Quality Assurance Bundle

Skills that help ensure software quality through testing, debugging, and analysis.

Browse all skill bundles

Included Skills (85)

Nemo Mbridge Resiliency — Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.
Workflow Blueprint Generator — This tool generates comprehensive technical documentation and implementation blueprints for software developers by analyzing project architecture, technology stacks, and complex data flow patterns.
MSTest Testing Assistant — This tool helps C# developers write effective unit tests using modern MSTest 3.x/4.x best practices, standard naming conventions, and efficient test lifecycle management.
Understand Explain — Explains one file, function, class, table or folder of a codebase in depth, starting from the knowledge graph built by the Understand-Anything plugin and confirming every statement in the source. Use when someone says "explain this file", "how does this function work", "walk me through the scheduler module", "what is this class for and who uses it", "run /understand-explain src/services/scheduler.ts", "I inherited this code, what does it do", or needs a written deep dive on a specific part of a project.
Doca Debug — Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca_* symbol, a runtime call returning DOCA_ERROR_*, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime → program → driver), verbosity controls (--sdk-log-level, DOCA_LOG_LEVEL, the doca-{lib}-trace flavor), container-debug constraints, or how to capture state for a Developer Forum post. Trigger even when the user does not say "DOCA debug" — implicit phrasings include "undefined reference to doca_*", "how do I get more logs", "packets aren't reaching the wire", "doca_caps returned nothing", or "hugepages empty in the container". Refuse and route elsewhere for library-specific debug (Flow pipe trace, RDMA QP, Comch stats), env-class pkg-config or hugepages symptoms, the DOCA_ERROR_* taxonomy and lifecycle interpretation, and performance or incident-response work — those belong to other skills.
Azure Troubleshooter — Helps engineers diagnose and resolve production issues across Azure services using authoritative debugging guidance.
Analyzing Ios App Security With Objection — Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
AI Governance Engine — This engine provides safety gates, evidence-based debugging, and ripple awareness to help AI agents deliver verified, disciplined, and reliable code modifications for developers.
API Integration Architect — Designs, implements, and debugs robust API integrations for developers and engineers.
SIEM Alert Optimizer — This tool helps SOC analysts reduce alert fatigue by systematically tuning SIEM detection rules, refining correlation logic, and implementing effective allowlisting strategies.
JUnit Test Generator — This skill generates production-grade JUnit 5 unit and integration tests for Java developers, including support for mocking, parameterized testing, and lifecycle management.
Playwright Java — Enterprise-grade Playwright E2E test automation in Java with POM, JUnit 5, Allure, and parallel execution.
Performing Mobile App Certificate Pinning Bypass — Bypasses SSL/TLS certificate pinning implementations in Android and
Spec Kit — Spec Kit is GitHub's open-source toolkit that installs a set of agent commands into a project so a coding agent builds features from a written specification: specify, plan, tasks, implement, then converge against the spec. It also ships optional processes for bug fixing and for assessing an idea. Use when someone asks to "set up Spec Kit", "run specify init", "use spec-driven development on this repo", "write the spec before the code", "run /speckit-specify or /speckit-plan", "fix this bug with a recorded diagnosis", or "assess whether this idea is worth building". Covers installation, per-agent command syntax, the artifact layout, extensions, and upgrades.
Detecting Malicious Npm Packages — Triage npm packages and lockfiles for install-script malware, credential exfiltration, and worming behavior using GuardDog, manual tarball inspection, and dynamic detonation with network/filesystem monitoring. Use when vetting a new dependency, reviewing a package.json/package-lock.json during code review, checking lockfiles against a supply-chain advisory's known-bad versions, or investigating a host suspected of installing a trojanized package.
Orca Replay — Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce a failure.
YARA Rule Developer — This tool assists cybersecurity analysts in crafting precise YARA and YARA-X signatures to effectively detect, classify, and hunt for malicious software artifacts.
Test Driven Development — This skill guides developers through the red-green-refactor cycle to ensure robust feature implementation and reliable bug fixes via automated testing.
Detecting Dependency Confusion — Detect and prevent dependency confusion (public-over-private package name resolution) in npm, PyPI, and Maven by enumerating claimable internal package names with tools like `confused` and OWASP `dep-scan`, then enforcing source restrictions via `.npmrc`, `pip.conf`/`pyproject.toml`, and Maven `settings.xml`. Use when onboarding a repo to a supply-chain security program, auditing lockfiles/manifests for confusable dependencies, or after an incident that may have leaked internal package names.
Exploiting Race Condition Vulnerabilities — Detects and exploits race condition (TOCTOU) vulnerabilities in web
Makepad Layout Guide — Provides guidance on Makepad's unique layout turtle system for building and debugging UI code.
APK Reverse Engineer — Aids security professionals in analyzing and modifying Android applications through reverse engineering techniques.
Debugging And Error Recovery — Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
Gdb CLI — GDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation
Durable Objects — Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
Agent Signal Emitter — This tool enables AI agents to communicate status updates and coordination signals to operators, ensuring transparency and efficient workflow management throughout the project.
Idea Refine — Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".
Design Facilitation Framework — This skill helps developers and architects transform raw concepts into validated, structured specifications through disciplined questioning before beginning any actual code implementation.
Bug Hunt Swarm — Finds the cause of a hard bug by running several read-only subagents in parallel, each attacking it from a different angle (change history, code path, data and state, environment, reproduction), then checking their evidence, ranking the hypotheses and naming the one experiment that would confirm the leader. It diagnoses and does not fix. Use when someone says "hunt this bug with multiple agents", "swarm on this regression", "investigate in parallel", "find the root cause", or when a failure is intermittent, crosses components, or has resisted a first look.
Orca Replay — Answer questions about an earlier agent run from its recording rather than from memory, and replay or fork that run. Use when the user asks why a previous run did something, which step changed a file or broke the build, whether yesterday's failure still reproduces, or whether a different model would have got it right.
Web Data Auditor — This tool audits live web pages to verify data integrity by identifying mock values, hardcoded strings, and broken endpoints for developers building AI-generated applications.
Agentic Verify — Check that a Python change is caught by tests: run every mutant of the changed lines and write tests until they catch them. Reports evidence instead of a diff to read.
Atlas Contract — Goal-integrity skill. Use for backend/API/persistence, preserve/do-not-change, tests/validation, mocks, rework, multi-part requests. Emits Goal Contracts, Deviation Notices, Phase Checks, Final Audits. Skip for Q&A or trivial edits.
Typosquatting Detection Tool — This tool helps security analysts identify malicious typosquatting attacks in npm and PyPI registries by analyzing package metadata, naming similarities, and usage anomalies.
Prompt Engineering Expert — This guide provides advanced prompt engineering patterns and optimization techniques to help developers improve LLM performance, reliability, and output quality for complex tasks.
Systematic Debugging Framework — This four-phase methodology helps developers identify root causes before applying fixes, ensuring reliable resolutions for bugs and complex test failures.
API Test Suite Builder — Use when the user asks to generate API tests, create integration test suites, test REST endpoints, or build contract tests.
Temporal Workflow Orchestrator — Orchestrates microservices and builds reliable distributed workflows, aiding developers in implementing saga patterns and fault-tolerant systems.
Pester Migration Assistant — This tool automates the complex process of upgrading PowerShell Pester test suites across major versions to ensure compatibility and modernize legacy testing syntax.
Agenttrace Session Audit — Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
Web Fuzzing Tool — Discover hidden web content, API endpoints, and subdomains using ffuf, a fast and versatile web fuzzer.
UI Development Workflow — A step-by-step process for building, polishing, and reviewing UIs to ensure high-quality results.
BrowserStack Test Runner — Automate cross-browser and cross-device Playwright testing on BrowserStack to help developers ensure application compatibility across various platforms and environments.
API Contract Validator — Helps developers design and review API contract tests to prevent compatibility issues between providers and consumers.
Memory Status — Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the user runs /si:memory-status or asks how full or healthy the agent memory is.
Systematic Debugging — Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Sanity Migration Specialist — This skill assists developers in planning, executing, and validating structured content migrations from various legacy CMS platforms into the Sanity ecosystem.
Playwright Test Fixer — This skill diagnoses and fixes failing or flaky Playwright tests, helping developers ensure reliable end-to-end testing.
Branch Completion Assistant — This tool automates the finalization of development branches by verifying test suites and providing structured integration options for software developers.
TUnit Testing Assistant — Provides developers with best practices and structured guidance for implementing efficient, data-driven unit tests using the TUnit framework in .NET projects.
Sanity Form Component Suspense — Fix a Sanity Studio custom form component (components.input, components.field, components.item, or a plugin's form.components) that suspends without its own Suspense boundary, so it loads without layout shift and never blocks new documents. Use when the console warns "The custom input/field/item component ... suspended without a <Suspense> boundary of its own" or "A form component ... suspended without a <Suspense> boundary of its own", when a custom form component uses React.lazy, use(), App SDK hooks (useDocumentProjection, useQuery, useDocument) or another suspending data library, or when a field or array item shows a skeleton that never goes away on new documents.
Strategic Reflection Framework — This tool helps developers critically evaluate project direction, identify faulty assumptions, and realign ongoing tasks with the user's original goals and objectives.
Issue Breakdown Assistant — This tool helps developers decompose complex project plans or specifications into actionable, independently-grabbable issues using vertical tracer-bullet slices for efficient task management.
Durable Workflow Orchestrator — This skill provides durable execution patterns and platform guidance to help developers build reliable, fault-tolerant automation for production-grade AI agent workflows.
Design Orchestration — Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order.
Test Framework Converter — Automates the migration of test scripts between Selenium, Playwright, Puppeteer, and Cypress to help QA engineers modernize their automation infrastructure efficiently.
GitHub Workflow Automator — This tool enables developers to programmatically manage GitHub repositories, issues, and pull requests while strictly adhering to established repository policies and security safeguards.
Closed Loop Delivery — Use when a coding task must be completed against explicit acceptance criteria with minimal user re-intervention across implementation, review feedback, deployment, and runtime verification.
ClickHouse Node Troubleshooting — This skill assists developers in diagnosing and resolving common configuration, connection, and data handling errors within the ClickHouse Node.js client environment.
Chrome Automation — Automate Chrome with OpenCLI to inspect pages, interact with sites, and manage browser sessions.
Test Coverage Analyzer — Analyzes code to identify test coverage gaps, helping developers ensure comprehensive testing and reduce potential bugs.
AKS Network Capture — Collects bounded packet captures from AKS nodes for wire-level evidence during troubleshooting.
Awt E2e Testing — AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g
NUnit Testing Assistant — Provides developers with best practices for structuring, organizing, and implementing effective standard and data-driven unit tests using the NUnit framework.
XUnit Testing Expert — This skill provides C# developers with best practices for implementing robust unit tests and efficient data-driven testing using the XUnit framework.
API Mocking Expert — This expert creates realistic mock services to help developers and testers simulate API behavior, enabling parallel development and efficient testing workflows.
Code Execution Tracer — This tool generates detailed, step-by-step execution traces to help developers understand complex code behavior and resolve logic-based confusion during debugging.
Verification Workflow Enforcer — This skill mandates that AI agents execute and validate verification commands before asserting that any coding tasks, bug fixes, or tests are complete.
Cypress Testing Assistant — This skill helps developers write and maintain end-to-end tests for web applications using the Cypress testing framework.
Structured Debugging Protocol — Enforces a rigorous five-phase debugging workflow that prevents premature code edits, helping developers and AI agents identify root causes before applying fixes.
Top Web Vulnerabilities — Provide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic vulnerability identification, impact assessment, and remediation guidance across the full spectrum of web security threats.
Find Bugs — Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
Sanity Content Assistant — Helps developers build content platforms using Sanity's structured content, GROQ queries, and real-time collaboration features.
storybook — The skill lets developers build, document, and test UI components in isolation with Storybook, automatically generating stories, configuring addons, and running visual regression tests. Designers and QA teams benefit from clear, versioned component documentation and reliable visual validation, reducing errors and accelerating delivery. This streamlines collaboration and improves workflow efficiency.
Root Cause Debugger — Debugging specialist for developers to analyze and fix errors, test failures, and unexpected behavior.
Local LLM Specialist — This skill assists developers in deploying, optimizing, and running open-weight large language models locally while ensuring hardware efficiency and data privacy.
E2E Testing Architect — This skill assists developers in building reliable, maintainable end-to-end test suites to ensure critical user workflows remain stable and regression-free during rapid deployment.
Debian System Troubleshooter — This tool helps system administrators diagnose and resolve Debian Linux issues by providing structured triage steps, remediation commands, and verification procedures.
Fedora System Troubleshooter — This tool assists Fedora Linux users by providing systematic diagnostic steps, remediation commands, and verification procedures for resolving complex system-level issues.
JavaScript Concept Guide — This skill provides developers with comprehensive explanations and best practices for thirty-three essential JavaScript concepts to improve coding proficiency and debugging.
Resilient Error Architect — This skill assists developers in implementing robust error handling strategies and fault-tolerant patterns to improve application reliability and debugging efficiency.
JavaScript Testing Architect — This skill provides developers with comprehensive strategies and best practices for implementing robust unit, integration, and end-to-end testing in JavaScript applications.
Rust Async Architect — This skill assists developers in building, optimizing, and debugging robust concurrent systems using the Tokio runtime and advanced asynchronous Rust programming patterns.
Python Testing Expert — This skill provides developers with robust strategies for implementing pytest suites, mocking dependencies, and applying test-driven development practices to ensure high-quality Python code.
Grilling — Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.