Ready to supercharge your AI agents?

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

Dashboard Brief Skill · mohitagw15856 | DecimalAI

mohitagw15856/dashboard-brief

SkillScore77Maintained

Convert a business question into a complete dashboard specification. Use when asked to design a dashboard, create a dashboard spec or brief, plan a BI report, or define what charts and metrics a dashboard should include. Produces a structured spec with metrics, dimensions, chart types, filters, and layout guidance.

Databy mohitagw15856

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

Automatic

Data Analyst pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/mohitagw15856-dashboard-brief/SKILL.md

decimalai skills pull mohitagw15856-dashboard-brief --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/mohitagw15856-dashboard-brief/SKILL.md https://app.decimal.ai/s/mohitagw15856-dashboard-brief/SKILL.md

Raw file: /s/mohitagw15856-dashboard-brief/SKILL.md ↗ · machine-readable summary at /s/mohitagw15856-dashboard-brief.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 46d ago

Yes — +64% lift · at higher cost+26% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-32%	0%
case-02	✗→✓	▲ Improved	-27%	0%
case-03	✗→✓	▲ Improved	16%	0%
case-07	✗→✓	▲ Improved	137%	0%
case-13	✗→✓	▲ Improved	29%	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 — 8/3/2026

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

mohitagw15856 / pm-claude-skills

skills/dashboard-brief/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Skill contents

SKILL.md

Dashboard Brief Skill

This skill converts a business question or monitoring need into a complete, implementation-ready dashboard specification. The output gives a data engineer or BI developer everything they need to build without a follow-up meeting.

Required Inputs

Ask the user for these if not provided:

The business question this dashboard should answer (e.g. "How is our activation funnel performing this week?")
Primary audience (exec / product team / operations / customer success / engineering)
Refresh cadence (real-time / hourly / daily / weekly)
Data sources available (e.g. Postgres, BigQuery, Mixpanel, Salesforce, Jira)
BI tool being used (Looker / Metabase / Tableau / Power BI / Grafana / Custom / Unknown)

Output Structure

Dashboard Brief: Dashboard Name]

Business Question: The question this dashboard answers — verbatim from inputs or refined] Audience: Who uses this] Refresh Rate: Real-time / Hourly / Daily / Weekly] Data Sources: List] BI Tool: Tool or Unknown]

Section 1: Key Metrics (KPI Cards)

List the headline numbers that should appear at the top of the dashboard as KPI cards.

| Metric | Definition | Data Source | Comparison | |---|---|---|---| | Metric name] | How it's calculated] | Table/source] | vs. last week / vs. target / MoM] |

Aim for 3–6 KPI cards. More than 6 is noise.

Section 2: Charts & Visualisations

For each chart, specify:

Chart N]: Chart Title]

Chart type: Line / Bar / Stacked bar / Pie / Funnel / Heatmap / Table / Scatter]
Why this chart type: One sentence — why this type suits this data]
X-axis / Rows: Dimension — e.g. Date, User segment, Product]
Y-axis / Values: Metric — e.g. Count of active users, Revenue]
Breakdown/colour: Optional secondary dimension — e.g. by Plan tier, by Channel]
Data source: Table or source]
Filters: Any default filters applied — e.g. "Exclude internal test accounts"]
Key insight to surface: What pattern or signal this chart should help the viewer spot]

Section 3: Filters & Controls

Global filters available to dashboard viewers:

| Filter | Type | Default | Options | |---|---|---|---| | Date range | Date picker | Last 30 days | Custom | | Segment filter] | Dropdown | All | List relevant values] | | Other filter] | Multi-select | All | List relevant values] |

Section 4: Layout Recommendation

Describe the dashboard layout in plain terms:

[ROW 1 — KPI Cards]: [Metric 1] | [Metric 2] | [Metric 3] | [Metric 4]
[ROW 2 — Primary chart, full width]: [Chart name]
[ROW 3 — Two charts side by side]: [Chart A] | [Chart B]
[ROW 4 — Supporting table, full width]: [Table name]

Section 5: Data Requirements

List any data transformations, joins, or derived fields needed:

| Derived Field | Logic | Source Tables | |---|---|---| | Field name] | How it's calculated] | Tables involved] |

Flag any fields that may not exist in current data infrastructure.

Section 6: Access & Ownership

Dashboard owner: Leave for user to fill]
Who can edit: Leave for user to fill]
Who can view: Leave for user to fill]
Review cadence: When should this dashboard be reviewed for relevance?]

Quality Checks

] Every chart has a stated "key insight to surface" — not just "show the data"
] KPI cards are 3–6 (not more)
] Chart types are justified
] Layout follows visual hierarchy (summary → detail)
] Data requirements section flags any missing fields
] Filters are practical and don't require IT to configure

Anti-Patterns

] Do not specify metrics that the available data sources cannot actually support — always validate data availability
] Do not include more than 8–10 primary metrics on a single dashboard — more creates noise, not insight
] Do not skip the primary business question — a dashboard without a north-star question becomes a vanity metrics display
] Do not choose chart types for aesthetic reasons — every chart type must match the data relationship it represents
] Do not leave filter configurations vague — specify exact filter values, not just filter categories

Example Trigger Phrases

"Design a dashboard to track business process]"
"Give me a spec for a team] performance dashboard"
"What should go on a topic] dashboard?"
"Write a dashboard brief for our metric] monitoring"

Illustrative Want to see what mohitagw15856/dashboard-brief would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/14/2026, 15:29 UTC · 22 cases

Lift

+64%

77% vs 14%

Agent turns

1.0 vs 1.0

Tokens

+26%

4,062 vs 3,224.32

fail → pass · 14pass → pass · 3fail → fail · 5

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-04 Write a dbt SQL transformation model for Postgres that aggregates daily active users and retention metrics from raw session event logs.	pass→pass	17,209	15,843	-8%	1	1	0%	3,507	4,456	+27%	0	0	—
case-01 Design a complete dashboard specification for our exec team to answer: 'How is our B2B SaaS retention and net revenue health tracking this quarter?' We use Postgres, Salesforce, and Mixpanel, and our target BI tool is Tableau with daily refreshes. Please output a structured brief that includes top-level summary metrics with comparisons, detailed chart-by-chart specs with axes and target insights, global filter controls, a plain-text wireframe layout, and any required data transformations.	fail→pass	59,947	17,051	-72%	1	1	0%	6,238	4,255	-32%	0	0	—
case-02 Can you write an implementation-ready dashboard spec to help our operations managers answer 'Where are orders experiencing delays in our fulfillment pipeline?' We are using hourly refreshed Postgres database tables and Jira data inside Metabase. The output should outline key headline numbers, individual chart configurations with axes and key patterns to spot, filter controls, visual row layout recommendations, and necessary derived data fields.	fail→pass	24,458	13,570	-45%	1	1	0%	4,673	3,433	-27%	0	0	—
case-03 I need a detailed brief for a real-time engineering monitoring board focused on the question 'How stable are our core API microservices during daily code deployments?' We use Grafana fed by Postgres and Datadog. Provide a brief document formatted with a list of key indicator cards, chart specifications detailing x/y axes and filters, interactive user controls, visual layout grouping, and data requirements for derived fields.	fail→pass	23,628	19,815	-16%	1	1	0%	4,146	4,809	+16%	0	0	—
case-05 Create a Mixpanel event tracking plan JSON schema for our mobile app checkout flow, specifying event names and property types for payment steps.	pass→pass	18,324	15,986	-13%	1	1	0%	3,821	4,302	+13%	0	0	—
case-06 Write a Prometheus alert rule YAML configuration that triggers a high latency alert when API 95th percentile latency exceeds 300ms for 5 minutes.	pass→pass	7,225	6,805	-6%	1	1	0%	1,277	2,453	+92%	0	0	—
case-07 Our risk operations team wants to build a Looker dashboard on top of BigQuery to answer 'Where are payment fraud spikes occurring across our gateways?' We'd like to show 12 top-level KPI numbers up front, and list charts as simple bullet points without explaining chart type choices. Create the specification brief.	fail→pass	9,606	17,358	+81%	1	1	0%	1,819	4,319	+137%	0	0	—
case-08 Design a dashboard brief for our customer support director answering 'Are we meeting our first-response and resolution SLA targets across support tiers?' We use Zendesk and Postgres in Metabase refreshed hourly. I only need chart titles and x/y axes; skip the key insights to surface since our team will figure that out when viewing.	fail→fail	9,027	13,103	+45%	1	1	0%	1,823	3,804	+109%	0	0	—
case-09 Create a dashboard specification brief for our growth marketing team to answer 'Which traffic channels produce the highest checkout conversion rates this month?' Data resides in BigQuery and Mixpanel, built in Power BI with daily updates. We don't need any data requirements section since our ETL pipeline is already clean.	fail→fail	13,591	15,749	+16%	1	1	0%	2,543	4,245	+67%	0	0	—
case-10 We need an executive dashboard specification for our product VP answering 'How effectively are free trial users activating key features before day 14?' Data is in Mixpanel and Postgres, refreshed daily in Metabase. Please dump all metrics into a bulleted text list with no table structure.	fail→fail	14,324	13,596	-5%	1	1	0%	2,982	4,146	+39%	0	0	—
case-11 Draft a dashboard spec for clinic operations managers answering 'Which departments have patient wait times exceeding target thresholds during peak hours?' Source data comes from Postgres refreshed hourly in Tableau. Please provide a detailed spec, but do not bother specifying default values for interactive filters.	fail→fail	16,533	16,825	+2%	1	1	0%	3,200	4,227	+32%	0	0	—
case-12 Write a dashboard brief for supply chain directors to answer 'Which warehouse SKUs are at risk of stockout within the next 14 days?' Source is SAP Postgres database and Snowflake in Looker with daily refreshes. Include 10 top summary cards at the top.	fail→fail	15,401	16,118	+5%	1	1	0%	2,799	4,513	+61%	0	0	—
case-13 Provide a dashboard spec for our iOS/Android engineering leads to answer 'Which app versions and OS builds are experiencing elevated crash rates post-release?' Data sources are Datadog and Sentry in Grafana refreshed in real-time.	fail→pass	18,451	16,586	-10%	1	1	0%	3,673	4,729	+29%	0	0	—
case-14 Write a complete dashboard specification brief for sales ops managers answering 'How is sales pipeline velocity and stage conversion rate moving across enterprise deals this quarter?' Data lives in Salesforce and Postgres, built in Tableau with daily refreshes.	fail→pass	25,120	12,884	-49%	1	1	0%	3,858	3,752	-3%	0	0	—
case-15 Create a dashboard brief for our HR leadership team answering 'What factors correlate with 90-day voluntary employee turnover across regional offices?' We use Workday and Postgres data inside Power BI refreshed weekly.	fail→pass	16,576	14,213	-14%	1	1	0%	2,800	3,949	+41%	0	0	—
case-16 Generate a dashboard specification brief for DevOps leads to answer 'Which cloud resource clusters are driving unplanned AWS spending spikes this month?' Data sources are AWS Cost Explorer and Snowflake in Grafana updated daily.	fail→pass	20,214	13,613	-33%	1	1	0%	3,685	3,425	-7%	0	0	—
case-17 Design an engineering manager dashboard brief answering 'How are cycle time and pull request review turnaround times trending across product pods?' We use Jira and GitHub in Metabase refreshed daily.	fail→pass	15,608	14,572	-7%	1	1	0%	2,732	3,990	+46%	0	0	—
case-18 Draft an executive dashboard brief for our Head of Growth answering 'Which monthly subscriber cohorts exhibit the highest churn rates within 90 days of onboarding?' Data sources are Stripe and BigQuery in Looker refreshed daily.	fail→pass	14,231	18,800	+32%	1	1	0%	2,333	4,976	+113%	0	0	—
case-19 Provide a dashboard specification brief for logistics dispatchers to answer 'Which vehicle delivery fleets are currently underutilized during weekday shifts?' Data sources are Telematics Postgres and Geotab in Metabase refreshed hourly.	fail→pass	19,600	12,380	-37%	1	1	0%	3,507	3,516	+0%	0	0	—
case-20 Create a dashboard specification brief for hotel general managers answering 'How is revenue per available room (RevPAR) and occupancy rate trending across property locations this month?' Data sources are PMS Postgres tables in Power BI with daily refreshes.	fail→pass	15,815	13,662	-14%	1	1	0%	2,910	3,760	+29%	0	0	—
case-21 Write a dashboard spec for underwriting managers answering 'What is the default rate and approval turnaround time across risk tiers for auto loans issued this quarter?' Data sources are Postgres and credit bureau logs in Tableau refreshed daily.	fail→pass	19,679	20,565	+5%	1	1	0%	3,271	4,865	+49%	0	0	—
case-22 Design a dashboard brief for store operations answering 'Which store locations are experiencing stockouts during weekend promotional events?' Data sources are POS Postgres tables and ERP Snowflake data in Metabase refreshed hourly.	fail→pass	19,701	12,567	-36%	1	1	0%	3,338	3,440	+3%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +64 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 13.6%
Pass rate with the skill: 77.3%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/14/2026, 15:29 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

Design a complete dashboard specification for our exec team to answer: 'How is our B2B SaaS retention and net revenue health tracking this quarter?' We use Postgres, Salesforce, and Mixpanel, and our target BI tool is Tableau with daily refreshes. Please output a structured brief that includes top-level summary metrics with comparisons, detailed chart-by-chart specs with axes and target insights, global filter controls, a plain-text wireframe layout, and any required data transformations.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run77

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+30% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 45 days ago

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