CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

run-experiment

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

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

75%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 highly actionable, well-sequenced operational skill whose commands are copy-paste ready and whose workflow includes validation and destructive-op safeguards. Its weakest point is token efficiency: several dense prose policy blocks and setup notes could be trimmed or moved to reference files.

Suggestions

Move the full 'Environment contract' and 'Preparation failures' policy prose into the referenced compute-env-contract.md (or a references/ file) and keep only a 2-3 line digest inline, cutting roughly 15 lines of the densest text.

Trim the trailing setup blockquotes (Vast.ai/Modal/W&B setup) to bare commands and links, removing explanatory asides like 'ideal for users without a local GPU who need to debug code or run small-scale tests'.

Add a short explicit error-recovery branch after Step 5 (e.g. what to check if screen -ls shows no session or the log shows an immediate crash) to close the last workflow-clarity gap.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands and project-specific conventions Claude would not know, but the dense prose blocks ("Environment contract", "Preparation failures") and trailing setup blockquotes (e.g. "ideal for users without a local GPU who need to debug code") are convoluted or padded and could be tightened.

3 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases for every environment: complete rsync include/exclude rules, ssh+screen launch with conda activation, W&B logging snippets, Modal launcher flow, and the full vastai rent-to-destroy lifecycle.

5 / 5

Workflow Clarity

The 7-step workflow is clearly sequenced with explicit skip conditions, a pre-flight GPU check, a verify-launch step, smoke-test validation, and careful handling of the destructive instance-destroy operation; it falls short of the top anchor only because explicit error-recovery branches for launch failures are not spelled out (the retry/escalation policy is prose).

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent), so all guidance is inline in one 340-line file; the numbered step sections are well-organized and sibling-skill delegation is clearly signaled, but the referenced ../shared-references/compute-env-contract.md is outside the bundle and its policy content is partially duplicated inline — good structure with minor organization gaps.

4 / 5

Total

16

/

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 strong description that explicitly covers both capability and trigger conditions, including bilingual triggers, with a well-defined ML-experiment deployment niche. Its main weaknesses are modest action specificity and a few missing natural trigger variants.

DimensionReasoningScore

Specificity

"Deploy and run ML experiments" names the domain and 1-2 concrete actions across four named environments, but does not enumerate several specific sub-actions (rent instance, sync code, launch in screen session, teardown), matching the anchor for domain plus 1-2 concrete actions rather than a comprehensive action list.

3 / 5

Completeness

It clearly answers both what ("Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU") and when ("Use when user says 'run experiment', 'deploy to server', '跑实验', or needs to launch training jobs") with concrete quoted trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases like "run experiment", "deploy to server", "needs to launch training jobs", plus the bilingual "跑实验", give good keyword coverage; common variants such as "train a model", "GPU job", or "launch training" are missing, so it falls just short of comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The ML-experiment-deployment niche with named providers is mostly distinct with specific triggers, but the generic "deploy to server" phrase carries minor overlap risk with general deployment skills, keeping it below the clear-niche anchor.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

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

Path

skills/run-experiment/SKILL.md

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.