belief-state-runtimelisted

# belief-state-runtime.skill Evaluates the trustworthiness of a claim based on evidence. ## When to use - User asks "is this true?" or "can I trust this?" - Agent collects information from multiple sources and needs to assess reliability - Detecting contradictions between evidence pieces - Quantifying confidence in a conclusion ## ⚡ AUTO WORKFLOW (Default - Always Run This First) **IMPORTANT: When this skill is triggered, you MUST follow this workflow automatically:** ```python from assess import get_assessment_prompt, assess_claim_with_response # Step 1: SEARCH FOR EVIDENCE (MANDATORY) # Use your search tool (online-search, multi-search-engine, etc.) to find # real, verifiable evidence about the claim. Search for: # - Official data and statistics # - Academic research and studies # - Credible news reports # - Expert opinions # # Example search queries: # - "[claim topic] facts evidence research" # - "[claim topic] statistics studies 2024" # - "专家观点 [claim topic]" # Step 2: Get the assessment prompt prompt = get_assessment_prompt(claim="The claim", evidence="Search results + user's evidence") # Step 3: YOU (the AI) answer the prompt with 6 boolean judgments # Based on your search results and analysis: # - direct_support: Does the evidence support the claim? # - new_info: Does it provide new information? # - logical_consistent: Is it logically consistent? # - direct_refute: Does it explicitly refute the claim? # - limitation: Are there limitati