Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
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
> Portable adaptation of Lauren Tan's pstack v0.15.30. Use available workspace, execution, and observation capabilities. When a tool is unavailable, preserve the procedure where possible and report evidence gaps rather than claiming verification.
# Benchmark checklist
Use this when you produce a performance number: a PR's before and after, a regression claim, a hillclimb harness, or a library or config choice. Answer each question with evidence from a run, not a guess about the code.
For a quick ballpark the user asked for, one run is enough. Still check questions 4 and 7, and say that it is one run. Skip the rest unless that run looks wrong. A choice between options is never a ballpark.
## Before you run anything
- Write down the claim you expect to make, in the words you would ship ("export is 30% faster at p50 on the 60k-row dataset"). The questions test that sentence.
- Read the measurement script. Note what it times, counts, and ignores.
- Check the load average with `uptime` and the core count with `nproc`. If the machine is busy, find out what is running. If you cannot stop it, interleave the sides so both see the same noise, and say so in the report.
## The questions
…
The line at the top of this page pins the label git:20261023.9aa1985, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_ufbvuiulzdayyxcl
GET https://markdownregistry.com/api/v1/resolve?ref=theonlyfusioncube/potetos-for-everyone/benchmark-checklist
GET https://markdownregistry.com/api/v1/blob/77e53cf3ca35b11cd731fdec26b52bcb40808486ae26605cec1cf8af02e20a79
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.
theonlyfusioncube/potetos-for-everyone · automations/benny/skills/reproduce-and-fix-issues/SKILL.md · Reproduce a confirmed issue on the closest real surface, find root cause, and optionally prepare a minimal draft fix…
theonlyfusioncube/potetos-for-everyone · automations/benny/skills/triage-issue-reports/SKILL.md · Triage incoming software issue reports using available repository and runtime evidence, without editing code. Use for…
theonlyfusioncube/potetos-for-everyone · skills/architect/SKILL.md · Settle data shapes, ownership, boundaries, and interfaces before code crosses a function/module boundary. Use for…
theonlyfusioncube/potetos-for-everyone · skills/arena/SKILL.md · Spawn parallel candidate implementations for the same task, cross-judge, and graft the best parts into the winning…
theonlyfusioncube/potetos-for-everyone · skills/automate-me/SKILL.md · Create a personal mode skill from recurring workflow patterns in available history. Use when the user wants their own…
theonlyfusioncube/potetos-for-everyone · skills/blast-radius/SKILL.md · Prove what a small-looking change can affect before or after editing. Use for compatibility, caller, state, schema, or…
theonlyfusioncube/potetos-for-everyone · skills/bro/SKILL.md · Restate the last technical explanation in plain human language with minimal jargon. Use when the user asks for a…
theonlyfusioncube/potetos-for-everyone · skills/correct/SKILL.md · Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types…
theonlyfusioncube/potetos-for-everyone · skills/create-formal-verification-skill/SKILL.md · Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
theonlyfusioncube/potetos-for-everyone · skills/create-verification-skill/SKILL.md · Generate a project-local verification skill that drives the real app and captures evidence. Use when setting up…
theonlyfusioncube/potetos-for-everyone · skills/figure-it-out/SKILL.md · Design a rigorous custom playbook when no bundled playbook safely fits a large or unusual task. Use for cross-cutting…
cursor/plugins · harness/pstack/claude-code/skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
cursor/plugins · pstack/skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
michael-denyer/pstack-claude · plugins/pstack/skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
backnotprop/pstack · skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
creedants/pstack-t3 · skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
arjitj2/open-pstack · plugins/pstack/skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
lucasheriques/pstack · skills/benchmark-checklist/SKILL.md · Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened)…
