feat: your skill and knowledge review requests in Claude Code — /altimate-code:rules, decision toasts, publish relays the review
SA
8h ago+207+207+012345678901234567890123456789-6-6-0123456789
Summary
Your own skill and knowledge requests to a linked workspace, and the owner's or an admin's decisions on them, now show in Claude Code sessions. This is read-only: withdrawing and removing happen in the Altimate web app, the altimate-code TUI or the VS Code extension. It needs altimate-code with AltimateAI/altimate-code#1716 (stacked on #1708). Merge and release this after the first altimate-code release that includes it. With an older altimate-code, the new parts stay quiet.
/altimate-code:rulesadds "Your skill and knowledge requests" after your proposals, fromworkspace review status --json.- Each request shows its status, whether it's an update, the reviewer and reason, and "waiting past 14 days".
- Replaced requests are counted, not listed.
- Publish guidance: the
altimate-codeskill now runsskill publish "<name>" --jsonand relays the review outcome: "sent for review to ", "already waiting", "already approved", or the refusal message, then points to/altimate-code:rules. - A direct toast for decisions (
hooks/review-notices.ts, started fromintegrations.tsxin interactive sessions):- It runs
workspace review decisions --json --unseen --mark-seen --host claude-uiat session start and every 15 minutes. - Each decision gets one toast ("◆ altimate · Your skill "X" was approved by Y…", or rejected or removed with the reason), at most 3 per check with the rest counted.
- It stops asking for the session on
signed_out,not_linked,unsupported, or a CLI without the command. - Its seen state is its own (
claude-ui), apart from the session-start context. altimate-code adds the decisions and the waiting count to that context with no change here.
- It runs
- Version 1.6.0, with the CHANGELOG and README updated.
Verification
- The mod tests pass (196, 7 new for the toast logic: one-time display, the cap, stopping on final statuses, older CLIs). Removing each of the 5 key fixes made a test fail.
- Shell tests and the 65 Python tests pass.
- The CLI side was tested end to end through the VS Code extension: AltimateAI/vscode-altimate-mcp-server#545 has screenshots. I haven't run this plugin in a live Claude Code session.
- To try it: install from this branch's marketplace and start an interactive session in a linked project. Run
/altimate-code:rules, and ask Claude to publish a project skill. Have the owner approve it in the web app, then wait for the toast or start a new session. The same decision isn't toasted again.
- To try it: install from this branch's marketplace and start an interactive session in a linked project. Run
🤖 Generated with Claude Code