Garry TanPresident and CEO of Y Combinator, gstack creator301 installs on skills.shBenchmark Models
Cross-model benchmark for gstack skills.
3 static scans, 0 counted findings.
Edge checks it again each time your agent loads it.
What it does
- Cross-model benchmark for gstack skills.
- (gstack)

Why Garry Tan
CEO of Y Combinator. Each fact links its public source.
- President and CEO of Y Combinator
He leads YC and co-founded Initialized Capital, earliest investor in Coinbase and Instacart.
LinkedIn headline - 137k+ GitHub stars on gstack
His Claude Code setup ships QA, planning and release documentation tools as skills.
GitHub repo - Co-founded Posterous, acquired by Twitter
He co-founded the YC S08 blog platform Posterous, which Twitter acquired.
Y Combinator people page
How it works
- 1Copy
Try for free gives you one prompt.
- 2Paste
Paste it into Claude Code, Codex or Cursor.
- 3Ask
Ask for the outcome. Your agent loads Benchmark Models.
3 static scans, 0 counted findings.
Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.
State definitionsSelect the Files tab to load SKILL.md.
Skill details
Security scansReviewed
3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.
Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .
Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 1.
Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .
- Edge static checks
- Pass · 0 counted findings · 2026-09-27
- Cisco skill-scanner
- Pass · 0 counted findings · 2026-09-27
- Semgrep Edge rules
- Pass · 0 counted findings · 2026-09-27
Creator, source & licencegarrytan
From the garrytan public repository. Edge did not write or edit this skill.
- Repository
- garrytan/gstack
- Skill file
- View source at revision
- Revision
- 01593aa67c94780528e8f5121e47362502410ced
- Package hash
- sha256:b62114268235de41de1ae2e4c3b65b35675d8f204e2958b7a0b32cc5cd7c2cda
- Licence
- MIT
- Description
- Cross-model benchmark for gstack skills. (gstack)
Quoted from the skill’s own description
Read skill files2 files
2 files, 20.8 KB at revision 01593aa67c94.
Questions about Benchmark Models
What does Benchmark Models do?
Cross-model benchmark for gstack skills. Published by Garry Tan (garrytan/gstack).
Is Benchmark Models safe to use?
Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.
How do I use Benchmark Models in Claude Code, Codex or Cursor?
Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.