Fix example rewrites that invent facts (v2.11.3) - #233
Open
Scott-Emberson wants to merge 1 commit into
Open
Conversation
The §7, §8, and §12 After texts added details missing from their Before texts: a delicacy claim, an exact figure for a stated lower bound, and a book as the medium. Rule 3 forbids adding facts the source does not contain, and the 2.9.0 example audit missed these three. Refs blader#187. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This was referenced Aug 20, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Three worked examples in SKILL.md add details that their Before texts do not contain, against rule 3 ("Do not add a fact, name, number, date, quote, or citation unless it comes from the source or the user"). The 2.9.0 release (#189) re-cut five examples for exactly this reason (fixes #187), and these three escaped that audit:
Because these Before/After pairs are the prompt's few-shot examples, they taught the model to fabricate attributes, de-hedge quantities, and guess the medium while claiming the skill "does not make things up" (README).
Version bumped to 2.11.3 in SKILL.md, plugin.json, and the README history per AGENTS.md. No change to the 35 patterns. Found in a full-repo review; happy to adjust the replacement wording.
Refs #187.
🤖 Generated with Claude Code