Loading...
Loading...
Found 594 Skills
Sweep current cross-platform hotspots and surface emerging keywords from the latest crawl batch. Use when the user asks 今日热点 / 今天有什么热点 / 今天热搜 / 各平台热搜 / 看一下当前热搜 / 现在在火什么 / 全网热点 / 全网在聊什么 / what's trending / what's trending now / multi-platform trend sweep / hotspot snapshot, or wants a quick snapshot of zhihu / weibo / douyin / bilibili / toutiao / baidu / thepaper / ifeng / tieba / cls-hot / wallstreetcn-hot at once via the trendradar MCP. Combines latest news with both preset-keyword extraction and emergent auto-extraction so the agent can flag 全网共振 (cross-platform resonance) and 新冒头 (newly emerging) terms in a single pass.
Watch a topic list for anomalous heat spikes and push channel-formatted alerts (飞书/钉钉/企业微信/Telegram/Slack/Bark/ntfy/Email/Webhook) via trendradar MCP. Use when the user wants 异动告警/突发热点推送/监控 XX 话题/订阅热点/breakout alert/ping me when X spikes.
Generate digest trend reports — daily/weekly/monthly/period-vs-period summaries — via the trendradar MCP. Picks one of three audience templates 执行摘要(C-suite)/媒体行业/投放团队. Use when the user asks 出一份日报/周报/月报/趋势简报/对比上周/给老板看的简报/digest/summary report/今天的总结.
Turn a trending hotspot into platform-native viral content — generates title variants, opening hooks, body skeletons, hashtags, and CTAs tailored to 小红书/抖音/B站/微博/知乎/公众号. Use when the user asks 写爆款/借势XX/小红书笔记/抖音脚本/微博热搜文案/B站标题/知乎回答开头/公众号开头/viral title for X. Includes 30+ proven title patterns and platform-specific 合规 guardrails.
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, openrouter, llm api, claude sonnet, claude opus, gemini api, kimi, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative
See and understand images when you (the current model) have no native vision. Use this WHENEVER you need to look at, read, describe, OCR, or reason about the contents of an image, screenshot, photo, diagram, chart, UI mockup, or scanned page — including when the user references a local image file or an image URL and you cannot view it yourself. Also triggers on: 看图 / 识图 / 截图 / 图片内容 / OCR 文字识别 / 这张图是什么. Delegates the actual seeing to a configurable OpenAI-compatible vision model via a small script.
Use when finding contradictions or reasoning gaps.
dontbesilent Execution Diagnosis. Diagnose the real reason why you know what to do but fail to act using the Adlerian psychology framework. Triggers: /dbs-action, /action, "I know what to do but can't do it", "Why do I always procrastinate" Execution block diagnosis using Adlerian psychology framework. Trigger: /dbs-action, "I know what to do but can't do it", "why do I procrastinate"
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
Keep a system's business logic independent of the technology it talks to, by reasoning about which way dependencies point across a hexagonal / ports-and-adapters / clean-architecture boundary. A system holds three kinds of code — its reason to exist (the business logic), its connections to the outside world, and how it's run (the wiring and entrypoint) — so the question is never "which folder" but "is this the reason, a connection, or how it's run, and what may it depend on?" Use it to scaffold a new system, place a feature, integration, or entrypoint, review how it's shaped, or write an ADR about the layout — and whenever a dependency points the wrong way or you're unsure where something belongs. Language-/framework-agnostic: the kinds map onto whatever names a project uses (app/infra/run, domain/adapters/cmd). Reach for it even when the user never says "hexagonal": "where should this go", "scaffold it ports-and-adapters", "review against hexagonal principles", "which layer owns this" are all signals.
dontbesilent Good Question Generator. Rewrite vague problems into problem briefs that Agents can reason about, critique, and verify, and assess the degree to which they can be solved automatically. Triggers: /dbs-good-question, /good-question, /problem-brief, /agent-solvability, "Can this problem be solved automatically?", "Help me clarify this problem" Turn fuzzy problems into agent-solvable problem briefs and evaluate automation readiness. Trigger: /dbs-good-question, "clarify this problem", "can an agent solve this"