sync (digest only) — 2026-06-01#6
Open
norbert-pap wants to merge 1 commit into
Open
Conversation
…wers) Sources checked: 6 (gstack, agent-skills, anthropics/skills, awesome-agent-skills, awesome-claude-code-toolkit, designpowers) Since: 2026-05-25 (no prior sync state found)
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Weekly upstream sync — 2026-06-01. No cherry-picks applied this week. Two deferred-but-noteworthy items from designpowers for your review.
Sources checked (6)
/shipcarving, PII redaction for gstack-specific skills. Nothing maps to claudebert's review pipeline.Changes applied
None.
Deferred — noteworthy
1. designpowers PR #27 — Add review lane (design-review)
Source: Owl-Listener/designpowers#27
Target skill:
design-reviewWhat it does: Adds a lightweight review-only lane for auditing existing work without the full build pipeline. Key concepts:
Why deferred: The architecture is fundamentally different from claudebert's two-layer (creative director + mechanical audit) design-review. The parallel sub-agent pattern doesn't map to claudebert's structure, and the lightweight "inferred brief" conflicts with claudebert's richer intake flow. The Reconciliation Protocol priority ordering is the one extractable principle, but adding it requires editorial judgment about where in the skill it belongs and how it interacts with the existing severity taxonomy.
2. designpowers PR #25 — Add design-md skill
Source: Owl-Listener/designpowers#25
Target skill:
new: design-md(does not exist in claudebert)What it does: A dedicated skill for reading user-provided
DESIGN.mdfiles as authoritative design token sources:Why deferred: Requires creating a new
design-md/SKILL.mdfrom scratch. The security framework is interesting (prompt injection via design files is a real vector), but the full scope needs editorial judgment — particularly how this relates to design-review's existing DESIGN.md handling and whether thedesign-docskill overlaps.Gstack detail (for reference)
The gstack v1.55 release wave included a "browser crash-loop" fix, but this applies to gstack's own browse binary (a different codebase from claudebert's browse binary). The gstack-specific browser fix has no direct port path.
gstack's
design-review/SKILL.mdwas modified in v1.55, but the change was YAML frontmatter quoting only (adding quotes to descriptions containing colons) — a compatibility fix for strict YAML parsers, not a methodology change.Sync run: 2026-06-01 | No prior
.sync-state.jsonfound — used 7-day lookback windowGenerated by Claude Code