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.
mdr add danmcinerney/orchflows/benchmaker@git:20261002.9a76467Pins 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
mdr add danmcinerney/orchflows/benchmaker@sha256:dd3f369355a386f5The 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.
[](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.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261002.9a76467 latest | 2026-10-02 | 9a76467 | 8,060 B | A | view · diff |
| git:20261002.47f5875 | 2026-10-02 | 47f5875 | 7,799 B | A | view · diff |
| git:20261002.5bc68ef | 2026-10-02 | 5bc68ef | 6,489 B | A | view · diff |
| git:20260924.6b325fd | 2026-09-24 | 6b325fd | 6,396 B | A | view · diff |
| git:20260924.267e6de | 2026-09-24 | 267e6de | 5,315 B | A | view · diff |
| git:20260924.ad95a67 | 2026-09-24 | ad95a67 | 5,217 B | A | view · diff |
| git:20260924.0e70d30 | 2026-09-24 | 0e70d30 | 5,100 B | A | view · diff |
| git:20260923.61fb7ef | 2026-09-23 | 61fb7ef | 4,843 B | A | view · diff |
| git:20260923.4056448 | 2026-09-23 | 4056448 | 3,902 B | A | view · diff |
| git:20260922.d9b2153 | 2026-09-22 | d9b2153 | 4,062 B | A | view · diff |
| git:20260922.6f31a92 | 2026-09-22 | 6f31a92 | 4,064 B | A | view · diff |
| git:20260920.6800955 | 2026-09-20 | 6800955 | 4,493 B | A | view · diff |
| git:20260918.c9794ad | 2026-09-18 | c9794ad | 4,501 B | A | view · diff |
| git:20260918.3197adc | 2026-09-18 | 3197adc | 5,364 B | A | view · diff |
| git:20260918.4a145ae | 2026-09-18 | 4a145ae | 4,725 B | A | view · diff |
| git:20260918.b9675e5 | 2026-09-18 | b9675e5 | 4,537 B | A | view · diff |
| git:20260916.00edb06 | 2026-09-16 | 00edb06 | 5,343 B | A | view · diff |
| git:20260916.32892e8 | 2026-09-16 | 32892e8 | 4,653 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 (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
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.