Let README readers audit their own page for AI Overviews readiness, straight from the repo - #3
Open
shesl-tinkerland wants to merge 1 commit into
Conversation
Lets README readers run the audit on their own page before installing. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Following up on #1, where this looked good and the question was what to do next. Here is a concrete PR.
The skill already classifies a request into audit / plan / fix and leads with prioritized findings. A README reader can't feel that until they've installed the CLI and pointed an agent at a page. This PR closes that gap with one link they can act on right where they're deciding whether the skill is worth installing.
The demo runs the same audit path the README describes: drop in a page URL, and it walks the technical / content / structured-data checklist from your audit-playbook and returns the executive-readout → priority-findings → backlog shape you specified. It keeps the myth-check too, flagging
llms.txtand chunking as unsupported.That stance is the unusual part. Most "AI SEO" tools lean into those hacks, and your skill explicitly rejects them. A reader who tries it once gets that opinion immediately instead of reading about it.
The proposal: drop this badge near the top of the README, where people already weigh the install. A reader can open the demo, paste a page they care about, and see a real audit before they touch
npx skills add.The same link is something a reader can forward to a teammate who owns a page that needs the check.
The other half is signal for you. README-originated runs leave usage records, so you can see which request type people reach for — audit vs plan vs myth-check — and what pages they bring. That maps back onto sharpening the checklists and examples in
SKILL.md. Once runs start coming through, I can send over the usage-record review link plus a few real sessions.Happy to adjust placement or wording to fit how you'd want it to sit in the README.