Repository navigation
fix(productivity): explain software behavior through user examples - #17
Merged
Merged
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
When someone asks why saving a shared document failed, the explanation should start with their attempted save and the refusal they saw. The skill previously made examples optional and waited for a plain-English request before checking unexplained shorthand, so a reply could start with terms such as "authorization preflight" and leave the reader asking for another explanation.
The skill now starts software explanations with a recognizable user action and result, then carries that same example through the cause and the fix. It introduces internal terms when they help explain the example and adapts when the reader already knows the context or asks for implementation detail.
Added a fictional shared-document case to the existing writing evals. It checks that the reply explains the failed save concretely while preserving the limits: valid team access allows saving, revoked access stays revoked, saving without active access remains denied, and no content was lost.
Validation
bun run validate: both catalogues and local Markdown references passed.bun test: 58 passed, 0 failed; 292 assertions.git diff --check: passed.gpt-6.1-soltarget was rejected by the local Codex SDK account. That run had 1 provider error and no graded results; no Promptfoo quality pass is claimed. Saved model settings were left intact.