/blindspotsAsks Claude to find what you're missing or assuming, not what you're asking.
Category: Thinking & Reasoning
Before / After
Review my plan to migrate from Postgres to MongoDB.
/blindspots Review my plan to migrate from Postgres to MongoDB.
What changes in Claude's response
Most reviews check 'is the plan internally consistent?'. /blindspots asks 'what is this plan assuming that might not be true?'. You'll get things like: 'You're assuming your data is mostly read-heavy, but your schema suggests heavy writes', or 'You haven't mentioned how you'll handle existing foreign-key constraints'. It surfaces the questions you didn't think to ask.
When NOT to use /blindspots
Avoid on small decisions. Blindspot analysis is 5x the work for an answer to a question you weren't asking — pointless for 'should I name this function camelCase or snake_case'.
Codes that stack with /blindspots
/blindspots is one of 120 tested prompt prefixes. The full cheat sheet has before/after examples, warnings, combos, and 10 workflow playbooks.
See the full cheat sheet — from $5More Thinking & Reasoning codes
L99Pushes Claude to maximum reasoning depth. Less hedging, more opinion, longer answers.
/deepthinkForces Claude to reason through every layer before answering. Shows the work.
OODAObserve → Orient → Decide → Act. Best for time-pressured operational decisions.
CHAINLOGICShows each reasoning step explicitly so you can verify the logic, not just the conclusion.
OVERTHINKDeliberately over-analyzes to surface details you'd normally skip past.