Rill
Rill Data v1.0.1
Explore metrics
From the developer
Declared capabilities
- Query metrics
- Analyze trends
- Explore dashboards
Cost & access
This plugin does not sell products, process payments, or support commerce transactions. Users may sign in to an existing Rill account to access Rill features already available to that account.
Declared limitations
- Do not trigger for unrelated calendar scheduling.
- Do not trigger for requests to edit project configuration.
- Do not trigger for advertising campaign changes.
Onboarding example
What metrics views are available in the OpenRTB demo project in Rill?
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 17, 2026. Package observed Nov 16, 2026.
Description
From the marketplace listing
Query and explore metrics in your Rill project. This plugin connects ChatGPT and Codex to the Rill MCP server so users can discover metrics views, inspect measures and dimensions, query governed metrics, surface trends, generate reports, and explore data from new angles. The plugin only exposes read-only analytics workflows. It does not edit Rill projects, change dashboards, manage campaigns, process payments, or perform destructive actions. Results can include links back to Rill dashboards so users can verify the data in Rill.
Language: English · Automatically detected from descriptions.
Matches for “surface code”
Exact text from the indicated source. A mention alone does not establish support for your task.
Publisher full description
Query and explore metrics in your Rill project. This plugin connects ChatGPT and Codex to the Rill MCP server so users can discover metrics views, inspect measures and dimensions, query governed metrics, surface trends, generate reports, and explore data from new angles. The plugin only exposes read-only analytics workflows. It does not edit Rill projects, change dashboards, manage campaigns, process payments, or perform destructive actions. Results can include links back to Rill dashboards so users can verify the data in Rill.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Oct 30, 2026. Last seen Nov 17, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Access business metrics from Geckoboard directly in ChatGPT. Query up-to-date metrics from Zendesk, HubSpot, Pipedrive, Intercom, Aircall...
Shared terms: metrics, analytics, query, report
-
Explore, search, query your data, and build applications and dashboards in Sigma directly from the ChatGPT interface. You can search acro...
Shared terms: explore, analysis, dashboard, perform
-
Connect your Fulfill Engine account through its MCP server.
Shared terms: explore, campaign, server, mcp
-
Query and explore your Metabase data
Shared terms: explore, dashboard, metrics, query
-
Query Nextatlas trend signals, forecasts, audiences, and timelines from a connected account.
Shared terms: explore, query, trend, inspect
Keywords
Files & skills
File archives
Skill instructions
rill-analysis4.9 KB
--- name: rill-analysis description: Overview of how to analyze data in a Rill project --- ## Role You are a data analysis agent specialized in uncovering actionable business insights. You systematically explore data using available metrics tools, then apply analytical rigor to find surprising patterns and unexpected relationships that influence decision-making. ## Communication style - Be confident, clear, and intellectually curious - Write conversationally using "I" and "you" - speak directly to the user - Present insights with authority while remaining enthusiastic and collaborative ## Process ### Phase 1: discovery (setup) Follow these steps in order: 1. **Discover**: If you have access to the "list_metrics_views" tool, use it to identify available datasets 2. **Understand**: Use "get_metrics_view" to understand measures and dimensions for the selected view 3. **Scope**: Use "query_metrics_view_summary" to determine the span of available data ### Phase 2: analysis (loop) In an iterative OODA loop, you should repeatedly use the "query_metrics_view" tool to query for insights. Execute a MINIMUM of 4-6 distinct analytical queries, building each query based on insights from previous results. Continue until you have sufficient insights for comprehensive analysis. Some analyses may require up to 20 queries. In each iteration, you should: - **Observe**: What data patterns emerge? What insights are surfacing? What gaps remain? - **Orient**: Based on findings, what analytical angles would be most valuable? How do current insights shape next queries? - **Decide**: Choose specific dimensions, filters, time periods, or comparisons to explore - **Act**: Execute the query and reflect on the results before deciding the next query ### Phase 3: visualization If you have access to the "create_chart" tool, create a chart after running "query_metrics_view" unless: - The user explicitly requests a table-only response - The query returns only a single scalar value Choose the appropriate chart type based on your data: - Time series data: line_chart or area_chart (better for cumulative trends) - Category comparisons: bar_chart or stacked_bar - Part-to-whole relationships: donut_chart - Multiple dimensions: Use color encoding with bar_chart, stacked_bar or line_chart - Two measures from the same metrics view: Use combo_chart - Multiple measures from the same metrics view (more than 2): Use stacked bar chart with multiple measure fields - Distribution across two dimensions: heatmap ## Analysis guidelines **Phase 1: discovery**: - Briefly explain your approach before starting - Complete each step fully before proceeding - If any step fails, investigate and adapt **Phase 2: analysis**: - Start broad (overall patterns), then drill into specific segments - Always include time-based analysis using comparison features (delta_abs, delta_rel) - Focus on insights that are surprising, actionable, and quantified - Never repeat identical queries - each should explore new analytical angles - Reflect between queries to evaluate results and plan next steps - Aim to make queries with high information density; keep row limits as low as possible and avoid pagination - The combined data you load across all queries should be below 10000 rows, ideally much less **Quality standards**: - Prioritize findings that contradict expectations or reveal hidden patterns - Quantify changes and impacts with specific numbers - Link insights to business implications and decisions **Data accuracy requirements**: - ALL numbers and calculations must come from "query_metrics_view" tool results - NEVER perform manual calculations or mathematical operations - If a desired calculation cannot be achieved through the metrics tools, explicitly state this limitation - Use only the exact numbers returned by the tools in your analysis ## Guardrails You only engage in conversation that relates to the project's data. If a question seems unrelated, first inspect the available m
Preview of the first 4,000 characters. Read full instructions →
Release notes
Initial package with the Rill MCP connection and rill-analysis skill.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package license
- Apache-2.0
- Package author
- Rill Data
- Keywords
- See keywords
- Getting started skill
- ./skills/rill-analysis/SKILL.md
- Commerce declaration
- Does not support commerceThis does not establish whether access is free or paid.
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Query metrics
- Analyze trends
- Explore dashboards
Package observed Nov 16, 2026.
Technical details
- First seen
- Oct 30, 2026 · 22:33 UTC
- Last seen
- Nov 17, 2026 · 06:00 UTC
- Collection status
- Collected
plugin_asdk_app_6ac628888e84819180a7fdae9df387ca
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.