Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
18 changes: 3 additions & 15 deletions .agents/plugins/marketplace.json
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
"installation": "AVAILABLE",
"authentication": "ON_USE"
},
"category": "Business"
"category": "Business & Operations"
},
{
"name": "data-analytics",
Expand All @@ -26,7 +26,7 @@
"installation": "AVAILABLE",
"authentication": "ON_USE"
},
"category": "Analytics"
"category": "Data & Analytics"
},
{
"name": "product-design",
Expand All @@ -38,19 +38,7 @@
"installation": "AVAILABLE",
"authentication": "ON_USE"
},
"category": "Design"
},
{
"name": "financial-markets",
"source": {
"source": "local",
"path": "./plugins/financial-markets"
},
"policy": {
"installation": "AVAILABLE",
"authentication": "ON_USE"
},
"category": "Business"
"category": "Creativity"
}
]
}
9 changes: 3 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,8 @@

Role-specific plugins make Codex easier to customize for a team's day-to-day work.
These templates package domain-specific skills, connector bindings, and starter
assets so teams can adapt Codex for roles like sales, data analytics, product
design, and financial markets. They were built with OpenAI subject matter
assets so teams can adapt Codex for roles like sales, data analytics, and
product design. They were built with OpenAI subject matter
experts around workflows that are already helping teams move faster internally
and with alpha partners. Over the coming weeks, we'll continue expanding this
collection with more roles, workflows, and examples.
Expand All @@ -19,7 +19,6 @@ available to the target workspace.
| [Sales](./plugins/sales) | Prepare for meetings, follow up after calls, review pipeline, find account context, and build deal plans. | Salesforce, HubSpot, Slack, Google Drive, Gmail, Outlook, Outreach, Clay, ZoomInfo, and other sales tools |
| [Data Analytics](./plugins/data-analytics) | Query, visualize, explain, and validate datasets; build dashboards; and investigate metrics. | Databricks, Snowflake, BigQuery, Hex, Amplitude, Mixpanel, Statsig, Metabase, ThoughtSpot, Google Drive, Slack, Microsoft 365, and more |
| [Product Design](./plugins/product-design) | Create product specs, prototypes, UI critiques, and product design artifacts. | Sites |
| [Financial Markets](./plugins/financial-markets) | Build public-equity research, earnings analysis, valuation work, model updates, long/short pitches, risk reviews, dashboards, and investment memos. | FactSet, LSEG, Morningstar, Daloopa, Quartr, S&P, PitchBook, Slack, Google Drive, Gmail, SharePoint, Teams, and more |

## Repository Layout

Expand All @@ -29,8 +28,7 @@ available to the target workspace.
`-- plugins/
|-- sales/
|-- data-analytics/
|-- product-design/
`-- financial-markets/
`-- product-design/
```

Each plugin generally follows this structure:
Expand Down Expand Up @@ -66,7 +64,6 @@ matching app or connector id available to your workspace.
| Placeholder | Replace with |
| --- | --- |
| `REPLACE_WITH_SALESFORCE_APP_OR_CONNECTOR_ID` | Salesforce or Agentforce Sales |
| `REPLACE_WITH_SITES_APP_OR_CONNECTOR_ID` | Sites |

Canonical shared platform connector ids and existing `templated_apps_*` template
registry ids are portable bindings and should be left unchanged. Do not copy
Expand Down
44 changes: 37 additions & 7 deletions plugins/data-analytics/.app.json
Original file line number Diff line number Diff line change
@@ -1,83 +1,113 @@
{
"apps": {
"slack": {
"id": "REPLACE_WITH_SLACK_APP_OR_CONNECTOR_ID"
"id": "REPLACE_WITH_SLACK_APP_OR_CONNECTOR_ID",
"category": "Team communication",
"optional": true
},
"teams": {
"id": "connector_246af0940da3457da0e751171dc1ce60",
"category": "Team communication",
"optional": true
},
"notion": {
"id": "REPLACE_WITH_NOTION_APP_OR_CONNECTOR_ID"
"id": "REPLACE_WITH_NOTION_APP_OR_CONNECTOR_ID",
"category": "Company docs",
"optional": true
},
"gmail": {
"id": "connector_2128aebfecb84f64a069897515042a44",
"category": "Email context",
"optional": true
},
"outlook_email": {
"id": "connector_4aaab2856305417b993eca9a216aaf6e",
"category": "Email context",
"optional": true
},
"outlook_calendar": {
"id": "connector_e6a7394682e24467ac68c60696f275a4",
"category": "Calendar context",
"optional": true
},
"google_calendar": {
"id": "connector_947e0d954944416db111db556030eea6",
"category": "Calendar context",
"optional": true
},
"google_drive": {
"id": "connector_5f3c8c41a1e54ad7a76272c89e2554fa"
"id": "connector_5f3c8c41a1e54ad7a76272c89e2554fa",
"category": "Company docs",
"optional": true
},
"databricks": {
"id": "templated_apps_Databricks",
"category": "Data warehouse",
"optional": true
},
"bigquery": {
"id": "connector_7c3f2c8cdbf64bb0b183ff52f527a06e",
"category": "Data warehouse",
"optional": true
},
"snowflake": {
"id": "templated_apps_Snowflake",
"category": "Data warehouse",
"optional": true
},
"sharepoint": {
"id": "connector_1e4f6a44acf14e3ca1d96672f8c945bc",
"category": "Company docs",
"optional": true
},
"github": {
"id": "connector_76869538009648d5b282a4bb21c3d157"
"id": "connector_76869538009648d5b282a4bb21c3d157",
"category": "Code repository",
"optional": true
},
"statsig": {
"id": "REPLACE_WITH_STATSIG_APP_OR_CONNECTOR_ID",
"category": "Behavior signals",
"optional": true
},
"hex": {
"id": "REPLACE_WITH_HEX_APP_OR_CONNECTOR_ID",
"id": "connector_690a9430a270819196671dcb4c95898e",
"category": "Notebook lab",
"optional": true
},
"deepnote": {
"id": "REPLACE_WITH_DEEPNOTE_APP_OR_CONNECTOR_ID",
"category": "Notebook lab",
"optional": true
},
"amplitude": {
"id": "REPLACE_WITH_AMPLITUDE_APP_OR_CONNECTOR_ID",
"id": "connector_690e2dabf430819196f8b3701ec838ec",
"category": "Behavior signals",
"optional": true
},
"mixpanel": {
"id": "REPLACE_WITH_MIXPANEL_APP_OR_CONNECTOR_ID",
"category": "Behavior signals",
"optional": true
},
"posthog": {
"id": "REPLACE_WITH_POSTHOG_APP_OR_CONNECTOR_ID",
"category": "Behavior signals",
"optional": true
},
"omni-analytics": {
"id": "REPLACE_WITH_OMNI_ANALYTICS_APP_OR_CONNECTOR_ID",
"category": "Dashboards and BI",
"optional": true
},
"metabase": {
"id": "templated_apps_Metabase",
"id": "templated_apps_6a044bbb47ec819193270b902fa5cd03",
"category": "Dashboards and BI",
"optional": true
},
"thoughtspot": {
"id": "REPLACE_WITH_THOUGHTSPOT_APP_OR_CONNECTOR_ID",
"category": "Dashboards and BI",
"optional": true
}
}
Expand Down
18 changes: 10 additions & 8 deletions plugins/data-analytics/.codex-plugin/plugin.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"name": "data-analytics",
"version": "0.1.34",
"description": "Analyze product usage, investigate metric movements, prepare KPI reports, build high-quality dashboards and notebooks, create source-backed semantic layers, guide first-run analytics setup, and generate analytics-grade report apps.",
"version": "0.2.6",
"description": "Answer product and business questions with data",
"author": {
"name": "Data Analytics Maintainers"
},
Expand All @@ -11,6 +11,8 @@
"keywords": [
"data-analytics",
"analytics",
"business intelligence",
"sql",
"business-context",
"dashboards",
"funnel-analysis",
Expand All @@ -33,18 +35,18 @@
"mixpanel-headless",
"metabase",
"thoughtspot",
"onboarding",
"guided-flow",
"semantic-layer"
],
"skills": "./skills/",
"apps": "./.app.json",
"mcpServers": "./.mcp.json",
"interface": {
"displayName": "Data Analytics",
"shortDescription": "Turn data into clear decisions",
"longDescription": "Turn analytical questions into validated answers, dashboards, reports, notebooks, and clear recommendations. Explore product and business data, explain why key metrics changed, design KPIs, size opportunities, check data quality, and save reusable metric and source context for future work.\n\nStart with connected warehouses, BI tools, product analytics, docs, chat, spreadsheets, or uploaded files. Guided onboarding helps you connect core tools and set up reusable data context, while interactive charts, tables, dashboards, and report apps keep the evidence reviewable and ready to share.",
"shortDescription": "Answer product and business questions with data",
"longDescription": "Data Analytics helps you turn questions about your product or business into answers you can trust. Ask why a metric changed, what the data shows about where a team should focus next, how to define KPIs, whether a dataset is reliable, or how large an opportunity might be, and it can help you investigate the data and turn the findings into shareable reports, charts, dashboards, notebooks, and recommendations.\n\nStart with the data you already have: connected warehouses, BI or product analytics tools, docs, chats, spreadsheets, uploaded files, pasted results, or clearly labeled sample data. The plugin guides you through the right workflow, checks sources where possible, and keeps the evidence visible in reviewable tables, charts, dashboards, and report apps you can share.",
"developerName": "OpenAI",
"category": "Analytics",
"category": "Data & Analytics",
"capabilities": [
"Interactive",
"Read",
Expand All @@ -54,8 +56,8 @@
"privacyPolicyURL": "https://openai.com/policies/privacy-policy/",
"termsOfServiceURL": "https://openai.com/policies/terms-of-use/",
"defaultPrompt": [
"Help me get started and set up reusable data context for future data work",
"Analyze product usage and recommend where the team should focus next",
"Help me get started with my first data task",
"Analyze product or business data and recommend where to focus next",
"Diagnose why a key metric changed and identify the biggest drivers"
],
"brandColor": "#0285FF",
Expand Down
4 changes: 2 additions & 2 deletions plugins/data-analytics/.mcp.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"mcpServers": {
"datascienceWidgets": {
"title": "Data Analytics Widgets",
"dataAnalyticsWidgets": {
"title": "Data Analytics",
"description": "Render Data Analytics charts, tables, dashboards, and report artifacts.",
"icons": [
{
Expand Down
27 changes: 0 additions & 27 deletions plugins/data-analytics/DEPENDENCIES.MD

This file was deleted.

29 changes: 8 additions & 21 deletions plugins/data-analytics/README.md
Original file line number Diff line number Diff line change
@@ -1,30 +1,26 @@
# Data Analytics

Answer product and business questions with data, explain why metrics changed, and turn analysis into reports, dashboards, and clear decisions.
Data Analytics helps you answer product and business questions with data you can trust, then turn the findings into shareable reports, charts, dashboards, notebooks, and recommendations.

## When to use this plugin

Use Data Analytics when you need to understand product or business performance, explain why a metric changed, define a success measurement plan, assess whether data is trustworthy, or package analysis for stakeholders. You can start from connected data in a data warehouse, dashboards, notebooks, spreadsheets, uploaded files, or pasted context.
Use Data Analytics when a product or business decision depends on metric-backed evidence: understanding performance, explaining a metric movement, deciding where to focus, defining KPIs, checking whether data is reliable, or sizing an opportunity. Start with connected warehouses, BI or product analytics tools, docs, chats, spreadsheets, uploaded files, pasted results, or clearly labeled sample data.

## Onboarding
## Get started

Ask Codex:
Try asking:

`@Data Analytics Help me get started and set up reusable data context for future data work`
`@Data Analytics Help me get started with my first data task`

Data Analytics has a guided onboarding flow that helps confirm the right data sources, save reusable metric and source-of-truth context you provide, and build a context-specific first analysis prompt.

Onboarding is an interactive, step-by-step conversation. Codex will guide you through setup, ask for approval before making changes, and help you try a first workflow.
The plugin will help you choose a data source, pick a useful workflow, and decide whether to use connected tools, upload data, paste results, or try sample data.

Already have a focused task? Start directly with one of the workflows below.

## Example workflows

The primary hero workflow is bolded.

| Workflow | Try this | Skill | Result |
| --- | --- | --- | --- |
| **Analyze a product or business question** | `Analyze activation and recommend where the team should focus next` | `product-business-analysis` | A decision-ready analysis with evidence, measurable opportunities, and a clear recommendation |
| Analyze a product or business question | `Analyze activation and recommend where to focus next` | `product-business-analysis` | A decision-ready analysis with evidence, measurable opportunities, and a clear recommendation |
| Diagnose a metric movement | `Diagnose why weekly active users dropped last week` | `metric-diagnostics` | A calibrated explanation of verified drivers, likely contributors, unresolved questions, and next actions |
| Design KPIs | `Design a KPI framework for this new product area` | `design-kpis` | A measurement plan with outcome metrics, drivers, guardrails, targets, and validation priorities |
| Prepare a KPI readout | `Turn this month's metrics into a leadership-ready operating update` | `kpi-reporting` | A concise KPI update with actuals, comparisons, validated drivers, and operating implications |
Expand All @@ -33,7 +29,6 @@ The primary hero workflow is bolded.
| Build an analytical report | `Create an executive report explaining the biggest growth drivers this quarter` | `build-report` | A polished report with answer-first narrative, charts, tables, caveats, and source metadata |
| Improve or render a chart | `Turn this analysis into a clear chart for the product review` | `visualize-data` | A production-ready visual with the right chart type, labels, hierarchy, and accessibility checks |
| Create a notebook | `Build a reproducible notebook for this experiment readout` | `jupyter-notebooks` | A clean SQL or Python notebook that can be skimmed, rerun, and extended |
| Work with spreadsheets | `Analyze this workbook and add a polished summary tab` | `spreadsheets` | A verified spreadsheet artifact with formulas, formatting, charts, tables, and a clear readout |
| Validate an analysis | `Review this analysis before I share it with leadership` | `validate-data` | A QA pass covering methodology, sources, calculations, analytical pitfalls, caveats, and conclusion strength |
| Assess data quality | `Check whether this table is reliable enough for our retention analysis` | `analyze-data-quality` | A source-backed quality assessment covering grain, freshness, missingness, duplicates, joins, and material risks |

Expand All @@ -44,17 +39,9 @@ Data Analytics can use available tools when they are connected:
| Source | Supported integrations | What they unlock |
| --- | --- | --- |
| Warehouses and query tools | Databricks, Databricks Genie, BigQuery, Snowflake | Schema inspection, query-backed analysis, and source-grounded metric investigation |
| Product analytics and BI | Amplitude, Mixpanel, Omni Analytics, Metabase, ThoughtSpot, Statsig | Behavior analysis, dashboard context, experiment evidence, and reusable reporting inputs |
| Product analytics and BI | Amplitude, Mixpanel, PostHog, Omni Analytics, Metabase, ThoughtSpot, Statsig | Behavior analysis, dashboard context, experiment evidence, and reusable reporting inputs |
| Notebooks and analytical workspaces | Hex, Deepnote | Reproducible analysis, notebook handoff, and shared analytical context |
| Docs and collaboration | Google Drive, SharePoint, Notion, GitHub, Slack, Microsoft Teams | Business definitions, source-of-truth documents, implementation context, and stakeholder evidence |
| Email and calendar | Gmail, Outlook Email, Outlook Calendar | Supporting context for stakeholder questions, operating cadence, and analytical handoff |

You can also start with spreadsheets, uploaded files, pasted query results, schema descriptions, or manually provided business context.

## Local development

The published plugin does not require users to install Node.js dependencies. For local development of the Data Analytics MCP server and widgets, install dependencies from the plugin directory:

```sh
npm ci
```

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Large diffs are not rendered by default.

Loading