OSINT-side tech-stack identification — public repositories (GitHub/GitLab), job postings & ATS, and Wayback Machine historical snapshots.
SkillScore91Maintained
Automatic
◆Security & AppSec pack
Last verified 8/19/2026
What it changes
Passed 20 of 22 test cases with the skill, and 16 of 22 without it.
Without skill73%
With skill91%
Checks it passed that the model alone missed
Recommends CDX snapshot sampling every 6 to 12 months
Extracts framework version ranges from go.mod dependency files
Categorizes mention frequencies into Core, Common, and Occasional tiers
and 1 more in the full report
4 fixed16 passed either way2 still failing0 broke
Pass-rate lift
+18 pp
Tokens
+1%
Agent turns
0%
Response time
-23%
Model gemini-3.6-flashMeasured 8/19/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
A public GitHub organization repository contains a go.mod file listing module github.com/gin-gonic/gin v1.9.1. What specific output category receives this information?
What was checked, without and with the skill
Checked
Without skill
With skill
Extracts framework version ranges from go.mod dependency files
Missed
Passed
case-19 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md37 linessingle file
OSINT Tech-Stack Identification
Scope
Recover technology signals from public, non-target sources:
Code repositories — public GitHub/GitLab orgs, language stats, dependency files (package.json, requirements.txt, Gemfile, go.mod, pom.xml, composer.json), CI configs, Dockerfiles.
Career signals — career page, ATS platform (Greenhouse, Lever, Workday, Ashby, iCIMS, Taleo, etc.), job-description tech requirements.
Web archives — Wayback Machine CDX queries to detect historical stack and migrations.
These provide indirect but valuable corroboration; weight lower than direct technical signals.
Signals (input)
Public repos: org metadata, language map, dependency files, CI/CD configs, Dockerfile FROM lines
Career page URL + ATS URL pattern + job-description text
Wayback CDX snapshots (every 6-12 months over 5y)
Inferences (output)
Languages and frameworks (with version ranges from dep files)
CI/CD platform and pipeline maturity
Container base images and orchestration manifests
ATS-derived hiring profile (startup vs enterprise)
Tech-mention frequency (Core Stack ≥50% / Common 25-50% / Occasional <25%)