policy-qa

npx skills add majiayu000/claude-skill-registry --skill policy-qa --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# Policy Q&A Skill ## Purpose Answer policy and SOP questions with strict source attribution. Refuses to answer without relevant sources. Designed for compliance-sensitive environments. ## Usage ```python # Ask policy question answer = policy_qa( question="What is the approval workflow for journal entries over $100K?", top_k=5, min_confidence=0.8 ) ``` ## Workflow ### 1. Embed Question ```python from sentence_transformers import SentenceTransformer def embed_question(question, model_name='sentence-transformers/all-MiniLM-L6-v2'): """Embed question using same model as policy corpus""" model = SentenceTransformer(model_name) embedding = model.encode(question) return embedding.tolist() ``` ### 2. Retrieve from pgvector ```python import psycopg2 def retrieve_policy_sources(question_embedding, top_k=5): """Retrieve similar policy chunks from pgvector""" conn = psycopg2.connect(os.environ['POSTGRES_URL']) cursor = conn.cursor() # Vector similarity search query = """ SELECT id, text, document_name, section, page_number, url, 1 - (embedding <=> %s::vector) AS similarity FROM policy_chunks WHERE 1 - (embedding <=> %s::vector) > 0.3 -- Minimum similarity threshold ORDER BY embedding <=> %s::