earlyaidopters/gumroad-resources · resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmark/SKILL.md

benchmark skillA

benchmark is agent-read markdown (skill) from earlyaidopters/gumroad-resources: Personal model benchmark built from YOUR own Claude Code history. Use when the user says /benchmark, "benchmark this model", "is <model> actually better", "test the new model on my workload", or when Claude Code upgrades to a new default model and they want a verdict grounded in THEIR tasks instead of public benchmarks. First run walks a setup wizard; after that it replays a frozen eval pack headlessly against any model or effort level and produces before/after scorecards..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add earlyaidopters/gumroad-resources/benchmark@git:20260810.9572c5c
Exact content
mdr add earlyaidopters/gumroad-resources/benchmark@sha256:07130a01182ff5d2

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_sf3ch2xmpwbqwdwe.svg)](https://markdownregistry.com/a/art_sf3ch2xmpwbqwdwe)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260810.9572c5c latest2026-08-10 9572c5c 14,176 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14176 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

earlyaidopters/gumroad-resources · 33 stars · license none · pushed 2026-09-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sf3ch2xmpwbqwdwe
GET https://markdownregistry.com/api/v1/resolve?ref=earlyaidopters/gumroad-resources/benchmark
GET https://markdownregistry.com/api/v1/blob/07130a01182ff5d2617b02fb2bc73188d1da975e5768b9e43758d5da42209948

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.