benchmark-checklist SKILL.md skillA
benchmark-checklist from creedants/pstack-t3 is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add creedants/pstack-t3/benchmark-checklist@git:20261011.042ae70Pins git:20261011.042ae70 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- creedants/pstack-t3
- Path
skills/benchmark-checklist/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261011.042ae70, committed Oct 11, 2026
- First version recorded
- Oct 3, 2026
- Size
- 5,152 bytes
- Repository stars
- 15
- License
- MIT
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
# Benchmark checklist
Read [the pstack-t3 runtime](../pstack-runtime/SKILL.md) before spawning workers, choosing models, scheduling, or isolating work. It maps those steps onto T3's orchestrator tools.
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
…Read the whole file at its exact version.
How to install
mdr add creedants/pstack-t3/benchmark-checklist@sha256:89ce679dffdcfd8dThe line at the top of this page pins the label git:20261011.042ae70, 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_qyzveghq26j5n3gx)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Oct 3, 2026 and Oct 11, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261011.042ae70 latest | 2026-10-11 | 042ae70 | 5,152 B | A | view · diff |
| git:20261004.066ee54 | 2026-10-04 | 066ee54 | 5,559 B | A | view · diff |
| git:20261003.a632f62 | 2026-10-03 | a632f62 | 5,543 B | A | view |
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 (5152 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
creedants/pstack-t3 · 15 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qyzveghq26j5n3gx GET https://markdownregistry.com/api/v1/resolve?ref=creedants/pstack-t3/benchmark-checklist GET https://markdownregistry.com/api/v1/blob/89ce679dffdcfd8dbb94aab0e2a74d8b83f278785eccd2654a694589622d27a3
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 creedants/pstack-t3
Every file in creedants/pstack-t3