全部能力

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation. (gstack) Voice triggers (speech-to-text aliases): "tech review", "technical review", "plan engineering review".

Route runtime-log requests into one evidence packet before diagnosing anything. Use when the user shares app/server/container/browser/CI/JSON log output and wants the first actionable blocker, repeated signature, likely blast radius, or safest next read-only checks. Choose one packet: app-runtime, container-runtime, browser-plus-api, ci-cascade, structured-json, or security-signal. Triggers on: check the logs, which line matters, real error, first blocker, noisy stack trace, retry storm, browser 401/500, pod logs, worker crash, CI abort, webhook failure. Route engine-specific Unity/Unreal logs to `game-build-log-triage`, observability design to `monitoring-observability`, and remediation/debug hypotheses to `debugging`.

Comprehensive Drupal patterns from "Drupal at Your Fingertips" by Selwyn Polit. Covers 50+ topics including services, hooks, forms, entities, caching, testing,…

Expert in building blazing-fast reactive dashboards with comprehensive testing. Masters React performance patterns, testing strategies for async components,…

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting…

Internationalization best practices for React Router framework mode using remix-i18next. Use when setting up locales, middleware, resource routes, or language…

Bun implementation guide for PMA-managed backend services. Defaults to a single-API-project layout; promotes to a Bun monorepo only when multiple deployable…

Expert-level code review focusing on quality, security, performance, and maintainability. Use this skill for conducting thorough code reviews, identifying…

This skill provides comprehensive knowledge for building static websites with Hugo static site generator. It should be used when setting up Hugo projects (blogs, documentation sites, landing pages, portfolios), integrating Tailwind CSS v4 for custom styling, integrating headless CMS systems (Sveltia CMS or TinaCMS), deploying to Cloudflare Workers with Static Assets, configuring themes and templates, and preventing common Hugo setup errors. Use this skill when encountering these scenarios: scaffolding new Hugo sites, choosing between Hugo Extended and Standard editions, integrating Tailwind CSS v4 with Hugo Pipes, configuring hugo.yaml or hugo.toml files, integrating PaperMod or other themes via Git submodules, setting up Sveltia CMS or TinaCMS for content management, deploying to Cloudflare Workers or Pages, troubleshooting baseURL configuration, resolving theme installation errors, fixing frontmatter format issues (YAML vs TOML), preventing date-related build failures, setting up PostCSS with Hugo, or setting up CI/CD with GitHub Actions. Keywords: hugo, hugo-extended, static-site-generator, ssg, go-templates, papermod, goldmark, markdown, blog, documentation, docs-site, landing-page, sveltia-cms, tina-cms, headless-cms, cloudflare-workers, workers-static-assets, wrangler, hugo-server, hugo-build, frontmatter, yaml-frontmatter, toml-config, hugo-themes, hugo-modules, multilingual, i18n, github-actions, version-mismatch, baseurl-error, theme-not-found, tailwind, tailwind-v4, tailwind-css, hugo-pipes, postcss, css-framework, utility-css, hugo-tailwind, tailwind-integration, hugo-assets

Comprehensive infrastructure engineering covering DevOps, cloud platforms, FinOps, and DevSecOps. Platforms: AWS (EC2, Lambda, S3, ECS, EKS, RDS,…

Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions, model-graded rubrics, transforms, datasets, exports, and CI gates. Use for non-redteam eval coverage, regression tests, or new eval matrices. Do not use for adversarial redteam plugin or strategy setup.

Production MLOps covering CI/CD, serving, drift monitoring, and GenAI security. Use when deploying or operating ML and LLM systems in production.

Provide systematic methodologies for leveraging Shodan as a reconnaissance tool during penetration testing engagements.

Hooks for managing, caching and syncing asynchronous and remote data in Vue. ALWAYS use when writing code importing \"@tanstack/vue-query\". Consult for…

Build, validate, and publish Obsidian plugins following official community submission standards. Use when developing an Obsidian plugin from scratch, reviewing existing plugin code, fixing ESLint violations from eslint-plugin-obsidianmd, preparing a plugin for community directory submission, or applying Obsidian-specific best practices (memory management, type safety, accessibility, CSS variables, vault API). Triggers on: obsidian plugin, obsidian development, obsidian-plugin, create obsidian plugin, obsidian eslint, obsidian submission, obsidian community plugin, obsidian API, plugin boilerplate, obsidian typescript, obsidian vault, obsidian settings, obsidian commands.

Build React animations with Motion (formerly Framer Motion) - gestures (drag, hover, tap), scroll effects, spring physics, layout animations, SVG, exit animations, and motion values. Use when: building React animations, adding hover/tap/drag interactions, scroll-triggered effects, layout transitions, shared element animations, exit animations with AnimatePresence, or working with motion values and springs. Triggers: "animate", "motion component", "framer motion", "gesture", "drag", "scroll animation", "layout animation", "exit animation", "spring", "whileHover", "whileTap", "whileInView", "AnimatePresence", "layoutId", "useScroll", "useSpring", "useAnimate", "motion value", "reorder", "parallax".

Reviews REST API designs for quality, consistency, and breaking changes. Lints OpenAPI specs, generates API scorecards, and detects breaking changes between versions. Use when designing APIs, reviewing API contracts, or managing API versioning.

Route performance work from the artifact people already have into one measurement-led tuning brief. Use when the main job is locating the tightest latency, throughput, memory, bundle-size, or frame-budget bottleneck; choosing the right trace, query plan, load-test result, profiler capture, or CWV report; naming one bottleneck; and recommending one or two bounded optimizations with before/after verification. Route telemetry rollout to monitoring-observability, correctness diagnosis to debugging, structural cleanup to code-refactoring, validation-policy design to testing-strategies, and engine-specific capture interpretation to game-performance-profiler.

Fuzzing skill for automated input-driven bug finding in C/C++. Use when setting up libFuzzer or AFL++ fuzz targets, defining fuzz entry points around parsing…

OpenAI integration. Manage Assistants, Files. Use when the user wants to interact with OpenAI data.