Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Diverga Dashboard · brycewang-stanford | DecimalAI

researchby brycewang-stanford

Diverga Dashboard

brycewang-stanford/diverga

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Diverga Dashboard - Live configuration status and feature overview. 24 specialized agents across 9 categories for social science research. VS methodology prevents mode collapse. Human checkpoints enforce human-in-the-loop decisions. Triggers: /diverga, diverga dashboard, diverga status

SkillScore83Maintained

Automatic

Research pack

Last verified 8/8/2026

What it changes

Passed 16 of 19 test cases with the skill, and 6 of 19 without it.

Without skill30%

With skill83%

Checks it passed that the model alone missed

Lists /diverga:hud for display settings.
Recommends Groq with the model llama-3.3-70b.
Lists /diverga:doctor for system diagnostics.

and 13 more in the full report

14 fixed5 passed either way2 still failing2 broke

Pass-rate lift: +52 pp
Tokens: +39%
Agent turns: 0%
Response time: -58%

Model gemini-3.6-flashMeasured 8/8/2026v119 of 23 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-diverga/SKILL.md https://app.decimal.ai/s/brycewang-stanford-diverga/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-diverga, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-diverga/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-diverga

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-diverga/SKILL.md https://app.decimal.ai/s/brycewang-stanford-diverga/SKILL.md

Raw file: /s/brycewang-stanford-diverga/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-diverga.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

Which quick action command displays project context and state memory in Diverga?

What was checked, without and with the skill
Checked	Without skill	With skill
Lists /diverga:memory for project context state.	Missed	Passed

case-15 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md143 linessingle file

Diverga Dashboard

When the user runs /diverga (the base command), display a live configuration dashboard.

Instructions

Display the following dashboard by reading live configuration and environment state. Use plain text output (no tool calls needed for display — just output the text directly).

Step 1: Display ASCII Logo

Output this exact logo block:

╔═══════════════════════════════════════════════════════════════════════════════╗
║                                                                               ║
║             ██████╗ ██╗██╗   ██╗███████╗██████╗  ██████╗  █████╗              ║
║             ██╔══██╗██║██║   ██║██╔════╝██╔══██╗██╔════╝ ██╔══██╗             ║
║             ██║  ██║██║██║   ██║█████╗  ██████╔╝██║  ███╗███████║             ║
║             ██║  ██║██║╚██╗ ██╔╝██╔══╝  ██╔══██╗██║   ██║██╔══██║             ║
║             ██████╔╝██║ ╚████╔╝ ███████╗██║  ██║╚██████╔╝██║  ██║             ║
║             ╚═════╝ ╚═╝  ╚═══╝  ╚══════╝╚═╝  ╚═╝ ╚═════╝ ╚═╝  ╚═╝             ║
║                                                                               ║
║              * Diverge from the Modal · Discover the Exceptional              ║
║                                                                               ║
╚═══════════════════════════════════════════════════════════════════════════════╝

Step 2: Read Configuration

Read config/diverga-config.json (relative to the plugin directory at ~/.claude/plugins/diverga/config/diverga-config.json). Extract:

human_checkpoints.level or infer from human_checkpoints.enabled + human_checkpoints.required
hud.preset if present
language
version

If config file doesn't exist, show "Not configured — run /diverga:setup"

Step 3: Check Project Status

Check if .research/project-state.yaml exists in the current working directory.

Track record

Benchmark

16 / 19

test cases passed, vs 6 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / Auto-Empirical-Research-Skills

skills/25-HosungYou-Diverga/skills/diverga/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Diverga Dashboard

Instructions

Step 1: Display ASCII Logo

Step 2: Read Configuration

Step 3: Check Project Status

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills