (hierarchy, design-system drift, dark-pattern) is an LLM audit. Call when the user says "qc uiux", "audit ui", "inspect the interface", "clean up UI antipatterns", "/qc-uiux", or AFTER there is a mockup/UI. MIRRORS /qc-code (expensive = manual LLM, cheap = automatic deterministic tests). DIFFERENT from /redesign (aesthetic renewal) and /visual-qa (screenshot + pixel guarding) — qc-uiux is a 4-section senior verdict.
Debug React applications by inspecting components, props, and the component tree. Use when the user is debugging React apps, wants to inspect component props/state, find which component renders an element, or understand the React component hierarchy.
Override Riverpod providers for tests, debugging, or environment-specific behavior; ProviderScope and ProviderContainer overrides, overrideWith, overrideWithValue. Use when mocking providers in tests, injecting different implementations, or scoping provider behavior. Use this skill when the user asks about overrides, testing Riverpod, or mocking providers.
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.
Provides empirical test protocols and metrics to validate whether hypothesized symmetries actually hold in data or models before committing to equivariant architecture. Includes invariance/equivariance testing, group structure verification, and distribution analysis under transforms. Use when testing invariance, validating equivariance, checking symmetry assumptions, debugging symmetry-related model failures, or needing data-driven validation before architecture decisions.
Use when encountering bugs, unexpected behavior, test failures, or errors during development. Enforces a rigorous 4-phase investigation process that prevents shotgun debugging. Triggers: test failure, runtime error, unexpected behavior, production incident, performance regression.
Use when writing any new code, adding features, or fixing bugs that require code changes. Enforces strict RED-GREEN-REFACTOR cycle with no production code without a failing test first. Triggers: new feature implementation, bug fix, refactoring existing code, adding behavior to existing modules.
Use when choosing a testing approach for a project — selecting frameworks, defining coverage thresholds, setting up test infrastructure, and establishing testing patterns. Triggers: new project setup, CI/CD pipeline design, coverage audit, test framework migration, quality standard definition.
Convert one or more webpage/app UI screenshots into a high-fidelity responsive implementation, either as a standalone page or by adapting an existing frontend. Prioritize exact viewport matching, typography/icon audits, explicit spacing and colour matching, browser screenshot comparison, and repeated refinement until no obvious mismatches remain. Handle missing assets by using supplied files, generating missing raster assets with direct image_gen when available, preferably as extractable asset sheets for multiple related assets, or otherwise using placeholders plus a single copy-paste code block containing one standalone generation prompt per remaining asset.
UX research and design toolkit for Senior UX Designers/Researchers, including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use when conducting user research, creating personas, mapping user journeys, planning usability tests, or validating designs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
A closed-loop VISUAL self-check WORKFLOW for a local SPA (an app generated by /br, or any web app): headless screenshots of each route → BASELINE pixel diff (catching unintended changes) → machine-checkable invariants (design conformance) → an agent READS ALL images against a rubric → FINDINGS.md → fix → re-screenshot → pass only when both the machine and the eye are clean. Use when changing theme/UI/rebrand, when an MCP extension cannot capture localhost, or when you need a UI gate for a frame. Triggers: "qa thị giác", "visual qa", "route-shots", "screenshot each route", "check the interface", "baseline diff", "does the UI have regressions", "headless UI testing", "/visual-qa".
Plan what to test, how to test, and who should test for accessibility. Use when defining a testing approach, planning QA, setting up automated and manual testing, or deciding what level of accessibility testing a project needs. Triggers on: accessibility testing, how to test, test plan, automated testing, manual testing, screen reader testing, user testing, accessibility QA, what to test, testing strategy.
Runs integration tests against the Azure SQL Database container (Private Preview, local engine) in CI. Use when setting up GitHub Actions, Azure Pipelines, or GitLab CI to test against Azure SQL DB; when adding a database service container to a CI workflow; when tests need a real Azure SQL engine in the pipeline; or when you see "service container", "health-cmd", "ACR_USERNAME/ACR_PASSWORD", "MSSQL_SA_PASSWORD secret", or "integration test database". Also use when a workflow was about to pull the SQL Server image mcr.microsoft.com/mssql/server, in which case stop and use the Azure SQL Database engine image instead. Covers pulling from the private ACR with credentials, the service health check that runs sqlcmd inside the container so the runner needs no client tools, provisioning appdb before tests, and pointing the test connection string at the user database not master.
Compare a Figma node's actual specs against a code spec (the values your component renders) and get a 0–100 parity score, a list of discrepancies, and fix suggestions. Use to detect design-to-code DRIFT: triggers 'check design parity', 'does my code match the Figma', 'compare this component to the design', 'is my implementation faithful', 'find differences between design and code', 'verify the build matches Figma', 'design QA against code', 'parity score'. Reads the node's visual / typography / spacing / token / accessibility specs via use_figma (any plan) and diffs them against a codeSpec you provide. Complements the native get_design_context: instead of GENERATING code, it VALIDATES that existing code stayed in sync with the design.
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
Comprehensive codebase audit — adaptive parallel deep analysis (frontend/backend contracts, data integrity, exception handling/security, architecture/technical debt, configuration/caching), structured findings + adversarial verification + baseline comparison, producing a unified severity-ordered report and remediation roadmap. Supports a quick health check mode. Use when user asks to audit, analyze, or review an entire codebase for design issues, find hidden bugs, check architecture health, or asks '全面审查', '代码库审计', '分析设计问题', 'audit codebase', 'health check', '有哪些问题', '快速体检'. Also trigger when user asks to find silent degradation, data flow breakpoints, type mismatches between frontend and backend, or wants to understand technical debt across a project.
Validates feature implementation against PRD, Tech Spec, and Tasks through E2E testing via available MCP tools, accessibility verification, and visual analysis. Documents all bugs found with screenshot evidence and generates a comprehensive QA report. Use when the user asks to run QA, validate a feature, or test implementation completeness. Do not use for code review, bug fixing, or task implementation.
Build DSPy evaluation harnesses with rich-feedback metrics that are essential for GEPA optimization. Use when writing a metric function, calling dspy.Evaluate, splitting dev/val sets, debugging "why is my optimizer not improving?", or designing CI-ready DSPy eval suites.
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs
This skill should be used when the user asks to "validate FHIR resources", "check HL7 messages", "validate healthcare data format", "parse FHIR", "HL7 v2 messages", "FHIR R5 validation", "CDA documents", "healthcare data interchange", "FHIR resource schema", "HL7 specifications", or mentions FHIR validation, HL7 message parsing, CDA validation, healthcare data format compliance, or Fast Healthcare Interoperability Resources standards.
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.