Index365 read report
Use when the user wants to see the results of an index365 scan without changing code. Triggers: "show my score", "what's wrong with my site", "read the audit report", "list the findings", "what did the audit find", "show the marketing signal report". Read-only: it reads and explains, it does not fix. To fix, use index365-apply-fix or index365-audit-and-fix.From its SKILL.md
npx -y skills add index365usa/agent-skills --skill index365-read-reportAssembled 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
2.3 KB, as published. Nobody here has run it
index365 read report
Read a scan's score and findings, and explain them. Read-only, and no ids needed:
every command defaults to the latest completed run and echoes what it resolved
(yoursite.com · scanned 2m ago). A domain narrows to that site's latest run.
Score first
index365 report
On a terminal this renders the score card; piped or with --json it prints the
compact agent-ready JSON context (score, severity counts, top findings, exec
summary). That JSON is bounded by construction, so it is safe to read directly.
Then findings
index365 findings # table from the latest run
index365 findings get 1 # first finding in full, plus a fix prompt
Filter the table with --severity critical (then high) or
--marketing-category <c> (seo, content, aeo, analytics_tracking,
conversion, trust_proof). --stage <s> still filters legacy runs completed
before the category model; it matches nothing on a current run. findings get <n> takes the ordinal straight from the
table; each finding also has a stable findingId that stays constant across
re-reads, which is what you match on when comparing runs.
Large reports: save, then read selectively
Only when you need every finding at once (full triage, cross-run diffing), save the
full report to the git-ignored .index365/ dir and read it with jq / grep:
index365 report --save # writes the full report into .index365/ by default
Never paste a whole saved report into context. Summarize the score, the severity counts, and the top findings.
History
index365 results lists your scans newest first; index365 results yoursite.com is
that site's score over time, the fastest way to show whether a fix moved the number.
Next
To act on the findings: index365-triage-findings (plan), index365-apply-fix (one fix), or index365-audit-and-fix (the full loop).
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most docs writing skills give
Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06
- Use third-person for skill descriptionsin 54 of 1951, across 35 files
- Start descriptions with Use whenin 43 of 1951, across 29 files
- Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
- Use active voicein 40 of 1951, across 36 files
- Map file responsibilities before defining tasksin 36 of 1951, across 29 files
- Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
- Ask one question at a timein 35 of 1951
- Offer execution options after saving the planin 33 of 1951, across 24 files
- Include complete code in every stepin 33 of 1951, across 27 files
- Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
- Announce the skill usage at the startin 30 of 1951
- Verify agent compliance after adding the skillin 29 of 1951, across 17 files
Said here and by no other author read
- Run index365 report to view score
- Run index365 findings to list issues
- Use findings get to view specific details
- Use index365 results to show history
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.