Audit

Skill produtoramaxvision/maxvision-utilities/media-forge/skills/audit

MaxVision's curated Claude Code marketplace — production-grade skills for n8n workflows, Google Tag Manager API, and more.

Install

npx -y skills add produtoramaxvision/maxvision-utilities --skill audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Audit a job's lineage: read metadata, trace, lineage, verdicts. Triggers: audit, lineage, verdict, history.

SKILL.md

1.1 KB, as published. Nobody here has run it

media-forge:audit

Job audit and lineage skill. Reads all metadata for a given job ID: trace entries, lineage chain, quality verdicts, cost breakdown, and model call log.

Workflow

Receive job ID from $ARGUMENTS.
Locate job dir at $CLAUDE_PROJECT_DIR/.media-forge/jobs/<jobId>/.
Read trace.jsonl, lineage.json, refined_spec.json, and all verdict JSONs.
Summarize: agent chain, model calls, retry count, final verdict, total cost.
Display structured audit report to user.

When to use

Invoke when user wants to inspect what happened in a previous generation job: which agents ran, what the quality scores were, how many retries occurred, and the total cost.

Outputs

Agent chain (ordered list of agents dispatched)
Prompt evolution (initial brief → refined spec)
Quality verdicts per attempt
Retry count and root causes
Total cost in USD
Asset paths