discernment-nudge: A Claude Skill That Tells You to Fact-Check Claude
discernment-nudge is an opt-in Claude Agent Skill that appends two or three follow-up questions after a substantive answer to help the user check facts and spot missing context.
What it is
A new opt-in skill added to Anthropic's Claude Agent Skills repository.
What it does
After a substantive answer the user might act on, it fires at most once per conversation to append short, targeted questions prompting the user to verify key facts, probe assumptions, and notice missing context; it explicitly skips trivial lookups, formatting tasks, code, and creative writing.
Why it matters
It's a rare case of a model vendor building a skill whose job is to make the user trust the model's own output less, which is a more honest response to hallucination risk than most 'just trust our benchmarks' marketing.
How to use it
Enable the discernment-nudge skill in Claude Code or via the API if you want automatic verification prompts appended to substantive answers.
A 1,024-Character Limit Just Forced a Skill Rewrite
Anthropic renamed its claude-academy-guide Claude Agent Skill to academy-guide and shortened its description to comply with skill-upload validation rules for custom skills.
Claude Academy Guide Skill Reads a Live Course Catalog So It Never Goes Stale
The academy-guide Claude Agent Skill recommends matching Claude Academy courses and tutorials by reading a live catalog JSON at runtime instead of an embedded snapshot.
claude-api Skill Gets an `upgrade` Subcommand for the 0.x to 1.x SDK Jump
Anthropic's claude-api Claude Agent Skill added an upgrade subcommand that walks a Python project through migrating from the anthropic 0.x SDK to 1.x, including the new httpx2 HTTP layer.