benchmark SKILL.md skillA
benchmark from earlyaidopters/gumroad-resources is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add earlyaidopters/gumroad-resources/benchmark@git:20260810.9572c5cPins git:20260810.9572c5c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- earlyaidopters/gumroad-resources
- Path
resources/personal-ai-benchmark-kit/unpacked/personal_benchmark_skill/personal-benchmark/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260810.9572c5c, committed Aug 10, 2026
- Size
- 14,176 bytes
- Repository stars
- 48
- License
- none declared
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# /benchmark, Your History Is Your Benchmark Answers "is the new model actually better?" using the user's real workload, not a stranger's website demo. Everything lives in `~/.claude/benchmark/`; scripts in `scripts/`. ## ALWAYS start with the status probe Run `python3 scripts/status.py --brief 2>/dev/null` before anything else, and make it your ONLY probe call. Never follow it with db.py summary, ls of run dirs, cat of verdict files, or the JSON status: --brief already contains the pack state, categories, latest run + verdict headline, unfinished runs, and upgrade detection. Multiple raw probe dumps look terrible on screen. (Use plain `status.py` JSON only inside the wizard, where you need `history_size` and `engine` fields.) - Output says `none (first run)` → run the **First-Run Wizard** below. - `UPGRADE DETECTED` line present → lead with it: "Claude Code updated since your last benchmark, which usually means a new model. Want to test it against <last benchmarked model>?" …
Read the whole file at its exact version.
How to install
mdr add earlyaidopters/gumroad-resources/benchmark@sha256:07130a01182ff5d2The line at the top of this page pins the label git:20260810.9572c5c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_sf3ch2xmpwbqwdwe)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 10, 2026.
Audit of the latest version
- 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
earlyaidopters/gumroad-resources · 48 stars · license none declared · pushed 2026-11-08 · 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
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from earlyaidopters/gumroad-resources
Every file in earlyaidopters/gumroad-resources