improve-skills: surface reviewer-facing case context (prompts, fixtures, per-epoch) - #113
Draft
gas2own wants to merge 2 commits into
Draft
improve-skills: surface reviewer-facing case context (prompts, fixtures, per-epoch)#113gas2own wants to merge 2 commits into
gas2own wants to merge 2 commits into
Conversation
…n body Make the skill spell out what a PR reviewer needs to understand an asta_skills validation from the PR's first post alone: per-case verbatim prompt + README-guidance mapping, the fixture/project-setup (and why it's realistic for the prompt), per-epoch arms values with a fixture column, and a note on which epochs were measured under a changed fixture. Also add a step-2 reminder to match a case's fixture to its prompt (a 'continue this research' prompt needs a seeded project, not an empty /app). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Draft — makes the
improve-skillsworkflow produce PR evidence a reviewer can understand and trust.Why
The validation history of asta-plugins#110 exposed three recurring gaps: prompts and fixture setup were initially absent from the first post; continuation prompts were mistakenly tested in an empty
/app; and the corrected seeded-fixture run returned scores without retained transcripts. That last run changed three apparent1regression guards into0 → 0gap cases, but cannot explain what the agent did instead.What
This is a workflow/documentation change; it does not modify runtime skill behavior.