Related Skills

Use the focused analysis skill before building the report when the report depends on market sizing, metric diagnostics, KPI reporting, product/business analysis, data-quality checks, or validation.

Report Building

Use this skill when the user needs a durable analytical report rather than a dashboard, notebook-only dump, or transient chat summary. The report owns the reader-facing narrative, audience shape, evidence placement, visual/table placement, caveats, source metadata, and handoff. The underlying analysis should still come from the appropriate analysis, notebook, data quality, diagnostics, KPI, or product-analysis workflow.

If this skill is selected directly or included by a report-mode workflow, the run is incomplete until the selected report surface exists or a concrete blocker is recorded. Do not finalize with chat-only prose, an inline widget, a local URL, or an ad hoc artifact that skips the report shape. Treat inline summaries and notebook outputs as progress evidence, not as substitutes for the report. Once this skill is selected, reserve charts, tables, and previews for the selected report surface. A user can explicitly waive report creation by requesting an inline, chat-only, brief/no-artifact answer, asking for no report/file/artifact, or selecting another primary artifact. Do not infer a waiver from the absence of the word "report" or from a direct diagnostic, recommendation, sizing, or readout question.

Skill Configuration

Choose exactly one report delivery mode for each run:

• Work Mode on any surface: automatically use sites-app for durable reports when the full Sites create, checkpoint, and deployment lifecycle is callable. Do not ask for another delivery choice or publish confirmation. Build and validate the canonical MCP artifact payload without visibly rendering it, then export and deploy it through Sites. Automatically switch to html when Sites is unavailable, publishing fails, or the user explicitly declines Sites. MCP servers and other callable tools remain valid evidence sources.
• ChatGPT Desktop outside Work Mode: use mcp-app by default. After a successful final MCP report handoff, offer Sites as an optional coworker-sharing follow-up; do not publish unless the user explicitly requests or accepts it.
• ChatGPT web Chat mode after the user explicitly overrides the Work Mode recommendation: use html. Do not automatically publish to Sites or select mcp-app in this branch.
• Any other runtime where MCP app report rendering is unavailable: use html.
• Unknown or unclassified runtime: default to portable html rather than omitting the report.