mob-checklisted

# mob-check ## Overview Surface what real people are actually discussing, recommending, and arguing about on a topic right now, ranked by what they engaged with (upvotes, likes, views, comments, prediction-market money), not by SEO. Google aggregates editors; this searches people. The skill is a fetch-rank-synthesize loop: 1. Parse intent and run a one-turn quality pre-flight (catch keyword traps before burning a search). 2. Fetch recent items from each available source using Hermes' native tools. 3. Pipe the gathered items through the bundled ranker (`scripts/rank.py`), which scores by relevance + recency + per-source-normalized engagement and fuses everything into one ranked, deduplicated, source-diversified list. 4. Read the ranked output and write a synthesized brief that obeys the output contract. The ranker is the skill's spine. Synthesizing from raw search results without running it is the single most common failure mode and produces confident, unranked slop. Run the ranker. ## When to Use Use when the user wants the live human conversation on a topic: - "what are people saying about <topic>", "what's the sentiment on <topic>" - "<X> vs <Y>, what does the community actually think" - "best <thing> according to real users", "is <thing> worth it" - "how are people using <tool/product>" - "latest on <event/person>", "take the pulse on <topic>" Do **not** use for: - A single authoritative fact, definition, or calculation. Use `web_search` directly. - Read