llm-serving-auto-benchmark
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving framework. Use when a user wants to…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-21 00:15
258,650 results
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving framework. Use when a user wants to…
Update an existing AI agent on a live LiteLLM proxy. Ask for the agent_id and what to change (model, description, MCP servers), then call PATCH…
Update an existing team on a live LiteLLM proxy. Ask for the team_id and what to change (budget, models, limits), then call POST /team/update.
Manage ScriptableObject assets
Use when the user wants to build a CLI tool to automate browser interactions on a specific website using kimi-webbridge. Invoke when user says "create a CLI…
Core React 19 patterns including hooks, Suspense, lazy loading, component structure, TypeScript best practices, and performance optimization. Use when working…
Framework-agnostic HTTP API route testing patterns, authentication strategies, and integration testing best practices. Supports REST APIs with JWT cookie…
Build a modern, collapsible sidebar for SaaS dashboards following the ChatGPT/Notion design pattern
Use when setting up Git hooks for a polyglot or monorepo project with Lefthook — wiring fast format/lint checks on staged files at pre-commit and slower…
Meta-framework for how a company runs -- the connective tissue between C-suite roles (EOS, Scaling Up, OKR-native). Use when setting up company operations,…
Create and maintain the foundational context doc (positioning, ICP, competitive landscape, brand voice, customer language) that other marketing skills read…
Create source-adjacent HTML visualizations for /visualize requests, docs, markdown, standardized plans, process flows, charts, Mermaid diagrams, context maps,…
Applies Tailwind CSS v4 setup and styling strategy. Use when configuring Tailwind v4, writing component styles, deciding between utility classes and custom…
P1 phase skill for Headless Ghidra baseline and runtime evidence. Use after P0 when the target must be imported into Ghidra, auto-analyzed, exported to…
Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from…
Query database safely with parameterized statements
Design, audit, and evolve physical source and package structures that expose real architectural boundaries while keeping related behavior together. Use when creating or reviewing repository trees, deciding where files or packages belong, reducing flat folders, organizing by feature, route, screen, use case, bounded context, workflow or endpoint, structuring frontend state/data/UI ownership and design systems, making hexagonal inside/outside boundaries visible, locating ports, adapters and composition roots, structuring BFF routes, planning folder migrations, or enforcing package and import direction. For one module's logical responsibility, deepening, splitting, or caller contract use codebase-design; for repository-wide architecture investment discovery use improve-codebase-architecture. A physical flattening alone is not a reduce-system-complexity result.
Handle Salesforce data operations including data migration, sandbox seeding, bulk data loading, data export, and data cleanup. Use when asked about…
Personalized Binance.US market, portfolio, and watchlist briefings using account balances, recent trading history, watchlists, market data, recent news…
Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately.…
CodeStable usage feedback loop. Use only when the user explicitly requests recording or reporting that a cs skill went off track, a tool failed, rules are unclear, or the agent was corrected; collect local evidence and prepare a confirmable public issue.
Audit whether "code that still has consumers" really needs to continue to exist, focusing on wrappers/facades, compatibility layers, stale public APIs, defensive branches, fallbacks, default values, configuration, duplicate sources, and hypothetical extension points. Use for code that is already used but whose necessity is insufficient, legacy compatibility cleanup, meaningless wrappers, defensive code removal, cleanup with no compatibility requirements, in-depth necessity checks, and "is this still needed?"-type requests; do not use it as...
Python development guidance with code quality standards, error handling, testing practices, and environment management. Use when writing, reviewing, or…
Set up the Datadog Azure integration with Terraform - creates an Entra ID app registration and service principal, assigns Monitoring Reader across the chosen…