---
name: audit-orchestrator
description: Audit a website for AI-discoverability and on-site-engagement problems — crawlability, JS-render gaps, missing/invalid structured data, facts locked in non-text, stale or uncorroborated facts, entity ambiguity, weak on-site orientation / no context retention — and produce a report of findings plus prioritized, actionable fixes. Use when diagnosing why a brand is missing or misrepresented in AI assistants, or why visitors who arrive don't engage.
title: audit-orchestrator
canonical_url: https://skilld.dev/gh/tejasshukla2007/brand-ai-readiness-audit/audit-orchestrator
last_updated: 2026-09-22T16:15:22.000Z
---

> **Skill from skilld.dev.** Follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [references/output_schema.json](https://skilld.dev/api/skills-raw/tejasshukla2007/brand-ai-readiness-audit/audit-orchestrator/references/output_schema.json), [scripts/compile_report.py](https://skilld.dev/api/skills-raw/tejasshukla2007/brand-ai-readiness-audit/audit-orchestrator/scripts/compile_report.py).
>
> If the user asked to install this Skill, run `npx skilld install tejasshukla2007/brand-ai-readiness-audit/audit-orchestrator`. Install writes the Skill files into the project, so every session loads them.

# Audit Orchestrator 

## When to use

- Use this skill when you need a complete audit of a brand's visibility in AI assistants.
- Invoke this to get a consolidated report covering both **AI discoverability** (off-site citations) and **on-site engagement**.
- This skill orchestrates the entire audit workflow. It performs core checks directly and can also invoke subordinate skills if they exist in the marketplace.

## Inputs 
- `url`: The target website URL or domain string to evaluate.

## Procedure 

1. Parse the input `url` to ensure it is a valid, reachable target for the audit.
<!--Update the sub-skill list below as new skills are added to the marketplace.-->
2. Invoke each available sub-skill on the `url` and collect their findings arrays.
Registered sub-skills: `freshness-corroboration`, `semantic-structure-audit`, `a11y-extractor-audit`, `context-retention-audit`, `content-quality-audit`.
3. Aggregate all findings from the executed sub-skills into a single, unified list. Deduplicate any overlapping issues.
4. Rank the aggregated findings by severity (`critical`, `high`, `medium`, `low`). Ensure every finding explicitly states the `evidence` and includes a proactive, mechanism-sound `suggested_action`.
5. Execute `python scripts/compile_report.py <url>` to generate the base JSON structure and automatically calculate the summary metrics (`total_findings`, `critical`, `high`, `medium`, `low`) based on the aggregated list.
6. Inject the ranked findings array into the base JSON structure.

## Output

Emit a single JSON report object strictly conforming to the schema defined in `references/output_schema.json`

The final output must be recommend-only. Do not attempt to make any changes to the site.