SKILLEMALL.ai
GitHub ↗ RU Sign in

AC orx-compute

Launch and monitor experiment runs and route guidance for hf, modal, k8s/Kubernetes, ssh, slurm, ray, OpenResearch, Tinker, and local backends. Covers the fixed run contract, sizing, cancellation, and wait versus wake. Use before any launch or relaunch, when authoring a k8s manifest, choosing or switching compute, or handling an OOM, stall, or timeout; then read one backend reference.

alphaXiv/OpenResearch Agent Skills author: alphaXiv MIT 11 files body ≈ 2 069 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Launch and monitor experiment runs and route guidance for hf, modal, k8s/Kubernetes, ssh, slurm, ray, OpenResearch, Tinker, and local backends.

As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ReferenceKubernetesSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
99
Quality 40%
88
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Dangerous commands cmd-background-process references/ssh.md:72
      Starts a background / autostarted process (quoted — discussed, not commanded)
      `setsid --wait`, and an absolute writable `$HOME`. Execution uses the container's
      quoted

    Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 38): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 9 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, write, node) that frontmatter does not declare
    • 100Steps. 20 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2069 tokens
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (10 tags): a typed call is more reliable

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 387: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 20 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (10 of 10)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.