aris-monitor-experiment

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/aris-monitor-experiment/SKILL.md

Quality

Content

71%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-sequenced, actionable monitoring workflow with concrete commands across SSH, Vast.ai, Modal, and W&B. It is largely efficient and clearly organized, though it is monolithic with no progressive disclosure into separate reference files and relies on placeholders the user must fill in.

Suggestions

Externalize the large W&B metrics block (Step 3.5) into a references file (e.g. references/wandb-metrics.md) and link to it from the main workflow, improving progressive disclosure and token efficiency.

Trim editorial commentary such as the blockquote about 'richer signal than just screen output' to keep the body lean and action-focused.

Provide at least one fully-resolved worked example (with concrete server/name values) so the command pattern is copy-paste ready rather than entirely placeholder-driven.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and minimal concept-explanation, but contains minor editorializing such as the blockquote 'This gives the auto-review-loop richer signal than just screen output' that could be trimmed.	4 / 5
Actionability	Provides concrete, real-syntax commands (ssh, screen -X hardcopy, vastai show instances, modal app list, wandb Python snippets), but heavy use of placeholders like <server>, <results_dir>, and <entity>/<project> requires substitution before execution.	4 / 5
Workflow Clarity	A clear Step 1 through Step 6 sequence with error-recovery hints ('If hardcopy fails...', 'If results look wrong, check training logs'); the monitoring task is read-only so the destructive-operation validation cap does not apply, though full validate-retry checkpoints are not formalized.	4 / 5
Progressive Disclosure	Content is well-sectioned into numbered steps, but it is a single monolithic file with no external references, and the substantial W&B Python block (Step 3.5) is inlined content that could arguably live in a separate reference file.	3 / 5
	Total	15 / 20 Passed

Description

83%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, well-constructed description that concretely states capabilities and provides explicit natural-language trigger phrases for when to use the skill. It is concise and largely free of fluff, with only minor room for broader keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the experiment-monitoring domain and three concrete actions ('Monitor running experiments, check progress, collect results'), but the verbs are somewhat high-level rather than fully comprehensive.	4 / 5
Completeness	Explicitly answers both what ('Monitor running experiments, check progress, collect results') and when ('Use when user says ...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('check results', 'is it done', 'monitor', 'wants experiment output') with good coverage, though a few common synonyms (e.g. 'training status', 'how's it going') are absent.	4 / 5
Distinctiveness Conflict Risk	The running-experiments niche with its specific triggers is mostly distinct, with only minor overlap risk against other experiment/training-related skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
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: OpenLAIR/dr-claw
Path: skills/aris-monitor-experiment/SKILL.md
Commit: cf5aa7a

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.