发现 AI Agent Skills

Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to create visuals that include specified text and layout requirements with AI Hive through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include text in image, typography generation, text-accurate poster, layout control.

Robly integration. Manage Organizations, Users. Use when the user wants to interact with Robly data.

Set up hot-reloading for chrome extensions. Provides a zero-dependency solution for automatic extension refreshing during development.

长文/测评文章 → 知识视觉笔记套图（3-5张）。自动提炼核心逻辑、规划分镜、生成高阶图像Prompt（4模块结构）。支持手写笔记/思维导图/架构图/对比矩阵四种风格。Use when: 文章转知识笔记、知识笔记图片、思维导图、视觉笔记、长文转图、知识卡片、文章可视化、article to infographic、knowledge note。Output: 中文摘要 + 纯英文生图Prompt。Pair with vectronode-image/relay-image-gen to generate final images.

Finds and finishes the last 20% of a built solution — the experiential layer agents skip: what the output actually reads like, which pages or screens should exist, first-run and empty states, opinionated defaults, the golden path. Use when planning any build so the magic gets specced as concretely as the plumbing, before calling any build "done", when a solution works but feels like a demo, or when the user says "last 20%", "finish this", "make it actually good", "is this actually done", or "why does this feel flat".

UI/UX best practices for web interfaces. Use when reviewing animations, CSS, audio, typography, UX patterns, prefetching, or icon implementations. Covers 11 categories from animation principles to typography. Outputs file:line findings.

Shopee（虾皮）SBS 仓储服务（与 linkfox-shopee-store-auth 同系列），经 /shopee/developerProxy 转发 Shopee Open API SBS 模块全部 5 个接口：get_bound_whs_info、get_current_inventory、get_expiry_report、get_stock_aging、get_stock_movement。当用户提到 Shopee SBS、仓储库存、绑定仓库、get_bound_whs_info、库龄报表、效期报表、库存变动 时触发。即使未明确提及"SBS"，只要涉及已授权 Shopee 店铺的 SBS 仓储与库存数据查询，也应触发。

Universal code quality principles applicable to all languages. Covers Clean Code, SOLID, complexity metrics, and quality standards. USE WHEN: user mentions "clean code", "SOLID", "code smells", "refactoring", "complexity", asks about "cyclomatic complexity", "cognitive complexity", "code review", "maintainability" DO NOT USE FOR: language-specific linting - use ESLint/Biome skills, security - use OWASP skills, testing - use testing skills

Perform digital forensics during incident response — evidence preservation, volatile data collection, artifact analysis, and timeline construction. Use when investigating a suspected compromise.

Transfer, pin, lock, or open a dev branch from a GitHub issue. Use when moving an issue between repos, pinning or locking it, or bulk-editing custom fields.

Orchestrate multiple Claude Code workers via iTerm2 using the claude-team MCP server. Spawn workers with git worktrees, assign beads issues, monitor progress, and coordinate parallel development work.

Help a user choose a Senpi trading strategy to deploy — a conversational, analyst-style picker. Use when the user asks "what should I trade?", "recommend a strategy", "help me pick a strategy", "what's winning?", "set me up", "I have a view on the world (a war, the economy, one coin winning) — trade it", "run a hedge fund / all-weather / tail-risk book", or wants a strategy but has NOT named a specific one — and every discretionary mandate: "deploy whatever you think is profitable", "trade for me", "be aggressive", "put it to work", "you decide". A mandate is a strategy request even when it names no strategy and no coin; it is never answered with hand-picked raw positions. Surface the closest matching TEMPLATE first — the quick start to the user's OWN strategy (every template deploys as `<User>'s <Template>` — or a name of their own — as-is or with levers moved, after ops walks them through it) — passing their worldview as `--theme` to rank the closest fits; offer building one as a peer with its cost class, never a downsell. You talk and RANK; a hidden engine (scripts/discover.py) fetches data + filters. NOT for installing a NAMED strategy (that's senpi-strategy-ops), or building/designing one from scratch or with a custom DSL (that's senpi-strategy-author).

百度热榜监控 | Baidu Hot Topics Monitor. 获取百度热搜榜、搜索趋势、关键词热度 | Get Baidu trending searches, trends, keyword popularity. 触发词：百度、热搜、baidu.

Build LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval, agent chain.

Build cost assemblies from CWICR work items. Combine multiple items into reusable templates for common construction elements.

Use when the user asks to "create an influencer brief" or "write a campaign brief"; produces a structured creator brief with deliverables, key messages, creative direction, timeline, disclosure rules, and compensation terms. Not for choosing how to split spend across creators — use budget-optimizer. 达人合作简报/创作者BF

Integrate Arcjet Guard into the Python Claude Agent SDK — wrap authored @tool with guard_tool, and use guard_hooks for UserPromptSubmit inbound plus PreToolUse on unwrapped built-ins / MCP. Use when asked to add Arcjet to claude-agent-sdk, rate limit those tools, screen inbound prompts, or block prompt injection / PII. This is Python claude-agent-sdk, not the JS adapter and not Claude Managed Agents hosted sessions.

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.