cloudml-eval-ops skillA
cloudml-eval-ops is agent-read markdown (skill) from miaodx/roboclaws: Run frozen Roboclaws Eval Harness rows on CloudML with bounded parallelism, official cml lifecycle commands, executor-backed JuiceFS transfer, durable task receipts, verified collection, and explicit retry/preemption evidence. Use when a user asks to run, refresh, resume, monitor, collect, or debug a Roboclaws baseline/eval on CloudML, especially parallel CPU, MuJoCo, Grounding DINO, provider, or hybrid local/cloud runs..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# CloudML Eval Ops Run CloudML as an execution environment for an existing Roboclaws Eval Harness manifest. Do not make CloudML a product backend and do not reimplement CloudML or storage APIs in Roboclaws. ## Ownership - Let Roboclaws own row selection, commands, graders, result schemas, and final reports. Read `../eval-harness/SKILL.md` before selecting rows. - Use the installed `cml-shared`, `cml-resource`, and `cml-train` skills and the official `cml` CLI for context, resources, YAML, submit, describe, logs, events, stop, and task status. - Use the installed `executor` skill only for cross-platform Repo and JuiceFS/FDS operations. Read its CloudML defaults before those operations. - Keep cluster, queue, image, mount, endpoint, and credential values in existing environment-owned CML/executor configuration or run-local ignored files. Do not add them to this skill, tracked source, commands printed in reports, or normal eval artifacts. ## Task Authorization Treat an explicit human request to run or refresh a repo-scoped CloudML eval as authorization for all necessary in-scope operations: read-only preflight, …
Read the whole file at its exact version.
How to install
mdr add miaodx/roboclaws/cloudml-eval-ops@git:20260826.4cd1c7amdr add miaodx/roboclaws/cloudml-eval-ops@sha256:a65b41fa076d7961Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_6ru5n2ayvrskdqly)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260826.4cd1c7a latest | 2026-08-26 | 4cd1c7a | 18,311 B | A | view · diff |
| git:20260826.c82bec7 | 2026-08-26 | c82bec7 | 18,263 B | A | view · diff |
| git:20260826.69ea029 | 2026-08-26 | 69ea029 | 17,995 B | A | view · diff |
| git:20260816.3e0c2f2 | 2026-08-16 | 3e0c2f2 | 16,664 B | A | view · diff |
| git:20260816.4e20ed0 | 2026-08-16 | 4e20ed0 | 16,659 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 (18311 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
miaodx/roboclaws · 6 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6ru5n2ayvrskdqly GET https://markdownregistry.com/api/v1/resolve?ref=miaodx/roboclaws/cloudml-eval-ops GET https://markdownregistry.com/api/v1/blob/a65b41fa076d79619e8c506514fd6384f0ddff284b9ffb73bbd597c7372889b2
Your agent 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.