Stop-hook hallucination and speculation-as-diagnosis detector. Audits the last assistant message for speculation, ungrounded causality, pseudo-quantification, and completeness overclaims; blocks stopping to force evidence-first rewrites.
/plugin marketplace add jamie-bitflight/claude_skills/plugin install hallucination-detector@jamie-bitflight-skillsUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Helps write internal communications including 3P updates, company newsletters, FAQs, status reports, and project updates using company-specific formats.
Assists in writing high-quality content by conducting research, adding citations, improving hooks, and providing section-by-section feedback.
Provides guidance for creating effective Claude Skills that extend capabilities with specialized knowledge, workflows, and tool integrations.