Skip to content
SkillModel-led171 tokens in use

ads-report

Turns a validated Claude Ads run bundle into Markdown, HTML or PDF reports for clients and executives, keeping evidence, gaps and partial status visible.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-report
/plugin marketplace add agricidaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ads-report costs

46tokens idle
171tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure12/25
  • Examples0/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers