cbh123

slack app:

cbh123

---
name: babysit
description: Use when asked to babysit, monitor, shepherd, or keep working on a GitHub pull request until it is green, review-ready, approved, mergeable, or ready to merge.
---

# Babysit

Use this skill to stay with a PR after it has been opened or while it is waiting on CI, reviews, mergeability, or small follow-up fixes.

The goal is: keep the PR moving until it is ready to merge. Do not merge unless the user explicitly asks.

cbh123

Review guidelines:

You are acting as a reviewer for a proposed code change made by another engineer.

Below are some default guidelines for determining whether the original author would appreciate the issue being flagged.

These are not the final word in determining whether an issue is a bug. In many cases, you will encounter other, more specific guidelines. These may be present elsewhere in a developer message, a user message, a file, or even elsewhere in this system message. Those guidelines should be considered to override these general instructions.

Here are the general guidelines for determining whether something is a bug and should be flagged.

cbh123

#!/usr/bin/env bash
# @referToSpec checkpointer
# watch-checkpointer.sh
# Watches the current directory and on changes:
# 1) runs checkpointer.sh save
# 2) captures the single-word id
# 3) cd's to $CONDUCTOR_ROOT_PATH
# 4) runs checkpointer.sh restore <id>

set -euo pipefail

cbh123

#!/bin/bash
#
# Migrate Cursor IDE config to Conductor (Claude Code)
#
# What this script does:
#   1. Copies MCP servers from ~/.cursor/mcp.json → ~/.claude.json
#   2. Copies project MCP servers from .cursor/mcp.json → .mcp.json
#   3. Copies .cursorrules → CLAUDE.md
#   4. Copies .cursor/rules/*.mdc → CLAUDE.md (appended)
#

cbh123

#!/bin/bash

# Script to copy entire production database to workspace instance

# Get the workspace name from CLAUDE_CODE_WORKSPACE or use default
WORKSPACE_NAME="${CLAUDE_CODE_WORKSPACE:-$(basename "$(pwd)")}"
IDENTIFIER="com.conductor.app.dev.$WORKSPACE_NAME"

# Define paths
PROD_DB="$HOME/Library/Application Support/com.conductor.app/conductor.db"

cbh123

{
    "scripts": {
        "setup": "pnpm run setup",
        "run": "pnpm run dev",
        "archive": "rm -rf \"$HOME/Library/Application Support/com.conductor.app.dev.$CONDUCTOR_WORKSPACE_NAME\""
    },
    "runScriptMode": "concurrent"
}

cbh123

Requirements:

- Reversion: Capture an entire state (HEAD + untracked/unstaged/staged changes) and restore it later (basically like git reset --hard, but also restoring untracked/unstaged/staged files)
- Turn-by-turn diff: Show a diff between two checkpoints (including all files - untracked, unstaged, staged, and committed), or between a checkpoint and the current state
- No disruption to user: In the process of storing a checkpoint, no files on disk should be modified, nor should there be any obvious public-facing changes in git (e.g., HEAD change)

The API would look like:
- checkpointId = capture()
- revert(checkpointId)
- diff(id1, id2) or diff(id1, 'current')

cbh123

#!/bin/bash

# MDM Pre-population Script for Chorus
# This script pre-populates the base URL and API keys for enterprise deployments

set -e

# Default values (can be overridden by environment variables)
CHORUS_BASE_URL="${CHORUS_BASE_URL:-}"
ANTHROPIC_API_KEY="${ANTHROPIC_API_KEY:-}"

cbh123

Claude's Guide to Chorus Development

What is Chorus?

Chorus is a native Mac AI chat app that lets you chat with all the AIs.

It lets you send one prompt and see responses from Claude, o3-pro, Gemini, etc. all at once.

It's built with Tauri, React, TypeScript, TanStack Query, and a local sqlite database.