Loading...
Loading...
Found 74 Skills
AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.
LLM guardrails with NeMo, Guardrails AI, and OpenAI. Input/output rails, hallucination prevention, fact-checking, toxicity detection, red-teaming patterns. Use when building LLM guardrails, safety checks, or red-team workflows.
Skill for optimizing article style to remove AI flavor. Used to identify and rewrite issues such as AI traces, template tone, material-like style, translationese, empty buzzwords, excessive golden sentences, overuse of em dashes, bullet stacking, and random bolding in articles, official account drafts, self-media drafts, oral broadcast scripts, speech scripts, course scripts, and product copy; activated when users say phrases like "remove AI flavor", "eliminate AI traces", "not written by AI", "more human-written", "more natural", "less robotic", "remove template feel", "polish to official account final draft". Not applicable for fact-checking, zero-based topic planning, converting papers to official account articles, pure title generation, or pursuing AI detector pass rates.
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
This skill is used when the answer requires web retrieval or independent multi-source verification, including fact-checking, technical comparison, current information, conflicting claims, important suggestions, as well as in-depth research that requires multiple rounds of deep exploration and iterative convergence.
Search for recent news and developments on a topic, organize them chronologically, and deliver a concise briefing. Use this skill when the user wants to catch up on recent events, news, or developments around a topic. Trigger on phrases like "what's new with X", "recent news about X", "any updates on X", "what happened with X lately", "catch me up on X", "news roundup for X", "what did I miss about X", "latest developments in X", or "has anything changed with X recently". Also trigger when the user mentions a time frame like "this week", "this month", "since January", or "in the last few days" combined with wanting information. Don't trigger for general research, product comparisons, or fact-checking — only when recency is the point.
Doubaoya (doubaoya / This Duck) — All-in-One Entry for New Media Data Retrieval and Content Creation: Use a single DOUBAOYA_API_KEY to access all available capabilities of the platform (search/ranking/daily feed/account/analysis/prohibited word detection/AI image generation/web verification), and route to specific capabilities based on intent. It also includes **web-based research with source attribution / fact-checking**. Trigger words: image editing, compliance check, follow-up updates, image matching, main visual, image-to-image, growth ranking, article scraping, text-to-image, extreme words, source verification, daily ranking, hot topic ranking, view comments, title creation, traffic chasing, weekly viral content, mid-line topic selection, fact-checking, today's hot topics, today's viral content, low-follower viral content, low-follower high-like content, content details, cross-platform hot searches, content export, content creation, content inspiration, Xiaohongshu content writing, export daily feed, export viral content, export topic selection, compliance detection, weekly trend, top accounts, real-time data retrieval, benchmark content, benchmark analysis, cover reference, cover strategy, cover inspiration, cover design, cover topic selection, small account strategy, citation source, comment section scraping, Douyin data retrieval, Douyin search, Douyin comments, continuous growth, most likes, latest releases, title optimization, title strategy, title inspiration, title generation, traffic trend, popularity index, hot topic scanning, popular articles, popular accounts, viral content imitation, viral content review, viral cover, viral ranking, viral articles, viral titles, viral structure, image generation, user demand, monitor Gongzhonghao, social media sentiment, competitor tracking, note benchmarking, note analysis, note generation, note topic selection, amateur viral content, web search, web verification, aggregated hot ranking, sentiment monitoring, link analysis, comment analysis, comment trend, topic research, Doubao search, recent viral content, topic analysis, topic inspiration, topic materials, topic angle, link parsing, read growth, first image inspiration, dark horse notes, dark horse accounts, AI image generation, cross-platform viral content, Gongzhonghao writing, Gongzhonghao data retrieval, Gongzhonghao cover, Gongzhonghao ranking, Gongzhonghao title, Gongzhonghao ranking list, Gongzhonghao viral articles, Gongzhonghao scraping, Gongzhonghao dark horse accounts, cold-start benchmarking, growth rate ranking, write after benchmarking, Xiaohongshu content, Xiaohongshu creation, Xiaohongshu weekly ranking, Xiaohongshu cover, Xiaohongshu ranking, Xiaohongshu search, Xiaohongshu daily ranking, Xiaohongshu title, Xiaohongshu ranking list, Xiaohongshu hot ranking, Xiaohongshu scraping, Xiaohongshu topic selection, scrape Douyin content, find benchmark notes, search Douyin viral content, hot search keywords, short video topic selection, Shipinhao daily feed, Shipinhao viral content, Shipinhao topic selection, subscribe to Gongzhonghao, cross-platform analysis, cross-platform hot searches, cross-platform topic selection, high-click title, AI Shipinhao, Gongzhonghao prohibited words, export traffic opportunity, Xiaohongshu weekly ranking, batch scrape Gongzhonghao, Douyin real-time search, Douyin comprehensive search, write Xiaohongshu content by example, discover viral notes, competitor content review, AI Shipinhao, account content list, last 30 days content, Xiaohongshu TOP, Xiaohongshu popular notes, Xiaohongshu viral notes, Xiaohongshu note query, hot ranking TOP10, view track hot content, Xiaohongshu/Douyin/Gongzhonghao, what did a certain Gongzhonghao publish
Validate whether an implementation matches its stated goal. Use this skill when a skill or agent wants a second opinion on its own output, when the user says "check this implementation", "validate what you did", "is this correct?", "review the output", or "did you do this right?". Also spawned automatically as a subagent by other skills (memory-bridge, daily-update) to self-check their outputs before presenting to the user. Returns a structured pass/warn/fail verdict with specific actionable issues.
Detect and annotate hallucinations, unsupported claims, fabricated studies, and incorrect conclusions in text so that AI only cites verifiable, trustworthy content. Use this skill whenever the user asks you to fact-check, validate sources, check for hallucinations, or ensure that generated content is grounded in real evidence, even if they do not explicitly use the word "hallucination".
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the speaker. Use before a pitch, press release, reactive comment, DM, or other journalist-facing draft is trusted or sent.
Verify reality-grounded claims against external sources in both directions before they ship — could the 'absurd' be real, could the 'obvious' be false or long-established? Use whenever an artifact, or the sentence you are about to write, asserts something as plausible, realistic, absurd, novel, or impossible from intuition rather than a checked source; before relying on a factual claim in prose, a design rationale, a research claim, or a plan. Fires on metacognitive doubt — when you can't actually know, verify instead of trusting the feeling. Scans read-only, then fixes the clear errors or flags the judgment calls; leaves deliberate fiction alone.
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.