Skip to content
Automation
Skill

/hud

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"

From plugin
auto-empirical-research-skills
4.9k200 skills

Claude Code

$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill hud --agent claude-code

SKILL.md

hud.SKILL.md
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"

Diverga HUD Skill

Configure and manage the Diverga HUD (Heads-Up Display) statusline.

Overview

The Diverga HUD provides a real-time statusline in your terminal showing:

  • Current research project name
  • Research stage progress
  • Checkpoint completion status
  • Memory/context health

The HUD is **independent** of oh-my-claudecode and works as a standalone component.

Commands

Status

/diverga-hud status

Show current HUD configuration and status:

  • Whether HUD is enabled
  • Current preset
  • Project name and stage
  • Checkpoint progress
  • Memory health

Presets

/diverga-hud preset <preset_name>

Change HUD display preset:

| Preset | Description | Example Output | |--------|-------------|----------------| | `research` | Standard view (default) | `๐Ÿ”ฌ AI-Ethics โ”‚ Stage: foundation โ”‚ โ—โ—โ—‹โ—‹โ—‹ (2/11) โ”‚ ๐Ÿง  95%` | | `checkpoint` | Detailed checkpoints | Multi-line with checkpoint details | | `memory` | Memory focus | Shows context and memory health | | `minimal` | Stage only | `๐Ÿ”ฌ foundation` |

Enable/Disable

/diverga-hud enable
/diverga-hud disable

Turn HUD display on or off.

Setup

/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

Installation

Automatic (Recommended)

Run `/diverga-hud setup` to automatically configure HUD.

Manual

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.

State Files

HUD State

**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
  }
}

Project State

HUD reads from:

  • `.research/project-state.yaml` - Project metadata
  • `.research/checkpoints.yaml` - Checkpoint completion status

Protocol

When `/diverga-hud` is invoked:

1. **status** command:

  • Read `.research/hud-state.json`
  • Display current configuration
  • Show live project status

2. **preset** command:

  • Validate preset name (research, checkpoint, memory, minimal)
  • Update `.research/hud-state.json`
  • Confirm change

3. **enable/disable** command:

  • Update `.research/hud-state.json` enabled flag
  • Confirm change

4. **setup** command:

  • Check if `~/.claude/hud/` exists, create if not
  • Copy/update `diverga-hud.mjs` script
  • Update `~/.claude/settings.json` statusLine
  • Initialize `.research/hud-state.json`
  • Display success message

Error Handling

| 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." |

HUD Components

Progress Bar

โ—โ—โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹ (2/11)
  • `โ—` = Completed checkpoint (green)
  • `โ—‹` = Pending checkpoint (dim)
  • `(X/Y)` = Completed/Total count

Memory Health

๐Ÿง  95%

Color coding:

  • Green: 70%+ (healthy)
  • Yellow: 40-70% (moderate)
  • Red: <40% (needs attention)

Stage Indicator

Available stages:

  • `foundation` - Research question, paradigm
  • `theory` - Theoretical framework
  • `methodology` - Research design
  • `design` - Database, sampling
  • `execution` - Data collection, screening
  • `analysis` - Data analysis
  • `validation` - Quality, peer review

Examples

Check Status

User: /diverga-hud status

Claude: ๐Ÿ“Š **Diverga HUD Status**

| Setting | Value |
|---------|-------|
| Enabled | โœ… Yes |
| Preset | research |
| Project | AI-Ethics-HR |
| Stage | foundation |
| Checkpoints | 2/11 (18%) |
| Memory Health | 95% |

HUD is active and displaying in statusline.

Change Preset

User: /diverga-hud preset minimal

Claude: โœ… HUD preset changed to **minimal**.

New display: `๐Ÿ”ฌ foundation`

To switch back: `/diverga-hud preset research`

Setup HUD

User: /diverga-hud setup

Claude: ๐Ÿ”ง **Setting up Diverga HUD...**

1. โœ… Created ~/.claude/hud/diverga-hud.mjs
2. โœ… Updated ~/.claude/settings.json
3. โœ… Initialized .research/hud-state.json

๐ŸŽ‰ HUD setup complete!

**Please restart Claude Code** to activate the statusline.

Your HUD will display:
`๐Ÿ”ฌ AI-Ethics-HR โ”‚ Stage: foundation โ”‚ โ—โ—โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹โ—‹ (2/11) โ”‚ ๐Ÿง  95%`

Troubleshooting

HUD Not Showing

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)

Stale Data

Run refresh to update cache:

/diverga-hud status

Or manually trigger cache rebuild by editing `.research/hud-state.json`.

Integration with Diverga

The HUD automatically updates when:

  • Checkpoints are completed
  • Stage advances
  • Project state changes

For manual sync, use `/diverga-memory sync`.

Read more
@brycewang-stanford
Ships withauto-empirical-research-skills

## ๐Ÿ”ฅ ๅŠ›่ ยท StatsPAI โ€” Stata ไธŽ R ็š„ Python ๅนณๆ›ฟ๏ผŒไธบ AI Agent ่€Œ็”Ÿ ๐Ÿ” Stata / R ๅนณๆ›ฟ๏ผšreghdfeใ€csdidใ€rdrobustใ€synthใ€fixestใ€did ็ญ‰ๅธธ็”จๅ‘ฝไปคๅœจ Python ไธญไธ€็ซ™ๅผๆ›ฟไปฃ๏ผŒไธ€ไธช import statspai as sp ๆžๅฎš DID / RD / IV / SCM / DML / matching ๐Ÿค– ้ขๅ‘ Agent ่ฎพ่ฎก๏ผš็ป“ๆž„ๅŒ–็ป“ๆžœๅฏน่ฑก + ๅ†…็ฝฎ MCP Server๏ผŒClaude / Codex

4.9k200 skills
Get the whole plugin

Stars on GitHub

Momentum

stars in total
4.9k
Star history of brycewang-stanford/Auto-Empirical-Research-Skills on GitHub, a chart by star-history.com

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, andโ€ฆ

n8n2w209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also coversโ€ฆ

@browser-use@browser-useInstall Skill
agent-browser

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, fillingโ€ฆ

@vercel-labs-2@vercel-labs-2Install Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use whenโ€ฆ

@nanocoai@nanocoaiInstall Skill

Questions about hud.

Which coding agents can use hud?
hud installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.