benchmaker SKILL.md skillA

benchmaker from danmcinerney/orchflows is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add danmcinerney/orchflows/benchmaker@git:20261002.9a76467

Pins git:20261002.9a76467 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
danmcinerney/orchflows
Path
example-workflows/benchmaker/skills/benchmaker/SKILL.md
Versions recorded
18
Latest version
git:20261002.9a76467, committed Oct 2, 2026
First version recorded
Sep 16, 2026
Size
8,060 bytes
Repository stars
125
License
MIT

Build benchmarks of realistic, hard agent tasks, researched from real work, admitting only verified, shortcut-resistant, calibrated tasks and reporting how well the suite separates systems.

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

Apply [library context](../../references/library-context.md). Accept a target: path, callable, command, endpoint, native workflow, skill or capability description. Also accept an optional claim, comparisons, budget and output location. Infer ordinary choices; clarify only material claim, permission or budget decisions. Without an executable target, a named representative stands in for it as the [quality card](../../references/quality-card.md) defines; a description with no executable representative supports only a draft.

A benchmark samples realistic, hard, valuable work and separates systems that differ in the claimed ability. Most candidate tasks should fail admission. A smaller budget admits fewer tasks and reaches a lower stage; it never weakens tasks or skips admission checks. Spend follows earned evidence: a task version that fails a criterion gets no further checks, so costly judgments go to tasks that cheaper evidence has not disqualified.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add danmcinerney/orchflows/benchmaker@sha256:dd3f369355a386f5

The line at the top of this page pins the label git:20261002.9a76467, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_zz3rojureio3bsor.svg)](https://markdownregistry.com/a/art_zz3rojureio3bsor)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 18 versions of this file, between Sep 16, 2026 and Oct 2, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261002.9a76467 latest2026-10-02 9a76467 8,060 BA view · diff
git:20261002.47f58752026-10-02 47f5875 7,799 BA view · diff
git:20261002.5bc68ef2026-10-02 5bc68ef 6,489 BA view · diff
git:20260924.6b325fd2026-09-24 6b325fd 6,396 BA view · diff
git:20260924.267e6de2026-09-24 267e6de 5,315 BA view · diff
git:20260924.ad95a672026-09-24 ad95a67 5,217 BA view · diff
git:20260924.0e70d302026-09-24 0e70d30 5,100 BA view · diff
git:20260923.61fb7ef2026-09-23 61fb7ef 4,843 BA view · diff
git:20260923.40564482026-09-23 4056448 3,902 BA view · diff
git:20260922.d9b21532026-09-22 d9b2153 4,062 BA view · diff
git:20260922.6f31a922026-09-22 6f31a92 4,064 BA view · diff
git:20260920.68009552026-09-20 6800955 4,493 BA view · diff
git:20260918.c9794ad2026-09-18 c9794ad 4,501 BA view · diff
git:20260918.3197adc2026-09-18 3197adc 5,364 BA view · diff
git:20260918.4a145ae2026-09-18 4a145ae 4,725 BA view · diff
git:20260918.b9675e52026-09-18 b9675e5 4,537 BA view · diff
git:20260916.00edb062026-09-16 00edb06 5,343 BA view · diff
git:20260916.32892e82026-09-16 32892e8 4,653 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (8060 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

danmcinerney/orchflows · 125 stars · license MIT · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_zz3rojureio3bsor
GET https://markdownregistry.com/api/v1/resolve?ref=danmcinerney/orchflows/benchmaker
GET https://markdownregistry.com/api/v1/blob/dd3f369355a386f5826e2cd8d55684b048e51ee70557886fec7f3bc390ed97d5

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 danmcinerney/orchflows

AGENTS.md AGENTS.md file
danmcinerney/orchflows · AGENTS.md
git:20260912.78b8c66 · audit A · 125 stars
CLAUDE.md CLAUDE.md file
danmcinerney/orchflows · CLAUDE.md
git:20260718.e46ce0d · audit B · 125 stars
DESIGN.md DESIGN.md file
danmcinerney/orchflows · DESIGN.md
git:20260923.6e9ec92 · audit A · 125 stars
3d-browser-game SKILL.md skill
danmcinerney/orchflows · example-workflows/3d-browser-game/skills/3d-browser-game/SKILL.md · Build a complete Three.js game or bounded production phase through mechanics experiments, Blender assets, QA and…
git:20260923.a587897 · audit A · 125 stars
make-blender-game-assets SKILL.md skill
danmcinerney/orchflows · example-workflows/3d-browser-game/skills/make-blender-game-assets/SKILL.md · Create original Blender assets with editable sources, GLB exports and inspection through a Three.js loader.
git:20260923.a587897 · audit A · 125 stars
playtest-3d-browser-game SKILL.md skill
danmcinerney/orchflows · example-workflows/3d-browser-game/skills/playtest-3d-browser-game/SKILL.md · Independently assess an exact Three.js build through browser play, mechanics, QA and rendered assets; no repairs.
git:20260922.d3c22ed · audit A · 125 stars
DESIGN.md@example-workflows/benchmaker DESIGN.md file
danmcinerney/orchflows · example-workflows/benchmaker/DESIGN.md
git:20261003.ec03795 · audit A · 125 stars
booking-rules SKILL.md skill
danmcinerney/orchflows · example-workflows/benchmaker/trials/benchmaking-benchmark/meta-tasks/calendar-skill/subject/booking-rules/skills/booking-rules/SKILL.md · Book a meeting into the team's calendar files under the booking policy. Use when asked to schedule, book or find a time…
git:20261002.979492b · audit A · 125 stars
analyze-iteration SKILL.md skill
danmcinerney/orchflows · example-workflows/design-loop/skills/analyze-iteration/SKILL.md · Analyze an increment's evidence, recommend adopt or retain, and inform the next brainstorm.
git:20260922.d9b2153 · audit A · 125 stars
brainstorm-options SKILL.md skill
danmcinerney/orchflows · example-workflows/design-loop/skills/brainstorm-options/SKILL.md · Propose a few scoped next increments from an endgoal, current state and prior observations.
git:20260922.29a330b · audit A · 125 stars
brainstorm-research SKILL.md skill
danmcinerney/orchflows · example-workflows/design-loop/skills/brainstorm-research/SKILL.md · Generate project improvement options, then research their decision-relevant uncertainties for design.
git:20260922.7150535 · audit A · 125 stars
design-increment SKILL.md skill
danmcinerney/orchflows · example-workflows/design-loop/skills/design-increment/SKILL.md · Turn a goal, options and research into one implementable increment and an old/new evaluation plan.
git:20260918.c9794ad · audit A · 125 stars

Every file in danmcinerney/orchflows

Browse by kind, by grade A, or by owner.