AGENT SKILLS · 任务装备
值得安装的 Agent Skills
汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。
- 目录范围
- 已验证
- Skills
- 23,248
- 仓库
- 3589
- 最近同步
- 2026年11月4日
TerminalSkillsleptos
Leptos is a Rust web framework that builds reactive user interfaces compiled to WebAssembly, either as a client-side app or as a full-stack app with server-side rendering, hydration and server functions on Axum or Actix. Use when a user asks to "build a web app in Rust", "start a Leptos project", "add a server function", "use signals and resources in Leptos", "set up cargo-leptos", "fix Leptos code that no longer compiles after 0.7", or "deploy a Leptos SSR app". Covers Leptos 0.8: signals, the
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsletsencrypt
Let's Encrypt is a free, automated certificate authority, and Certbot is its official ACME client for getting and renewing TLS certificates. Use this skill when asked to add HTTPS to a website, get a free SSL certificate, issue a wildcard certificate, set up automatic renewal, fix a Certbot renewal failure, or get certificates automatically in Docker with Traefik.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslibrechat
LibreChat is a self-hosted, ChatGPT-style web chat that puts OpenAI, Anthropic, Google, OpenRouter, Ollama and other providers behind one login, with agents, MCP tools, file search and per-user spending budgets. Use when deploying LibreChat with Docker Compose, editing librechat.yaml or .env, adding a custom endpoint, connecting MCP servers, closing registration or adding SSO, creating users, or updating an instance. Trigger phrases: "set up LibreChat", "self-hosted ChatGPT for the team", "add C
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslibsql
Connects JavaScript and TypeScript apps to libSQL, the open-source SQLite fork behind Turso, with the @libsql/client SDK: local files, in-memory databases, remote Turso databases over libsql:// or HTTP, and embedded replicas that sync from the cloud. Use when a user asks for SQLite with remote sync, an edge-friendly SQL database, a Turso setup, or batches, transactions and parameterized queries with libSQL.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsliepin-jobs
Connects an AI coding agent to Liepin's (猎聘) official MCP server so it can search jobs, read and edit the user's resume, and submit applications after explicit approval. Covers adding the server to Claude Code, Codex, Gemini CLI and Cursor with tokens kept in environment variables. Use when the user says "find jobs on Liepin", "搜职位", "猎聘", "改简历", "投简历", "求职", or wants a resume reviewed against live Chinese job listings.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslighthouse-ci
Lighthouse CI (lhci) runs Google Lighthouse audits on every pull request, checks the scores and metrics against assertions or performance budgets, and uploads the reports. Use when a user asks to track Core Web Vitals in CI, stop performance regressions, audit accessibility on each PR, or set a performance budget for a web app.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslinear
Manage projects and issues with Linear. Use when a user asks to set up Linear workspaces, create issues and projects, automate workflows, build Linear integrations, sync issues with GitHub, manage sprints and cycles, set up triage processes, build custom views, use Linear's GraphQL API, create webhooks, automate issue transitions, or build tools on top of Linear. Covers workspace configuration, team workflows, API automation, and integration patterns.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslinkedin-marketing
Create, optimize, and automate LinkedIn content for personal branding, lead generation, and B2B marketing. Use when someone asks to "write a LinkedIn post", "grow on LinkedIn", "LinkedIn content strategy", "LinkedIn API integration", "automate LinkedIn posting", "LinkedIn carousel", "LinkedIn analytics", or "LinkedIn outreach". Covers post formatting, the LinkedIn Posts API with image and document uploads, company page posting, analytics access, and growth strategy.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslinkerd
Linkerd is a lightweight service mesh for Kubernetes that adds automatic mTLS, retries, timeouts, traffic splitting, authorization policy and golden-metric observability without changing application code. Use when installing Linkerd, meshing a namespace, running a canary rollout, restricting which services can call each other, or linking clusters.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslitellm
LiteLLM is a Python SDK and self-hosted proxy that calls 100+ LLM providers (OpenAI, Anthropic, Google Gemini, Mistral, Bedrock, Ollama and more) through one OpenAI-compatible interface. Use when someone asks to "switch between LLM providers", "LiteLLM", "unified LLM API", "LLM proxy", "call Claude and GPT with the same code", "LLM load balancing", "fallbacks between models", or "multi-model AI gateway". Covers SDK calls, Router, fallbacks, virtual keys, budgets and spend tracking.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsliveblocks
Liveblocks is a hosted platform for adding real-time collaboration to web apps: live cursors, presence, shared storage, comments, notifications and collaborative text editors. Use this skill when a user wants multiplayer features in a React or Next.js app, asks how to use Liveblocks hooks (useOthers, useStorage, useMutation, useThreads), set up the LiveblocksProvider and RoomProvider, or write the server auth endpoint with @liveblocks/node.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslivekit
Build real-time audio and video applications with LiveKit. Use when a user asks to implement WebRTC rooms, video conferencing, live streaming, screen sharing, or real-time communication using the LiveKit SDK.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsllama-cpp
llama.cpp runs large language and vision models locally from GGUF files on CPUs, Apple Silicon and GPUs, and serves them over an OpenAI-compatible HTTP API. Use when a user asks to run a model locally with llama.cpp, start llama-server or "llama serve", download a GGUF model from Hugging Face, host a local OpenAI-compatible endpoint, offload layers to the GPU, get embeddings or schema-constrained JSON from a local model, quantize a model to Q4KM, or benchmark tokens per second.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsllamafile
llamafile packages a large language model and the llama.cpp runtime into one executable that runs on Linux, macOS, Windows and BSD without installation. Use when running an LLM offline from a single file, serving a local OpenAI- or Anthropic-compatible API, scripting one-shot prompts with --cli, bundling a GGUF model with zipalign, or distributing a portable AI app.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsllamaindex
LlamaIndex is an open-source Python framework for connecting LLMs to your own data: it loads and chunks documents, indexes them in a vector store, and answers questions over them with retrieval (RAG) and tool-calling agents. Use when ingesting documents, configuring retrieval strategies, building query engines, creating multi-step agents, or evaluating answer quality. Trigger words: llamaindex, llama-index, rag, retrieval augmented generation, vector index, query engine, document loader, knowled
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsllm-cost-optimizer
Cuts LLM API spend by measuring cost per feature and user, routing easy requests to cheaper models, using provider prompt caching, adding a semantic response cache, and using the batch APIs. Use when someone asks to "reduce AI costs", "track LLM spending", "my OpenAI or Anthropic bill is too high", "set up model routing", "cache LLM responses", "compare model costs", or "set budget alerts for AI".
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslm-studio-subagents
Offload tasks to local LLMs via LM Studio. Use when a user asks to run local models with LM Studio, save API costs by using local LLMs, create subagents with local models, offload summarization or classification to a local model, or use LM Studio's API for batch processing. Covers local model inference, task delegation, and cost optimization.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsload-balancer
Configures load balancers and reverse proxies with Nginx and HAProxy: upstream pools, least-connections balancing, HTTPS termination, health checks, rate limiting, sticky sessions and WebSocket proxying. Use when someone asks to "set up load balancing", "configure an Nginx reverse proxy", "set up HAProxy", "add SSL termination", "configure health checks", "proxy WebSocket connections", "rate limit traffic", or "set up failover".
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslocalai
Expert guidance for LocalAI, the open-source drop-in replacement for OpenAI's API that runs locally. Helps developers self-host LLMs, image generators, audio transcription, and text-to-speech models with an OpenAI-compatible API — no GPU required, completely offline and private.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslocust
Load-test web services with Locust, an open-source Python framework where user behavior is written as plain Python code and run from a real-time web UI or headless in CI. Use when the user mentions "locust", "locustfile", "Python load testing", "distributed load test", "locust web UI", or wants to simulate thousands of concurrent users against an API. For JavaScript-based load testing, see k6 or artillery.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslog-analyzer
Analyzes application logs, server logs, and error traces to identify root causes, patterns, and anomalies. Use when debugging production incidents, investigating error spikes, parsing crash reports, or correlating events across multiple log sources. Trigger words: logs, errors, stack trace, crash, exception, debug, incident, 500 errors, timeout, latency spike.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillslogstash
Configure Logstash for log ingestion, parsing, transformation, and output to Elasticsearch and other destinations. Use when a user needs to build log processing pipelines, write Grok patterns, parse unstructured logs, enrich events, or set up multi-pipeline Logstash deployments.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsloki
Loki is a horizontally scalable log aggregation system built by Grafana Labs. Unlike traditional log platforms that index the full text of every log line, Loki indexes only metadata labels, making it significantly cheaper to operate. Use when someone asks to "set up Loki", "ship Docker logs to Loki", "write a LogQL query", "replace Promtail with Alloy", or "show logs in Grafana".
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日
TerminalSkillsloops
Send marketing and transactional emails with Loops. Use when a user asks to set up email marketing for a SaaS, create drip campaigns, send product update emails, or use a modern alternative to Mailchimp for startups.
- 安装量
- —
- GitHub Stars
- 192
- 最近更新
- 11月4日