Agent Skills
Instruction packs that give your AI agent know-how — some work anywhere, some only with the tool they came with.
✦ Standalone skills2,599
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons428
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
🔌 Needs setup first94
Each relies on something you set up separately — such as an app, a command-line tool or an account — and its page names what that is.
browser-use
2,599 standalone skills
position-sizer
★ 52by wind-information-co-ltd
Calculate risk-based position sizes for long stock trades. Use when user asks about position sizing, how many shares to buy, risk per trade, Kelly criterion, ATR-based sizing, or portfolio risk allocation. Supports stop-loss distance calculation, volatility scaling, and sector concentration checks.
position_sizing_decision_skill
★ 52by wind-information-co-ltd
根据风险预算、波动特征、交易把握度与组合承受力，给出单笔交易的合理仓位大小与分批节奏建议。适用于下单前控仓、候选股比较与风险暴露管理场景。
shareholder_letter_digest_skill
★ 52by wind-information-co-ltd
总结股东信中的长期战略、经营变化、资本配置与管理层信号。适用于长期跟踪优质公司、年度复盘、更新投资主线等场景。
stock_first_look_skill
★ 52by wind-information-co-ltd
首次接触个股时，快速建立公司业务、市场关注点、关键指标、估值位置与主要风险的基础认知。适用于第一次研究一只股票、临时补课、候选标的初筛等场景。
theme_leader_identification_skill
★ 52by wind-information-co-ltd
识别热门题材中的龙头、中军、跟随股与掉队股，判断谁最值得优先跟踪，并输出题材阶段、驱动链条与风险提示。适用于题材轮动选股、热点复盘、板块主线判断等场景。
trading_halt_resume_tracker_skill
★ 52by wind-information-co-ltd
跟踪停牌、临停、复牌事件的原因、进展、潜在影响与复牌后观察框架。适用于遇到停复牌事件、判断信息性质、评估复牌后走势风险与机会等场景。
wind-alice
★ 52by wind-information-co-ltd
调用万得 Alice Agent（A2A 协议，SSE 流式）执行指定 Skill 并获取分析结果的 CLI 工具。当用户要求"用 Alice 跑某个 Skill"、"出一份某公司的调研问题清单"、"做一页纸投资备忘"、"核验一段金融信息"等需要点名 Alice 子 Skill 的场景使用。
agent-auth-mcp
★ 51by better-auth
Use the Agent Auth MCP tools to discover providers, connect agents, manage capabilities, and execute operations through the MCP protocol. Use when working inside an MCP-enabled environment (Cursor, Claude Code, etc.) and need to authenticate agents, execute capabilities, or interact with Agent Auth providers.
agent-auth-connectors
★ 51by better-auth
Reliable workflow for using Agent Auth connector capabilities (Gmail and any other provider exposed through the agent-auth tools) — discovering capabilities, connecting an agent per provider, scoping grants with constraints, executing calls, and decoding failure codes. Use whenever a request involves reading or acting on a user's connected account through agent-auth — reading/searching email, listing threads, fetching messages, deploying, or any "check my [provider]" task that routes through agent-auth search / connect_agent / execute_capability. Trigger it even when the user phrases it casually ("read my last email", "what's in my inbox", "did I get a reply").
agent-auth-cli
★ 51by better-auth
Use the Agent Auth CLI (auth-agent) to discover providers, connect agents, manage capabilities, and execute operations. Use when the user wants to interact with an Agent Auth provider from the terminal, authenticate an agent, execute capabilities, or manage agent connections.
feature-flags-php
★ 49by posthog
PostHog feature flags for PHP applications
integration-react-tanstack-router-code-based
★ 49by posthog
PostHog integration for React applications using TanStack Router with code-based routing
integration-expo
★ 49by posthog
PostHog integration for Expo applications
logs-datadog
★ 49by posthog
PostHog logs for Datadog
error-tracking-go
★ 49by posthog
PostHog error tracking for Go
error-tracking-svelte
★ 49by posthog
PostHog error tracking for Svelte
logs-go
★ 49by posthog
PostHog logs for Go
feature-flags-android
★ 49by posthog
PostHog feature flags for Android applications
integration-astro-ssr
★ 49by posthog
PostHog integration for server-rendered Astro applications with API routes
integration-astro-hybrid
★ 49by posthog
PostHog integration for Astro hybrid rendering with both static and server-rendered pages
integration-angular
★ 49by posthog
PostHog integration for Angular applications
feature-flags-nodejs
★ 49by posthog
PostHog feature flags for Node.js applications
feature-flags-nextjs
★ 49by posthog
PostHog feature flags for Next.js applications
feature-flags-java
★ 49by posthog
PostHog feature flags for Java applications
feature-flags-ios
★ 49by posthog
PostHog feature flags for iOS applications
feature-flags-elixir
★ 49by posthog
PostHog feature flags for Elixir applications
error-tracking-hono
★ 49by posthog
PostHog error tracking for Hono
feature-flags-rust
★ 49by posthog
PostHog feature flags for Rust applications
omnibus-instrument-llm-analytics
★ 49by posthog
Add PostHog LLM analytics to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. Also handles initial PostHog SDK setup if not yet installed.
logs-other
★ 49by posthog
PostHog logs for Other Languages