CtrlK
BlogDocsLog inGet started
Tessl Logo

monitor-experiment

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

73

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The content is highly actionable with a clear, checkpointed workflow and clean section organization. Its main weakness is conciseness: explanatory commentary and large inline code blocks could be trimmed or split out.

Suggestions

Move the large inline W&B Python snippets and the Modal/Vast/Feishu branches into reference files (e.g. references/wandb.md), keeping only the core screen/SSH workflow in SKILL.md.

Trim the opening cadence blockquote and the "What to extract" prose to essentials, since Claude can infer what training-loss/eval-metric signals mean.

Fix or remove the dangling reference to ../shared-references/external-cadence.md, which does not resolve to a real file.

DimensionReasoningScore

Conciseness

The body is mostly lean executable commands, but the opening cadence blockquote, the verbose "What to extract" commentary, and the large inline W&B Python blocks add tokens Claude could do without or that could be referenced out.

2 / 3

Actionability

Provides copy-paste-ready commands (ssh screen -ls, hardcopy, vastai show instances, modal app logs) and complete W&B API Python snippets, matching the fully-executable anchor.

3 / 3

Workflow Clarity

A clear numbered Steps 1-6 sequence with conditional checkpoints ("If hardcopy fails...", "If JSON results exist...") and error-handling notes; monitoring is non-destructive so no destructive-loop cap applies.

3 / 3

Progressive Disclosure

No bundle files exist; the self-contained body is organized into well-labeled sections with one-level-deep signaled references, satisfying the simple-skill note. A broken external link (shared-references/external-cadence.md) is a minor defect not captured by the bundle-structure anchors.

3 / 3

Total

11

/

12

Passed

Description

100%

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

The description is concise, action-oriented, and gives explicit natural-language triggers covering both what the skill does and when to invoke it. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Monitor running experiments, check progress, collect results"), matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.

3 / 3

Completeness

Explicitly answers both what (monitor/check/collect) and when via an explicit "Use when user says..." trigger clause, satisfying the full what-and-when anchor.

3 / 3

Trigger Term Quality

Provides several natural user phrasings ("check results", "is it done", "monitor", "wants experiment output") that a user would actually say, giving good coverage rather than a lone keyword.

3 / 3

Distinctiveness Conflict Risk

The experiment-monitoring niche with its distinct trigger phrasings is unlikely to fire for unrelated skills; it does not fall to the overlap-prone 2 anchor.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 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

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

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.