agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/sqlsimtools/.github/skills/sqlsimtools-project-stats/SKILL.md

sqlsimtools-project-stats

Skill42 starsChanged 32 days agoMITView on GitHub

Source-repository-only maintainer report of current sqlsimtools project numbers: release download counts per file, GitHub Pages website status and click-throughs, 14-day repository views, clones, referrers, and popular pages, plus stars, forks, and watchers. USE WHEN: a maintainer asks for project stats, download numbers, how many people downloaded a release, website or repository traffic, referrers, or how usage changed since earlier numbers. DO NOT USE FOR: tool run telemetry (sqlsimtools collects none), Google Search Console or Bing Webmaster Tools data (view those in their portals), or running SQL workloads (use the sqlsim, sqlpysim, or sqlsimstudio skills).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If it fails because the GitHub CLI is missing or signed out, tell the user to install it from https://cli.github.com/ or run gh auth login, …

    line 23
  2. Distinctive:

    If the user supplied earlier numbers or asked about change over time, report the difference for each comparable value.

    line 38
  3. Very specific:

    If traffic is null and trafficError is set, the signed-in account lacks push access.

    line 56
  4. Distinctive:

    When the user wants the full console report instead of a summary, run:

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

sqlsimtools project stats

Reports the latest public-interest numbers for microsoft/sqlsimtools by running the repository script scripts/get-project-stats.ps1. The report is read-only; never change repository settings, files, or releases while using this skill.

Procedure

  1. From the repository root, run the script with JSON output and capture it in a variable. Do not add shell redirects or pipes to the command itself.

    $stats = .\scripts\get-project-stats.ps1 -Json | ConvertFrom-Json

    If it fails because the GitHub CLI is missing or signed out, tell the user to install it from https://cli.github.com/ or run gh auth login, then stop.

  2. Summarize for the user, in this order:
    • Downloads: downloads.total, then each release in downloads.releases with its files sorted by downloads, highest first.
    • Website: website.status for website.url, and website.clickThroughs (website.uniqueClickThroughs unique) from the site into GitHub over the last 14 days.
    • Repository traffic (last 14 days): traffic.views, traffic.clones, the top traffic.referrers, and the top traffic.pages. Mention any notable day in traffic.dailyViews.
    • Repository: stars, forks, watchers, and open issues and pull requests from repositoryCounts.
  3. If the user supplied earlier numbers or asked about change over time, report the difference for each comparable value. Compare download totals per file, not only the grand total.

Interpreting the numbers

State these caveats when they affect the answer:

  • Download counts are running totals since each file was uploaded. GitHub keeps no daily history, and the automatic "Source code" archives are not counted. The maintainers' own test downloads are included.
  • Traffic covers only the last 14 days. Unique visitors cannot be added across days or periods.
  • Clones include CI checkouts, so they overstate real users.
  • GitHub provides no visitor analytics for the Pages site. Click-throughs count only visitors who followed a link from the site into GitHub. For search impressions and clicks, point the user to Google Search Console and Bing Webmaster Tools (URLs in website).
  • If traffic is null and trafficError is set, the signed-in account lacks push access. Report downloads and repository counts, and explain that traffic and click-throughs need a maintainer account.

Formatted report

When the user wants the full console report instead of a summary, run:

.\scripts\get-project-stats.ps1

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free