Ready to supercharge your AI agents?

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

Dashboard Skill — measured AI agent skill | DecimalAI

nexu-io/dashboard

NewSkillScoreMaintained

Admin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin", "analytics", or "control panel" screen.

by nexu-io

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Frontend / UI pack

decimalai skills pull nexu-io-dashboard

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/nexu-io-dashboard/SKILL.md

Raw file: /s/nexu-io-dashboard/SKILL.md ↗ · machine-readable summary at /s/nexu-io-dashboard.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

No — -14% lift+12% tokens0% turns9% of whole cases pass with skill (2/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-15	✗→✓	▲ Improved	9%	0%
case-17	✗→✓	▲ Improved	9%	0%
case-04	✓→✗	▼ Worse	32%	0%
case-05	✓→✗	▼ Worse	17%	0%
case-06	✓→✗	▼ Worse	83%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

nexu-io / open-design

design-templates/dashboard/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1

Skill contents

SKILL.md

Dashboard Skill

Produce a single-screen admin / analytics dashboard.

Workflow

Read the active DESIGN.md (injected above). Colors, typography, spacing,

component styling all come from it. Do not invent new tokens.

Classify what the dashboard monitors (sales, traffic, usage, incidents,

ops, etc.) from the brief. Generate specific, plausible metric names and values — no "Metric A / Metric B" placeholders.

Lay out the required regions:

Left sidebar (220–260px): brand mark at top, 6–8 nav links with

icons, active state uses the DS accent.

Top bar: page title on the left, search input + user avatar / status

on the right.

Main:
Row 1: 3–4 KPI cards (label + big number + delta vs. prior period).
Row 2: one primary chart (full width or 2/3) — render as an inline SVG

line / bar / area chart drawn from real-looking numbers.

Row 3: one secondary chart or table (recent events, top items, etc.).

Write one self-contained HTML document:

<!doctype html> through </html>, CSS in one inline <style> block.
CSS Grid for the overall layout; Flexbox inside cards.
Semantic HTML: <aside>, <header>, <main>, <section>.
Tag each logical region with data-od-id="slug" for comment mode.

Charts: inline SVG only, no JS libraries. A line chart is ~10 lines of

<polyline> with a subtle area fill. A bar chart is N <rect>s with DS-accent fill. Label axes lightly (muted text, smaller scale).

Self-check:

Every color comes from DESIGN.md tokens.
Accent used at most twice (sidebar active + one chart highlight).
Sidebar + top bar are sticky; main scrolls independently.
Density matches the DS mood — airy DSes get more padding, dense DSes

(trading, crypto) tighten rows.

Output contract

Emit between <artifact> tags:

<artifact identifier="dashboard-slug" type="text/html" title="Dashboard Title">
<!doctype html>
<html>...</html>
</artifact>

One sentence before the artifact, nothing after.

Want to see if nexu-io/dashboard would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.