Merged
Conversation
Mark the skill template TextPart as synthetic so the full prompt is
sent to the model but hidden from the user. Add a short ignored
summary part ('Running skill: <command>') so the user still sees
confirmation that the skill was loaded.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
TextPartassynthetic: trueinresolvePromptParts()so the full prompt is sent to the model but hidden from the user in the chat UI.ignored: truesummary part ("Running skill: <command>") so the user still sees confirmation that the skill was loaded, without exposing the full prompt or polluting the model's context.Details
When a user invokes a slash command (e.g.
/onboarding), the entire SKILL.md template was previously injected as a regularTextPartand displayed verbatim in the chat — disruptive for long skill prompts.OpenCode's existing
synthetic/ignoredsemantics handle this cleanly:synthetic: trueignored: trueThe subtask path is unaffected (it uses
SubtaskPart, notTextPart). The OpenWork frontend already filters on these flags, so no UI changes are needed.