How do I install the Index365 Run Audit skill?

Run npx skillmds@latest add index365usa/index365-run-audit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Index365 Run Audit safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Index365 Run Audit?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Index365 Run Audit free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Index365 Run Audit?

index365usa (@index365usa) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Index365 Run Audit by index365usa — Agent Skill

Name: Index365 Run Audit
Author: index365usa

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.

index365usa Updated Sep 17, 2026

File contents

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.

---name: index365-run-auditdescription: 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.---# index365 run auditOne command. `scan` resolves the project from the domain, waits, and prints thescore card.```bashindex365 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)```bashindex365 scan yoursite.com --yes --no-wait # queue itindex365 check # is it done yet?````check` with no argument checks your most recent scan; `check yoursite.com` checksthat site's. When it completes, `index365 report` and `index365 findings` read itwith 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 URLinstead. Do not offer a local pre-deploy gate.## After the scanThe 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` scanresponse carries a `resolved` block naming the run it created, but downstreamcommands do not need it: they default to the latest run.

Frequently asked questions