Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Test quality validation through mutation testing, assessing test suite effectiveness by introducing code mutations and measuring kill rate. Use when evaluating test quality, identifying weak tests, or proving tests actually catch bugs.
Transform passive "Verify X" test descriptions into active, observable test actions. Use when test ideas lack specificity, use vague language, or fail quality validation. Converts to action-verb format for clearer, more testable descriptions.
Apply XP practices including pair programming, ensemble programming, continuous integration, and sustainable pace. Use when implementing agile development practices, improving team collaboration, or adopting technical excellence practices.
Design responsive layouts that maintain accessibility across screen sizes, zoom levels, and orientations. Use when designing responsive interfaces, testing zoom behaviour, or reviewing layouts across devices. Triggers on: responsive, zoom, reflow, breakpoint, mobile accessibility, screen size, orientation, viewport, 200% zoom, text scaling, layout shift, horizontal scroll.
QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation, and write every artifact to the one canonical evidence path .omo/evidence/omo-senpi-adapter/<slug>/. The live drivers under packages/omo-senpi/scripts/qa/ create their own isolated SENPI_CODING_AGENT_DIR and ignore the caller's, so the real ~/.senpi/agent is never written. Ships scripts/resolve-evidence-dir.mjs, which is the ONLY sanctioned way to pick an evidence directory: it rejects traversal, separators, absolute paths, and stray roots such as local-ignore/qa-evidence. Use whenever someone changes anything under packages/omo-senpi or packages/senpi-task, or wants to QA, smoke-test, verify, or debug the Senpi adapter, the task/team engine, the DAG, task RPC, or skill delivery. Triggers: senpi qa, qa senpi, senpi-qa, test senpi adapter, verify senpi task, senpi task e2e, senpi team e2e, task dag qa, live senpi driver, senpi evidence path.
Skill that analyzes existing TAKT workflows and facets and proposes improvements. Performs structural validation of workflow YAML, consistency checks between facets, style guide compliance verification, detection of unused facets, and rule design optimization proposals. If execution logs (.takt/logs/*.jsonl) exist, it also performs log-based diagnostic analysis, reporting rule evaluation efficiency, loop hotspots, ABORT rate, and more. Analysis is based on the style guides and engine specifications under references/takt. Triggers: 「ワークフローを分析」「taktの設定を確認」「ファセットの品質チェック」「ワークフローのレビュー」「takt analyze」「ワークフローの改善提案」「ワークフローの整合性チェック」「taktの問題を見つけて」「ログを分析」「実行ログの診断」「taktのログを見て」「ルール評価の統計」「ai_fallbackの頻度」「ループの検出」
Generate a manual test guide for human testers from code changes (diff, commit, MR/PR). Triggers when user says 「生成测试指南」「测试指南」「人工测试指南」「测试指引」「test guide」「根据代码生成测试」「从 MR 生成测试指南」「从 PR 生成测试指南」 (generate test guide / manual test guide / test guide from code / from MR / from PR), or provides a diff/MR/PR link and asks for a test guide.
Strategic guidance for choosing and implementing testing approaches across the test pyramid. Use when building comprehensive test suites that balance unit, integration, E2E, and contract testing for optimal speed and confidence. Covers multi-language patterns (TypeScript, Python, Go, Rust) and modern best practices including property-based testing, test data management, and CI/CD integration.
This skill should be used to audit an existing or legacy ADR, especially one imported, LLM-generated, stale, or never self-critiqued. PROACTIVELY activate on "review this ADR", "critique this ADR", "audit our decision log", "is this ADR any good?", "fix this old ADR", "rewrite this legacy ADR", "ADR cleanup", "ADR quality sweep", "tighten this ADR", "score these ADRs", or "this ADR is too long." Provides: line-by-line ADR critique, filler/hedging/drift detection, and per-line approval workflow.
Must be used when the user requests AI/Agent security assessment, blue-team exercises, AI security review, prompt injection testing, MCP/Skill/plugin/code package audits, Agent toolchain abuse testing, or needs to generate Markdown/HTML resembling a penetration test report. This skill turns the Agent into an AI security expert from an authorized blue-team perspective, conducting security exercises against AI products, Agents, MCP Servers, Skills, code repositories, and AI infrastructure. Prefer first-principles reasoning and real evidence over mechanically running a payload library; scripts are used only for deterministic auxiliary tasks such as HTTP fingerprinting, evidence aggregation, and report rendering.
Examples and a structure audit for the Architecture rules in AGENTS.md. Those rules are always on. Use this skill to draft a structure card or see good and bad shapes, not as the source of the rules. Triggers: folders, services, data reads, SITE_URL, auth on writes, Date.now in queries.
Clean-code engineering standards for writing, refactoring, and reviewing code in any programming language. Use this whenever the user asks to write clean code, follow clean-code principles, refactor for clarity, improve naming, reduce complexity or duplication, separate concerns, tighten error handling, work test-first or do TDD, or otherwise raise code quality, readability, and maintainability. Apply these rules by default when producing or changing code for a quality-conscious user.
Audit or configure CodeRabbit repository review policy from effective sources. Use for CodeRabbit setup, configuration review, path coverage, or a specific pull-request review audit. Trigger on "configure CodeRabbit", "review .coderabbit.yaml", "set up CodeRabbit", "audit CodeRabbit settings", or "is CodeRabbit covering X". Keep audits read-only by default and separate schema validity, rule quality, and completed-review evidence. Do not use it to run a CodeRabbit CLI review or autofix, or to fix review comments on a pull request.
Audit connection management — serverless functions opening direct Postgres connections, transaction-mode pooler misuse (PgBouncer / Supabase / prepared statements), and pool sizing against backend max_connections. Module M15. Feeds the Performance & Scale score.
Enhances milestones.yaml with detailed acceptance criteria for each milestone. Derives functional acceptance criteria, non-functional gates, testing requirements, documentation requirements, and exit checklists from business and technical requirements. Updates milestones.yaml in place with optional acceptance_criteria and exit_checklist fields.
Clean up UI/UX slop when onboarding any project — scan the existing views, take playwright screenshots (before), let hallmark read the project itself and genuinely REDESIGN it (generating its own design.md, not boxed in by the old slop tokens), then loop on fixes driven by the slop-test 58 gates + `/impeccable audit`/`critique` + `/qc-uiux` (a four-part senior verdict, deterministic `visual-qa` engine) until clean or out of loop budget. Call when the user says "clean the slop", "tidy up the project UI", "standardize the UI end to end", "onboard then clean the UI", "design prim", "/design-prim".
Use when completing work on a feature branch, preparing to merge, or cleaning up after development is done. Triggers: branch work is complete, user says "merge", "create PR", "finish branch", "done with this branch", ready for code review.
Use when given a GitHub issue URL or number to investigate and implement a fix. Triggers on "fix issue", "fix bug", "fix #123", GitHub issue URLs, or any request to resolve a reported problem from a GitHub issue. Also triggers when asked to investigate errors, diagnose failures, or debug unexpected behavior in DBHub.
Software development engine for coding. A production-grade skills system for web apps and mobile architecture, APIs, databases, web, mobile, AI, security, UX, SaaS, and ERP engineering. Encodes reusable engineering judgment through layered baseline and specialist skills to help generate secure, scalable, maintainable, high-performance software systems
Routes Meta VR and Horizon OS simulator work to the right `metavr` command group, and drives a running Meta XR Simulator via `metavr xrsim` — runtime, device, input, compositor layers and MP4 recording. Use when a goal concerns a simulated headset rather than a physical one, when choosing between `xrsim`, `ssim`, `capture` and `tapedeck`, or when a `metavr xrsim` command returns a connection error. For installing the simulator or configuring it into a Unity, Unreal or native OpenXR project, use hz-xr-simulator-install-and-configure instead.
Installs and configures the Meta XR Simulator for testing Meta VR and Horizon OS apps without a physical device. Use when installing the simulator or integrating it with Unity, Unreal, or native OpenXR projects. For controlling a running simulator, use hz-xr-simulator-control. Build paths: Unity, Unreal, and native OpenXR; route Standard Android, Meta Spatial SDK, and WebXR work through hz-quest-verify-first.
Use to assess the software architecture of a codebase, a module, or the current branch's changes against quality attributes and design principles (coupling/cohesion, layering/hexagonal adherence, separation of concerns, scalability, maintainability, testability). Produces a traceable assessment report with rated findings and prioritized recommendations. Invoke standalone to audit a system or design, or from another flow (incu-way-development at planning, incu-way-docs, incu-way-init) to evaluate a proposed or existing design before committing to it. Especially important before a large change, a refactor decision, or when tech debt and structural risk need to be made explicit.
Use when designing or auditing how an LLM or multimodal LLM is evaluated on a clinical task (report generation, VQA, text extraction). Covers reference standard, clinical-efficacy metrics beyond BLEU/ROUGE, hallucination, contamination and prompt sensitivity. Imaging models are /model-assessment.
Use when evaluating an Armory package, auditing agent or hook quality, checking package completion contracts, or reviewing the catalog across package types. Covers single-package and repository-wide audits. Not for LLM prompt optimization or ordinary PR code review.
Use when optimizing application performance, reducing load times, improving database queries, meeting performance budgets, or diagnosing bottlenecks in web applications or APIs. Triggers: slow page loads, poor Web Vitals, database timeouts, large bundle size, user-reported sluggishness, scaling preparation.
Benchmarks a trained Physical AI Studio policy in a simulation gym and reports success metrics. Use when running physicalai benchmark, editing configs under library/configs/benchmark, adding or changing a Benchmark class in physicalai.benchmark, tuning rollout/episode/env settings, recording rollout videos, or interpreting results.json / results.csv.
Exports and validates Physical AI Studio policies for Runtime deployment. Use when working on policy.export(...), the physicalai export CLI, the ONNX/OpenVINO/Torch/ExecuTorch backends, export metadata, numerical parity checks, or the Studio side of the export/load contract that Runtime consumes with InferenceModel(...).
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.