agentsclimarketplace

Index365 run audit

Skill index365usa/agent-skills/skills/index365-run-audit

Use when the user wants to run or re-run an index365 scan. Triggers: "run an audit", "scan my site", "check my score", "re-run the audit", "run a marketing signal audit", "audit yoursite.com again". Covers the Marketing Signal scan and async runs. A scan is a paid action, see below.From its SKILL.md

Install
npx -y skills add index365usa/agent-skills --skill index365-run-audit

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

One thing to look at

  • 1 stars1 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.

SKILL.md

2.4 KB, as published. Nobody here has run it

index365 run audit

One command. scan resolves the project from the domain, waits, and prints the score card.

index365 scan https://yoursite.com --yes
  • There is one product, so there is nothing to choose. Marketing Signal is the default and the only startable product. Do not pass a legacy --product value to start a run: the API rejects it with 400 legacy_product_not_creatable. Completed legacy runs stay readable, so report and findings can still open them.
  • Waiting is the default. The command blocks until the score lands and renders the score card plus top findings. No polling, no ids to track.
  • --yes is for agents and CI. A new domain normally asks one [Y/n] before creating the project and spending credits; --yes answers it. Non-interactive shells never prompt: without --yes a new domain exits 2 with the --yes command in the next: hint.
  • A scan spends one Page Check (10 credits). To make a retry safe (network blip, agent re-entry), pass a stable --idempotency-key; a repeat with the same key returns the same run instead of double-spending.

Async (CI, long queues)

index365 scan yoursite.com --yes --no-wait   # queue it
index365 check                               # is it done yet?

check with no argument checks your most recent scan; check yoursite.com checks that site's. When it completes, index365 report and index365 findings read it with no ids.

Local pre-deploy scan is retired

index365 scan local is retired: submitted HTML cannot verify the registered page, so the result could not be trusted. Run a live scan against the deployed URL instead. Do not offer a local pre-deploy gate.

After the scan

The score card already answers "what's my score". For findings, hand off to index365-read-report; to compare against previous scans, index365 results yoursite.com shows that site's score over time. A --json scan response carries a resolved block naming the run it created, but downstream commands do not need it: they default to the latest run.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most audit compliance skills give

Counted across 960 of the 1,589 authors here whose files we hold, read 2026-09-06

  • Read product marketing context before asking questionsin 29 of 960, across 11 files
  • Rank findings by severityin 29 of 960, across 22 files
  • Generate audit reportin 22 of 960
  • Run the audit scriptin 20 of 960, across 19 files
  • Generate a prioritized action plan reportin 19 of 960, across 11 files
  • Ensure one H1 per pagein 15 of 960, across 5 files
  • Ensure sitemap exists and is accessiblein 14 of 960, across 4 files
  • Verify alt text on all imagesin 12 of 960, across 3 files
  • Determine the audit scope before startingin 12 of 960, across 4 files
  • Verify important pages allowed in robots.txtin 11 of 960, across 2 files
  • Detect business type from homepage signalsin 11 of 960, across 7 files
  • Delegate specialized tasks to subagentsin 11 of 960, across 7 files

Said here and by no other author read

  • Run the scan command with the domain
  • Pass the yes flag for non-interactive shells
  • Pass a stable idempotency key for retries
  • Use check to see if an async scan is done
  • Run a live scan against the deployed URL

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 613,297. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.