Trim Build macOS plugin prompts#263
Open
dimillian-oai wants to merge 1 commit into
Open
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Why
build-macos-appscould not be scored byplugin-evalwhile its manifest starter prompt was still a string. After that prompt shape was normalized, the static report showed both trigger and invocation budget failures driven by long skill trigger metadata and detailed examples in always-loadedSKILL.mdentrypoints.This PR keeps the same macOS skill inventory and routing terms, but moves detailed examples out of the entrypoint path where they can be loaded only when the task needs them.
Impact
Build macOS Apps keeps its existing workflows while its starter prompt metadata matches the current plugin contract, trigger descriptions are smaller, and high-detail SwiftUI/window examples live in references instead of always-loaded skill bodies.
plugin-eval report progression
The same local report command was used throughout:
cd plugins/plugin-eval node ./scripts/plugin-eval.js analyze ../build-macos-apps --format markdownBefore the manifest prompt was normalized,
plugin-evalcould not emit a scored report because the string-shapeddefaultPrompthit:The final report clears the trigger and invocation budget failures. Remaining warnings are static budget warnings for trigger, invoke, and deferred text.
Validation
node ./scripts/plugin-eval.js analyze ../build-macos-apps --format markdowngit diff --check