Name: comet-ml
Rating: 59.2 (1 reviews)
Author: membranedev

comet-ml

Comet ML integration. Manage data, records, and automate workflows. Use when the user wants to interact with Comet ML data.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/comet-ml/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.

The body delivers executable, well-sequenced Membrane CLI guidance with a solid connection-state feedback loop, but it is entirely monolithic with no reference files and carries minor redundancy and a few placeholder gaps.

Suggestions

Extract the Comet ML entity-type overview and the proxy flag table into a references/ file (e.g. REFERENCE.md) and link to it from the body to improve progressive disclosure.

De-duplicate the action-list instructions (the command appears in both 'Searching for actions' and 'Popular actions') and remove the filler line 'Use action names and parameters as needed.'

Reconcile the inconsistent step numbering ('1b', 'Step 2' references) into a single coherent numbered sequence.

Dimension	Reasoning	Score
Conciseness	Mostly lean CLI commands with minimal padding, though there is redundancy (action list shown twice) and a filler line ('Use action names and parameters as needed') plus an inlined entity-type list that could be trimmed.	4 / 5
Actionability	Concrete, copy-paste-ready commands throughout (install, login, connection ensure, action run with --input, proxy flags table) with only minor gaps like unexpanded placeholders (CONNECTION_ID, QUERY).	4 / 5
Workflow Clarity	Clear sequence (install -> auth -> connect -> poll states -> search -> run/proxy) with a polling feedback loop over READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR, though section numbering is slightly inconsistent and there is no validation checkpoint on action execution itself.	4 / 5
Progressive Disclosure	Well-organized with clear headers, but with no bundle files present all content is inlined in a single ~150-line file, including an entity-reference list and a proxy-flag table that could live in separate references.	3 / 5
	Total	15 / 20 Passed

Description

66%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.

The description names a specific platform and includes both a capability summary and a Use-when trigger, but the actions are somewhat generic and trigger-term coverage misses common synonyms like 'experiments' or 'model tracking'.

Suggestions

Replace generic actions ('Manage data, records') with concrete Comet ML capabilities such as 'track experiments, log metrics and parameters, compare models, and manage datasets'.

Expand the Use-when clause with natural trigger phrases users actually say, e.g. 'when the user wants to track ML experiments, log metrics, or compare models'.

Add common synonyms/file extensions to the trigger terms (experiments, model tracking, monitoring) to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Comet ML) and a couple of concrete actions ('Manage data, records, and automate workflows'), but 'data, records' are generic and coverage is not comprehensive.	3 / 5
Completeness	Clearly answers 'what' (manage data, records, automate workflows) and provides an explicit 'Use when the user wants to interact with Comet ML data' trigger, though the 'when' could be more specific.	4 / 5
Trigger Term Quality	Includes the natural keyword 'Comet ML' and an explicit Use-when clause, but misses common variations users would say like 'experiments', 'model tracking', or 'monitoring'.	3 / 5
Distinctiveness Conflict Risk	'Comet ML' is a clearly named niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/comet-ml/SKILL.md
Commit: f484c82

Reviewed: 4 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.