collect-github-stats
Skill373 starsChanged 6 days agoApache-2.0View on GitHub
Collect GitHub repo health/usage stats into merged JSON.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- compress-promptSkill
- daily-ossSkill
- documentationSkill
- merge-mainSkill
- sync-web-siteSkill
- update-change-logSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 25
PUSH ACCESS REQUIRED: No push → traffic 403 → script FAILS LOUD with fix steps.
- Distinctive: line 26
MUST NOT accept a partial file.
- Very specific: line 30
MUST have gh authenticated, repo scope, push access to the target repo.
- Distinctive: line 31
SHOULD relay the script's post-run summary to the user.
- Very specific: line 35
If you learned something new which is reusable, there are process efficiency improvements, you can prevent failures in the future, update …
≈ “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.
Files
collect-github-stats
Runs one script: fetch GitHub stats for a repo, merge into docs/github-stats.json.
Run (MUST)
python3 <skill_dir>/scripts/collect_stats.py [--repo OWNER/NAME] [--out PATH] [--no-enrich]Defaults: --repo griddynamics/rosetta, --out docs/github-stats.json. MUST run from
repo root (or pass absolute --out). --no-enrich skips company/location lookups.
CRITICAL
- NEVER DELETE OR OVERWRITE
docs/github-stats.json. Script APPEND-MERGES. Traffic is a 14-DAY ROLLING WINDOW — deleted history is GONE FOREVER, unrecoverable from the API. - PUSH ACCESS REQUIRED. No push → traffic 403 → script FAILS LOUD with fix steps. MUST NOT accept a partial file.
Rules (MoSCoW)
- MUST have
ghauthenticated,reposcope, push access to the target repo. - SHOULD relay the script's post-run summary to the user.
- COULD normalize company variants when REPORTING; MUST NOT mutate stored raw values.
- WON'T fabricate cloner identity (cloners are ANONYMOUS — counts only), store PII/secrets.
If you learned something new which is reusable, there are process efficiency improvements, you can prevent failures in the future, update ## Lessons learned below for self-improvement.
Lessons learned (self-improvement, keep updating, first line is template, keep template, follow "<instructions>", high confidence only):
- <key action item, less then 7 words> <concise/terse: what happened, why, root cause, reasoning, less then 25 words>.
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
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.

