feat(plugin): enable transcript inference by default; remove recall/remember skills#6
Open
lightzt99 wants to merge 2 commits into
Open
feat(plugin): enable transcript inference by default; remove recall/remember skills#6lightzt99 wants to merge 2 commits into
lightzt99 wants to merge 2 commits into
Conversation
These skills duplicated functionality now handled automatically by the UserPromptSubmit hook (search injection) and SessionEnd/PostCompact hooks (memory write). Exposing them as slash commands was redundant.
write_runtime_base_url() now writes POWERMEM_INFER_TRANSCRIPT=true into runtime.env so that every Claude Code session automatically triggers LLM fact extraction from the full transcript on SessionEnd, without requiring manual env configuration.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Remove
recallandrememberskills — these slash commands duplicated what the hook layer already does automatically (UserPromptSubmit injects search results; SessionEnd/PostCompact persist memories). Removing them reduces user-facing surface area and avoids confusion.Enable
POWERMEM_INFER_TRANSCRIPT=trueon init —write_runtime_base_url()incommon.shnow writes this flag intoruntime.envso LLM fact extraction runs on every session transcript automatically, without requiring manual env configuration after install.Changes
skills/recall/SKILL.mdskills/remember/SKILL.mdscripts/common.shwrite_runtime_base_url()Notes
POWERMEM_INFER_TRANSCRIPTwas previouslyfalseby default (onlyPOWERMEM_INFER_COMPACTdefaulted totrue). This change makes transcript inference opt-out rather than opt-in.POWERMEM_INFER_TRANSCRIPT=falsein their environment before re-runninginit.sh.🤖 Generated with Claude Code