Merge main into dev

.claude/skills/spawn-merge/SKILL.md

@@ -8,7 +8,7 @@ Read the /merge, /takeover, and /close skills before starting.
 The goal is to evaluate the open PRs in the repository and decide which ones to merge.
 Each merge is performed in parallel by a sub-agent.
 
-Start by listing all open PRs.
+Start by listing all open PRs that are ready for review (skip drafts).
 An argument can be used to filter the PRs in scope.
 
 One at a time, for each PR, interactively prompt the user if we should /merge, skip, or /close.

.claude/skills/start-quest/SKILL.md

@@ -5,14 +5,18 @@ description: Start work on a quest.
 
 Before you begin, read `quest/CLAUDE.md` completely.
 
-Your goal is to implement the quest, or as much of it as possible, and create a PR.
+Your goal is to implement the quest, or as much of it as possible, and create a draft PR.
 The argument is the quest to work on.
 
 If you are unsure on the best course of action, ask the user for direction.
 
 Confirm the quest is ready and unclaimed.
 Claim it as `quest/CLAUDE.md` describes: `quest branch` names the branch and its bases, missing line branches get a draft PR, and the quest branch gets an empty commit.
+
 Implement the quest until it is complete, or some blocker is hit, then create a PR against the base.
 Keep scratch files (PR body, logs, notes) in the worktree's gitignored `.scratch/`.
 Never write to or clean up a directory other agents share, such as a session scratchpad.
-Summarize the notable changes for the user.
+
+When done, summarize any issues encounted, and suggest potential follow-up.
+If you're happy with the outcome, switch the draft PR to ready for review.
+If you want another set of eyes on it, keep it a draft.

CLAUDE.md

@@ -48,7 +48,7 @@ This file is split into nested `CLAUDE.md` files based on the language/situation
 - Try to do stuff asynchronously. ex. ask about follow-ups while tests run.
 - Try to recognize when you're stuck, or making minimal progress, and stop early.
 - If the core problem is addressed, ship it instead of spinning your wheels on meaningless revisions.
-- Benchmark any performance optimizations instead of relying on intuition.
+- Add or extend a benchmark for any performance-sensitive change so later regressions show up, and measure optimizations instead of relying on intuition.
 
 # Public API