Run Claude Cowork Email Ops in one command. Dispatches to the email-ops-operator agent with a selected mode (morning, cleanup, retro, voice-refresh).
npx claudepluginhub khenson99/lesser-rings-cowork-marketplace --plugin claude-cowork-email-opsThis skill uses the workspace's default tool permissions.
This is a convenience entrypoint that runs the whole system via the plugin agent `email-ops-operator`.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Automates semantic versioning and release workflow for Claude Code plugins: bumps versions in package.json, marketplace.json, plugin.json; verifies builds; creates git tags, GitHub releases, changelogs.
This is a convenience entrypoint that runs the whole system via the plugin agent email-ops-operator.
Run one of:
/email-ops-run morning/email-ops-run cleanup/email-ops-run retro/email-ops-run voice-refreshOptional flags (space-separated):
shadow forces shadow mode behavior (no archive/trash/drafts; propose + digest + log only)live-archive allows auto-archive if config permits (never enables trash)no-labels avoids applying labels (digest only)Examples:
/email-ops-run morning shadow/email-ops-run cleanup live-archive$ARGUMENTS.email-ops-operator agent with a concise mode-specific instruction.
email-ops-operator spec.policies/threshold-config.yamlWhen delegating, send exactly one of these to email-ops-operator:
Run morning triage. Apply deterministic hygiene first, then classify remaining items. Follow policies/threshold-config.yaml and policies/always-human-rules.md. Produce a digest and include unsubscribe recommendations (recommend-only).
Run light cleanup only. Scope to obvious low-value broadcast content. No drafts. Never touch protected tiers or high-risk threads. Prefer label-only if any doubt.
Run weekly retrospective for the last 7 days. Measure precision/rescues and propose updates. Separate safe auto-applied updates vs approval-required. Do not lower destructive thresholds without explicit operator approval.
Run a voice refresh on sent mail only (last 30 days). Produce distilled updates to voice-profile.md, relationship-rules.md, and do-not-say.md guidance. Do not store raw email bodies anywhere outside the mailbox.