By omriariav
Primes Claude with a collaborator frame at session start (based on Amanda Askell's prompting philosophy — positive framing, permission to push back, no apology spirals). Provides /coacher:status, /coacher:audit, /coacher:reset, and /coacher:rant for mid-session integrity checks, CLAUDE.md conflict detection, re-anchoring, and frustration-to-productive translation.
Cross-check the coacher frame against any CLAUDE.md content in context and flag stance-layer conflicts or overlaps with file+line evidence.
Translate a raw user vent into a productive task and execute it under the coacher frame. Pass your full unfiltered frustration as the argument — no filtering needed.
Re-anchor the coacher collaborator frame mid-session. Useful when Claude has drifted into hedging or over-apologizing.
Verify whether the claude-coacher collaborator frame is present in Claude's current context — integrity check for the SessionStart hook.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub omriariav/claude-coacher --plugin coacherBen Gurion Airport (TLV) live flight data, destination weather, and historical delay analysis
Install claude-pulse statusline for real-time token usage monitoring.
Format and copy Claude output to clipboard for Slack, Gmail, Google Chat, Google Docs, Jira, Markdown, Rich Text, or plain text.
Review any project's .claude/ folder setup against best practices (based on https://x.com/akshay_pachaar/status/2035341800739877091). Scores 8 dimensions (24-point rubric).
Evaluate any skill's design quality against best practices (based on https://x.com/trq212/status/2033949937936085378). Scores 10 dimensions (29-point rubric), detects anti-patterns, and optionally applies safe fixes. Complements /reflect which covers conversation-level learnings.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns