CtrlK
BlogDocsLog inGet started
Tessl Logo

remote-compute-ssh

Run Feynman research jobs on SSH, Slurm, or lab hosts. Use when a task needs remote host setup, job submission, log harvest, artifact sync, or GPU/cluster execution outside Modal.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-structured remote-compute workflow with clear sequencing and a validation checkpoint. Its main weakness is actionability: it describes what to capture and do but omits executable command/script templates that would make it copy-paste ready.

Suggestions

Add a minimal example for the two most common operations — e.g., a sample `sbatch` submission script that logs package versions/hardware/seed, and an `ssh`/`rsync` snippet for artifact harvest — to lift actionability toward 4-5.

Include an explicit feedback loop after the step-2 smoke test ("if the smoke command fails, diagnose access/env before resubmitting") to earn the workflow-clarity 5 anchor.

Show a concrete checksum command (e.g., `sha256sum` over artifacts) in step 4 so the harvest step is fully executable rather than descriptive.

DimensionReasoningScore

Conciseness

Lean and efficient — a short numbered workflow plus one closing note, with no padding or explanation of concepts Claude already knows (e.g., what SSH or Slurm is). Every token earns its place.

5 / 5

Actionability

The workflow gives concrete checklists of what to record and harvest (host alias, scheduler, stdout/stderr, job id, checksums), but provides no executable examples — no sample sbatch script, ssh command, or rsync/sync template — leaving key execution details implicit.

3 / 5

Workflow Clarity

Clear five-step sequence with an explicit validation checkpoint (step 2: "Verify access and a tiny smoke command"), but lacks an explicit feedback loop for error recovery (e.g., what to do when the smoke test or job fails), which keeps it below 5.

4 / 5

Progressive Disclosure

A simple skill under 50 lines with no external references needed; content is well organized into a heading, a numbered workflow, and a closing note, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly communicates purpose, trigger conditions, and scope boundaries with concrete action vocabulary. The only gaps are a few missing synonyms and slightly less-than-exhaustive action coverage.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions — "remote host setup, job submission, log harvest, artifact sync, or GPU/cluster execution" — but stops short of fully comprehensive coverage of remote-compute tasks (e.g., monitoring, env provisioning detail).

4 / 5

Completeness

Explicitly states both what ("Run Feynman research jobs on SSH, Slurm, or lab hosts") and when ("Use when a task needs remote host setup, job submission, log harvest, artifact sync, or GPU/cluster execution outside Modal") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good coverage of natural terms users would say ("SSH", "Slurm", "lab hosts", "job submission", "GPU", "cluster", "outside Modal"), but missing common synonyms like "HPC", "supercomputer", or "batch jobs".

4 / 5

Distinctiveness Conflict Risk

Clear niche (remote SSH/Slurm/lab compute) with an explicit boundary ("outside Modal") that distinguishes it from a Modal-based compute skill, minimizing conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
companion-inc/feynman
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.