GitHub Skill Adoption Audit
Overview
Measure whether a public skill repository is being discovered or used. Separate
hard signals such as stars and unique cloners from weak signals such as generic
search hits.
Read references/adoption-signals.md when interpreting results.
Workflow
Resolve the repository set.
- If the user names a repo, inspect only that repo.
- If the user says "my skills", discover likely skill repos from local git
remotes or
gh repo list <owner>.
Gather GitHub metadata.
- Use
gh repo view for stars, forks, watchers, issues, PRs, visibility,
pushed date, and URL.
- Use GitHub traffic endpoints for views, clones, referrers, and popular
paths when the authenticated user has permission.
Check external discovery.
- Search for exact repo names, install commands, and unique skill phrases.
- Treat generic skill names as weak evidence unless the result clearly points
back to the user's repo.
- Note GitHub code-search rate limits rather than retrying aggressively.
Interpret cautiously.
- Stars show public endorsement.
- Unique clones suggest installation or inspection, but may include bots,
mirrors, CI, or the owner.
- Views/referrers show discovery channels for the last GitHub traffic window,
usually about 14 days.
- Marketplace indexing is discoverability, not proof of active use.
Output a short decision.
- Identify the strongest repo.
- List star count and traffic counts.
- Say what is not yet proven.
- Recommend one practical next action: README demo, screenshot, release,
example task, marketplace metadata, or targeted distribution.
Script
Run the bundled audit script when gh is authenticated:
python3 scripts/audit_skill_repos.py \
--owner walterkken \
--repos doc-driven-engineering-software-skills matlab-simulink-agent-skill \
--output skill-adoption-audit.md
It writes a markdown report and a sibling JSON file. If traffic endpoints fail,
the report should still include public metadata and the exact permission/rate
limit issue.
1---2name: github-skill-adoption-audit3description: Audit GitHub repositories that publish agent skills and summarize real adoption signals: stars, forks, watchers, issues, recent views, clones, referrers, popular paths, directory/marketplace indexing, and external references. Use when Codex is asked whether a skill repo has users, how many stars it has, whether people are cloning it, which repo is getting traction, or how to prioritize skill promotion.4---56# GitHub Skill Adoption Audit78## Overview910Measure whether a public skill repository is being discovered or used. Separate11hard signals such as stars and unique cloners from weak signals such as generic12search hits.1314Read `references/adoption-signals.md` when interpreting results.1516## Workflow17181. Resolve the repository set.19 - If the user names a repo, inspect only that repo.20 - If the user says "my skills", discover likely skill repos from local git21 remotes or `gh repo list <owner>`.22232. Gather GitHub metadata.24 - Use `gh repo view` for stars, forks, watchers, issues, PRs, visibility,25 pushed date, and URL.26 - Use GitHub traffic endpoints for views, clones, referrers, and popular27 paths when the authenticated user has permission.28293. Check external discovery.30 - Search for exact repo names, install commands, and unique skill phrases.31 - Treat generic skill names as weak evidence unless the result clearly points32 back to the user's repo.33 - Note GitHub code-search rate limits rather than retrying aggressively.34354. Interpret cautiously.36 - Stars show public endorsement.37 - Unique clones suggest installation or inspection, but may include bots,38 mirrors, CI, or the owner.39 - Views/referrers show discovery channels for the last GitHub traffic window,40 usually about 14 days.41 - Marketplace indexing is discoverability, not proof of active use.42435. Output a short decision.44 - Identify the strongest repo.45 - List star count and traffic counts.46 - Say what is not yet proven.47 - Recommend one practical next action: README demo, screenshot, release,48 example task, marketplace metadata, or targeted distribution.4950## Script5152Run the bundled audit script when `gh` is authenticated:5354```bash55python3 scripts/audit_skill_repos.py \56 --owner walterkken \57 --repos doc-driven-engineering-software-skills matlab-simulink-agent-skill \58 --output skill-adoption-audit.md59```6061It writes a markdown report and a sibling JSON file. If traffic endpoints fail,62the report should still include public metadata and the exact permission/rate63limit issue.
walterkken