pipeline
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack โ pandas + numpy + scipy +โฆ
Diverga HUD (Heads-Up Display) management skill. Configure and manage the research project statusline display. Supports multiple presets: research, checkpoint, memory, minimal. Triggers: "hud", "statusline", "display settings"
Claude Code
$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud --agent claude-code
Codex
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud -a codex -y
Cursor
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud -a cursor -y
Gemini CLI
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud -a gemini-cli -y
GitHub Copilot
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud -a github-copilot -y
OpenCode
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud -a opencode -y
Windsurf
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud -a windsurf -y
name: hud description: | Diverga HUD (Heads-Up Display) management skill. Configure and manage the research project statusline display. Supports multiple presets: research, checkpoint, memory, minimal. Triggers: "hud", "statusline", "display settings" version: "12.0.1"
Configure and manage the Diverga HUD (Heads-Up Display) statusline.
The Diverga HUD provides a real-time statusline in your terminal showing:
The HUD is **independent** of oh-my-claudecode and works as a standalone component.
/diverga-hud status
Show current HUD configuration and status:
/diverga-hud preset <preset_name>
Change HUD display preset:
| Preset | Description | Example Output | |--------|-------------|----------------| | `research` | Standard view (default) | `๐ฌ AI-Ethics โ Stage: foundation โ โโโโโ (2/11) โ ๐ง 95%` | | `checkpoint` | Detailed checkpoints | Multi-line with checkpoint details | | `memory` | Memory focus | Shows context and memory health | | `minimal` | Stage only | `๐ฌ foundation` |
/diverga-hud enable /diverga-hud disable
Turn HUD display on or off.
/diverga-hud setup
Install or repair HUD statusline integration: 1. Creates `~/.claude/hud/diverga-hud.mjs` 2. Updates `~/.claude/settings.json` with statusLine command 3. Initializes `.research/hud-state.json` in current project
Run `/diverga-hud setup` to automatically configure HUD.
1. Ensure the HUD script exists at `~/.claude/hud/diverga-hud.mjs`
2. Add to `~/.claude/settings.json`:
{
"statusLine": {
"type": "command",
"command": "node ~/.claude/hud/diverga-hud.mjs"
}
}3. Restart Claude Code for changes to take effect.
**Location**: `.research/hud-state.json`
{
"version": "1.0.0",
"enabled": true,
"preset": "research",
"last_updated": "2026-02-04T18:45:00Z",
"cache": {
"project_name": "AI-Ethics-HR",
"current_stage": "foundation",
"checkpoints_completed": 2,
"checkpoints_total": 11,
"memory_health": 95
}
}HUD reads from:
When `/diverga-hud` is invoked:
1. **status** command:
2. **preset** command:
3. **enable/disable** command:
4. **setup** command:
| Error | Response | |-------|----------| | No project found | "No Diverga project detected. Initialize with `/diverga-setup`" | | Invalid preset | "Invalid preset. Available: research, checkpoint, memory, minimal" | | Settings write fail | "Could not update settings.json. Check file permissions." |
โโโโโโโโโโโ (2/11)
๐ง 95%
Color coding:
Available stages:
User: /diverga-hud status Claude: ๐ **Diverga HUD Status** | Setting | Value | |---------|-------| | Enabled | โ Yes | | Preset | research | | Project | AI-Ethics-HR | | Stage | foundation | | Checkpoints | 2/11 (18%) | | Memory Health | 95% | HUD is active and displaying in statusline.
User: /diverga-hud preset minimal Claude: โ HUD preset changed to **minimal**. New display: `๐ฌ foundation` To switch back: `/diverga-hud preset research`
User: /diverga-hud setup Claude: ๐ง **Setting up Diverga HUD...** 1. โ Created ~/.claude/hud/diverga-hud.mjs 2. โ Updated ~/.claude/settings.json 3. โ Initialized .research/hud-state.json ๐ HUD setup complete! **Please restart Claude Code** to activate the statusline. Your HUD will display: `๐ฌ AI-Ethics-HR โ Stage: foundation โ โโโโโโโโโโโ (2/11) โ ๐ง 95%`
1. Check if script exists:
ls -la ~/.claude/hud/diverga-hud.mjs
2. Check settings.json:
cat ~/.claude/settings.json | grep statusLine
3. Test script manually:
node ~/.claude/hud/diverga-hud.mjs
4. Ensure you're in a Diverga project directory (has `.research/` folder)
Run refresh to update cache:
/diverga-hud status
Or manually trigger cache rebuild by editing `.research/hud-state.json`.
The HUD automatically updates when:
For manual sync, use `/diverga-memory sync`.
## ๐ฅ ๅ่ ยท StatsPAI โ Stata ไธ R ็ Python ๅนณๆฟ๏ผไธบ AI Agent ่็ ๐ Stata / R ๅนณๆฟ๏ผreghdfeใcsdidใrdrobustใsynthใfixestใdid ็ญๅธธ็จๅฝไปคๅจ Python ไธญไธ็ซๅผๆฟไปฃ๏ผไธไธช import statspai as sp ๆๅฎ DID / RD / IV / SCM / DML / matching ๐ค ้ขๅ Agent ่ฎพ่ฎก๏ผ็ปๆๅ็ปๆๅฏน่ฑก + ๅ ็ฝฎ MCP Server๏ผClaude / Codex
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack โ pandas + numpy + scipy +โฆ
Use when the user asks to run a full empirical / causal analysis in Python โ by default in the style of an applied economicsโฆ
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack โ pandas + numpy + scipy +โฆ
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem โ native Stata + reghdfe + ivreg2 + csdid +โฆ
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem โ dplyr + tidyr + haven +โฆ
Systematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-readyโฆ
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also coversโฆ
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, fillingโฆ