Loading...
Loading...
Found 44 Skills
Claude + Gemini Cross Fact-Checking. Conduct independent checks by three parties: Opus itself, Gemini Flash, and Gemini Pro → extract issues → discuss → output a consensus report.
In-depth article analysis, interpretation and fact-checking. Used to extract core viewpoints, examine logic, evaluate value and analyze writing skills.
USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking
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.
Search the web for information using DuckDuckGo or other search engines via curl. Use when users ask questions requiring up-to-date information, research, or fact-checking.
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.
Structured workflow for fact-checking claims in journalism. Use when verifying statements for publication, rating claims for fact-check articles, or building pre-publication verification processes. Includes claim extraction, evidence gathering, rating scales, and correction protocols.
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.
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.
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".
Analyzes events through journalistic lens using 5 Ws and H, investigative methods, source evaluation, fact-checking, newsworthiness criteria, and ethical journalism principles. Provides insights on story angles, information gaps, credibility, public interest, and media framing. Use when: Breaking news, information verification, source analysis, story development, media criticism. Evaluates: Factual accuracy, source credibility, completeness, newsworthiness, bias, public interest.
Detects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).