Stats
Actions
Tags
From commercial-legal
Reviews pending playbook update proposals from the playbook-monitor agent, showing diff and offering accept/reject/edit/defer options. Use when proposals are pending or user asks about updates.
How this skill is triggered — by the user, by Claude, or both
Slash command
/commercial-legal:review-proposals [no arguments needed — works from the pending proposals file][no arguments needed — works from the pending proposals file]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Steps through pending playbook update proposals from the monitor agent and applies approved changes to `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`.
Steps through pending playbook update proposals from the monitor agent and applies approved changes to ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md.
Load the playbook-monitor agent and run Step 5 (review and approval flow).
If no proposals file exists or it is empty: respond "No pending proposals. Playbook is up to date." Do not proceed further.
Present proposals one at a time. For each, show the full proposal block and offer four options: Accept, Reject, Edit, Defer.
For Accept or Edit: show the exact diff to ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md before writing. Only apply after the attorney explicitly confirms.
For Reject or Defer: log the decision. Do not modify ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md.
After all proposals are resolved: show a summary of what changed, then archive the proposals file.
/commercial-legal:review-proposals
/commercial-legal:review-proposals
(runs automatically after playbook-monitor notifies you)
npx claudepluginhub anthropics/claude-for-legal --plugin commercial-legalReviews pending Turkish-law commercial playbook update proposals, presenting each for attorney approval before applying changes to CLAUDE.md. Useful for legal compliance workflows.
Cross-references structured review findings against an implementation plan, classifies each finding into an action category, applies concrete edits, and produces a traceability summary.
Guided experiment-loop retrospective over the ax agent-experience graph. Walks through open proposals, pending verdicts, and harness-hook effectiveness. Invoke via "ax retro" or "/ax:retro".