CtrlK
BlogDocsLog inGet started
Tessl Logo

run-experiment

Deploy and run ML experiments on local or remote GPU servers. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex/run-experiment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 well-structured, executable workflow with strong sequencing and validation for destructive operations. The main weaknesses are a jargon-dense env-contract paragraph and templated placeholders that keep commands from being fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly tight bash/python snippets and imperative steps, but the 'environment contract' paragraph (lines 23-30) leans on dense jargon like 'seeded kernel witness' and 'agent-follows-doc pass' that could be trimmed.

4 / 5

Actionability

Concrete, executable ssh/screen/rsync/modal commands cover the common cases, but heavy use of placeholders (<server>, <exp_name>) and the wandb snippet's undefined WANDB_PROJECT/{...hyperparams...} are minor gaps from fully copy-paste-ready.

4 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced with explicit validation checkpoints (pre-flight GPU check, Step 5 verify launch, Step 7 'do not destroy' if artifact copy fails) and a Key Rules checklist, satisfying the destructive/batch validation requirement.

5 / 5

Progressive Disclosure

Content is well-organized into labeled Workflow steps, Key Rules, and an AGENTS.md Example, and the single external reference ('../shared-references/compute-env-contract.md') is one level deep and clearly signaled, though no bundle files exist and the AGENTS.md example is inlined.

4 / 5

Total

17

/

20

Passed

Description

78%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 clear, third-person description that answers both what and when with concrete, multilingual trigger phrases. It is strong on completeness but slightly generic on the action verbs and has minor overlap risk with broader deploy/run skills.

DimensionReasoningScore

Specificity

Quotes 'Deploy and run ML experiments on local or remote GPU servers' name the domain plus two concrete actions (deploy, run), but the actions stay generic rather than enumerating specifics like sync, screen-session binding, or W&B logging.

3 / 5

Completeness

Quotes 'Deploy and run ML experiments on local or remote GPU servers' answer the 'what' and 'Use when user says ...' explicitly answers 'when' with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Quotes 'run experiment', 'deploy to server', '跑实验', and 'launch training jobs' give good natural keyword coverage with synonyms and a multilingual term, though common variations like 'train a model' or 'start training' are absent.

4 / 5

Distinctiveness Conflict Risk

The GPU/ML-training deployment niche with explicit triggers is mostly distinct, but 'run experiment' / 'deploy to server' are broad enough to risk minor overlap with general code-run or deploy skills.

4 / 5

Total

16

/

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
wanshuiyin/Auto-claude-code-research-in-sleep
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.