DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to turn GEO gaps into tickets and check that fixes worked with Geolook

Create implementation tickets with acceptance criteria and let re-crawls and sampling decide if each fix is done.

Who it is forAn SEO or content lead who has a diagnosis but no one executing the recommendations.

The problemAdvice piles up without an owner, and nobody can prove that a change helped AI engines.

The outcomeStructured tickets with owner, effort, risk grade, and acceptance criteria, each with a progress bar from first-measured to target, and automatic reopening if a regression appears.

What you need first

  • Python 3.9+ on macOS or Linux (Windows via WSL)
  • git
  • Optional: an engine API key, such as DeepSeek or GLM, for automated sampling and drafts

Steps

  1. Complete the setup and first run from the diagnosis use case, then run python3 scripts/geo.py ui.
  2. Open the Action area and review the generated tickets, sorted by priority and risk grade.
  3. Assign owners and work the tickets, using the content workbench for drafts and the deploy assets for llms.txt and JSON-LD.
  4. Re-run sampling on a schedule, or run ./scripts/service.sh install on macOS so scheduled re-runs keep firing.
  5. Check the Results page for per-question before and after comparisons and the verification history.

Prompt for your agent

Using the geolook repo at <repo path>, read the open implementation tickets for <brand> and draft the acceptance criteria check for each one. Output a list with ticket name, current measured value, target value, and pass or fail. Verify that the list matches the progress bars shown in the Action area.

Caveat. Automatic verification depends on re-crawls and sampling rounds, so the progress reflects only the metrics the tool can measure.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page