Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, o — from…
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, o — from…
SGLang Model Gateway (`sgl-model-gateway`, formerly `sgl-router`) — Rust router fronting vLLM/SGLang inference workers on Kubernetes.
sGLang RadixAttention — KV cache stored in a radix tree, reused across requests sharing common prefixes. Cache-aware scheduling (depth-first, LRU at branch level).
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by…
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces.
Modern CSS/SCSS architecture based on shadcn/ui design principles. Use this when generating any CSS, SCSS, or styling code to ensure modern, refined, and accessible design…
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples.
Reviews shadcn/ui components for CVA patterns, composition with asChild, accessibility states, and data-slot usage.
Testing skill for shadcn/ui and Radix UI component libraries covering accessible component testing, dialog and popover testing, form validation testing, data table testing,…
Use when creating Next.js projects with shadcn/ui, scaffolding new apps with Radix components, or setting up React apps with the Nova theme.
ใช้ skill นี้เมื่อผู้ใช้ต้องการลบ shadcn/ui ออกจากโปรเจกต์ทั้งหมดแล้วติดตั้งใหม่ตั้งแต่ต้น และอาจต้องการแยก cva() variants ออกจาก component หลังติดตั้งใหม่เสร็จ ใช้ skill…
Use when adding, using, or customizing shadcn-svelte components in a Svelte or SvelteKit project, or when you need to look up component APIs, install commands, or underlying…
Develop high-quality, accessible React components using shadcn-ui, Tailwind CSS, and Radix UI. Use when building forms, layouts, dialogs, tables, or any UI components.
shadcn/ui is a collection of accessible UI components built with Radix UI and Tailwind CSS that you copy into your project for full customization.
Apply pre-configured shadcn/ui themes with CSS variables. Use when user requests theme changes, color scheme updates, or design system modifications.
shadcn-vue Blocks — fertige Seiten-Layouts (Login, Signup, OTP, Dashboard, Sidebar, Products). Triggers: "shadcn-vue blocks", "shadcn vue blocks", "blocks overview", "shadcn vue…
Form-Komponente (shadcn-vue): Zugaengliche Formular-Abstraktion ueber vee-validate und Zod. Automatische ARIA-Attribute, eindeutige IDs, typgeprueft via toTypedSchema.
shadcn-vue Formulare mit vee-validate + Zod (toTypedSchema, useForm, VeeField, FieldArray) und mit TanStack Form (useForm aus @tanstack/vue-form, form.Field, mode="array").
shadcn-vue Setup und Installation fuer alle unterstuetzten Frameworks: Vite, Nuxt, Astro, Laravel (Inertia), manuell. Alle Schritte, Befehle und Konfigurationen vollstaendig.
Eigene shadcn-vue Registry aufbauen: registry.json anlegen, Komponente hinzufuegen, CLI-Build (npx shadcn-vue@latest build), Registry bereitstellen (public/r/*.json), per CLI…
shadcn-vue Typography: alle Text-Stil-Klassen fuer h1-h4, p, blockquote, table, list, Inline Code, Lead, Large, Small, Muted. Tailwind-Klassen und Verwendung.
Detect and triage shadow AI usage from AWS VPC Flow Logs, including model-provider egress, Bedrock-adjacent runtime evidence, RAG/vector traffic, model downloads, internal…
Verify a Shadow attestation record (Ed25519 or HMAC) without leaving Claude Desktop. Confirms request wasn't tampered, response wasn't tampered, the exact pinned model ran, and…
Design know-how for shadow-mode validation — running a candidate decision mechanism (typically an LLM judgment) in observe-only parallel with the live path, recording what it…
Size a trading position with FinPos discipline. Takes a direction from an upstream Judge (long / short / no_op), a bankroll, a volatility regime, and Kelly parameters — returns a…
Creates isolated container environments for testing local uncommitted changes before pushing. Use when testing library changes, multi-repo coordination, or validating "works on my…
Comprehensive post-build verification of Shannon Framework's application outputs using three-layer methodology: Flow Verification (execution trace analysis), Artifact Ver — from…
Use when building a whole-codebase Shape model — author higher-level architecture, boundary, and INVARIANT shapes on top of the generated AST layer, grounded in the AST anchors,…
Multi-tenant architecture design. Tenant isolation strategies, RLS, routing, and scale design for SaaS.
Use cargo-nextest when an agent needs more reliable Rust test execution than cargo test, especially for sharding, retries, machine-readable output, and CI triage.
Lets an agent split a large pytest suite into timing-balanced shards so parallel CI lanes finish faster and with less variance.
Platform-agnostic skills including skill creation templates and best practices. Use when creating new skills or improving existing ones.
Turborepo, workspaces, package architecture, @repo/* naming, exports, tree-shaking
TypeScript strict mode configs, TS 5.x+ options (verbatimModuleSyntax, module preserve, moduleDetection force, configDir), path alias sync, specialized configs
Process images with the Sharp library for Node.js — resize, convert formats, composite, apply effects, and manage metadata.
On-the-fly image optimization using Sharp (libvips Node.js bindings) with CDN-aware caching headers. Supports responsive srcset generation, AVIF/WebP transcoding, and blur…
Sharpen and maintain knives using whetstones, field stones, and improvised abrasives. Covers blade anatomy, bevel assessment, whetstone technique (coarse to fine progression),…
CellCog is built by its own Coding Agent. That same agent builds your spreadsheets. Full Python access for complex data manipulation, formulas, pivot tables, financial models,…
Use Agent Sheets as an external-agent spreadsheet runtime. Use when reading, editing, validating, debugging, versioning, or automating workbooks through the CLI/API instead of the…
ShellCheck validation as a non-negotiable 2025 workflow practice. PROACTIVELY activate for: (1) running ShellCheck on bash scripts, (2) interpreting and fixing ShellCheck warnings…
Orchestrates the full Sherpy planning workflow from requirements to QA-ready delivery plan. Supports AI, human, and hybrid audience selection for appropriate task detail levels.
Move testing activities earlier in the development lifecycle to catch defects when they're cheapest to fix. Use when implementing TDD, CI/CD, or early quality practices.
Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering. Use when implementing production observability or progressive delivery.
Guidance for using, changing, testing, and troubleshooting the ripgrep shim in this repository, including stdin-friendly search behavior and rg image/version expectations.
Use when when a Shiny application is documented or observed to run only on Windows, blocking deployment to Linux or macOS users.
Use when a task needs the judgment of a Ship Captain / Deck Officer — determining give-way/stand-on status and the required collision-avoidance action in a crossing, overtaking,…
Audit pré-publication d'un repo : secrets (historique git compris), dépendances, hygiène repo + légal, infra Supabase, et surface applicative vibecode (IDOR, RLS, rate limiting,…
Prepare and coordinate zkp2p-contracts deployment changes across source, staging activation, production activation, package export, RC publication, and stable publication.
Execute the current sprint in test-first waves.
Run the full end-to-end cadence to finish a slice of SelfOS work — quality gate, self code-review, doc sync, and a Conventional Commit.
Package, deploy, and verify a playable Three.js or web game. Use for release builds, asset delivery, private/public deployment, production smoke tests, browser proof, release…
Receive and verify ShipBob webhooks. Use when setting up ShipBob webhook handlers, debugging signature verification, or handling fulfillment events like order.shipped,…
Develop code using Shipbox sandboxes with real Cloudflare containers. Use when the user wants to run code in a sandbox, test in isolation, or deploy workers.
Receive and verify ShipHero webhooks. Use when setting up ShipHero webhook handlers, debugging signature verification (x-shiphero-hmac-sha256), or handling fulfillment events like…
Add a single SwiftUI UI component from ShipSwift recipes (animation, chart, alert, loading, input, etc.).
Build a complete iOS feature by composing multiple ShipSwift recipes (auth, camera, chat, paywall, settings, dashboards, etc.).
Explore and browse the ShipSwift recipe catalog (animations, charts, components, modules). Use when the user says explore/browse/show recipes, "what ShipSwift components are…
Use when writing tests, structuring test suites, choosing test boundaries, or debugging test quality issues like flakiness, over-mocking, or brittle tests.
Use inside a Shoal workspace to finish assignments with `shoal done`, mark work ready for review, notify the user, ask the user questions, open, change, watch and wait on PRs and…