ads-report is the reporting step of the Claude Ads toolkit. It takes a validated, versioned JSON run bundle from an earlier audit or plan and renders it as Markdown, HTML or PDF for the audience you name.
Every format comes from the same data and the same templates. Findings, confidence, evidence references, contradictions, missing inputs, actions, owners and measurement windows carry through, and a partial or low-evidence run is never hidden in the executive summary.
What You Get
- A Markdown, HTML or PDF report built from one validated run bundle
- Findings with confidence, evidence references, contradictions and missing inputs preserved
- Actions with owners and measurement windows
- An executive summary that states partial or insufficient-evidence status
- A report written inside the run directory with its manifest updated
Common Use Cases
- Sending an agency client the PDF of a finished paid media audit
- Producing a short executive version of a plan for a budget owner
- Re-exporting an earlier audit in a different format
- Handing a Markdown version of the results to a teammate
What Makes It Unique
It refuses loose worker prose and renders only from a validated bundle, so the report cannot say more than the audit proved. All formats share one data source, and the instructions forbid softening partial or low-evidence status in the summary. Credentials, customer lists, private paths, raw research and promotional copy stay out unless branding is enabled.
Under The Hood
The skill is a short set of instructions with no scripts of its own. The agent reads the run bundle from the run directory, runs structural and visual checks on the output, and writes the rendered files atomically inside that directory, updating the run manifest. Rendering and PDF output rely on the surrounding Claude Ads tooling. It writes files but does not call web services or change ad accounts, and it treats account and web content as data.