Index365
Use when the user mentions index365, has an i365_ API key, or wants to audit a website for how well AI agents and AI search can read it (AI-Readiness) or whether demand can find, trust, act on, and measure the site (Marketing Signal). Triggers: "is my site AI-ready", "audit my site", "check my AI visibility", "run an index365 audit", "what's my score", "fix what index365 found", or a pasted index365 finding / "copy fix prompt for your agent" button. This is the router: it picks the right index365 sub-skill. Do NOT trigger for unrelated SEO tools, generic web scraping, or local-file tasks.From its SKILL.md
npx -y skills add index365usa/agent-skills --skill index365Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things 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.
- runs commandsInstructs the agent to run 7 commands, including `index365 runs start` and 6 more.
SKILL.md
3.2 KB, 653 tokens by cl100k_base, as published. Nobody here has run it
index365
index365 audits a website and returns a score plus findings
with stable IDs, evidence, and machine-readable remediation. Everything the dashboard
does is also available to your agent over the public /api/v1, wrapped by the
@index365/cli and @index365/mcp packages. These skills wrap the CLI; the CLI wraps
the API. The API holds all the logic, so the skills stay thin and never go stale.
The two audits
| Audit | Answers | Run with |
|---|---|---|
| AI-Readiness | Can AI agents and AI search read, understand, and act on this site? | index365 runs start |
| Marketing Signal | Can demand find the site, trust the offer, act, and be measured? | index365 marketing run |
Each run produces a 0–100 score and findings. Findings carry a stable findingId,
severity, category (AI-Readiness) or stage (Marketing Signal: Find / Trust /
Act / Measure / Improve), affectedUrls, human remediation, and machine-readable
agentActions.
The ladder (route to the sub-skill)
| The user wants to… | Skill |
|---|---|
First-time setup, a 401, "connect index365", doctor fails | index365-setup |
| Add a site / "start auditing example.com" | index365-add-project |
| Run or re-run an audit | index365-run-audit |
| See the score / read findings / "what's wrong" | index365-read-report |
| Prioritize / "what do I fix first" | index365-triage-findings |
Fix one finding (a pasted findingId, the copy-prompt button) | index365-apply-fix |
| "Make my site AI-ready", audit AND fix the whole thing | index365-audit-and-fix (flagship) |
| Re-check the score after a change | index365-run-audit then index365-read-report |
| Remove a project | index365-delete-project (destructive, confirms first) |
Always first
Run index365 doctor. If the key is missing or auth fails, go to index365-setup
before anything else, do not work around a missing key.
Output discipline
CLI write commands and large reads land in a git-ignored .index365/ dir. Read them
with grep / jq / head; never paste a whole report into context. index365 reports context <runId> prints JSON to stdout, redirect it to a file.
Single calls don't need a skill
index365 projects list, index365 runs get <id>, and index365 findings get are
single commands with no added judgment, just run them. Skills exist for the steps that
need judgment (which audit, what to fix first, applying a fix safely).
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most marketing audience skills give in 653 tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Said here and by no other author read
- run the doctor command first
- use index365-setup for missing key or auth failure
- never work around a missing key
- store write commands and large reads in a git-ignored directory
- parse large reads with standard cli tools
- never paste a whole report into context
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.