Name: code42
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

code42

Code42 integration. Manage data, records, and automate workflows. Use when the user wants to interact with Code42 data.

Quality

63%

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/code42/SKILL.md

Quality

Content

68%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 content is actionable and well-structured with executable commands throughout, but it omits validation/verification checkpoints for destructive or batch API operations and carries minor verbosity. Adding result-validation steps and trimming the introductory concept paragraph would raise both workflow clarity and conciseness.

Suggestions

Add explicit validation/verification steps after action runs and proxy requests (e.g., check the response status/error field and confirm the expected output before proceeding) to satisfy the destructive/batch feedback-loop requirement.

Remove the introductory 'Code42 is a data security platform...' paragraph and the filler 'Use action names and parameters as needed.' line to reduce token overhead.

Replace the placeholder CONNECTION_ID with a concrete worked example showing a real action run, so the 'Popular actions' section lists named actions rather than restating discovery.

Dimension	Reasoning	Score
Conciseness	The body is command-focused and mostly lean, with only minor over-explanation such as the introductory 'Code42 is a data security platform...' paragraph and the filler line 'Use action names and parameters as needed.'	4 / 5
Actionability	It provides concrete, executable membrane commands with a flag table and --json examples across install, auth, connection, action, and proxy flows, though CONNECTION_ID remains a placeholder and the 'Popular actions' section restates discovery rather than listing named actions.	4 / 5
Workflow Clarity	The connection flow is well-sequenced with state polling and retry feedback, but action/proxy execution — which can be destructive or batch-oriented — lacks explicit validation or verification of results, capping this dimension at 3 per rubric guidance.	3 / 5
Progressive Disclosure	The single-file body is well-organized into clearly headed sections, but at ~145 lines some reference material (clientAction schema details, the full flag table) could be split into separate files for cleaner navigation.	4 / 5
	Total	15 / 20 Passed

Description

57%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 has a clear product trigger and an explicit 'Use when' clause, satisfying both what and when, but its actions are generic rather than concrete Code42 capabilities. Tightening the verb list to real Code42 operations (legal holds, alerts, file events) would lift specificity and trigger quality.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Code42 actions such as placing legal holds, reviewing file/security events, and running saved searches.

Expand the 'Use when' clause with natural user phrases like 'alerts', 'legal hold', 'exfiltration', or 'file events' to improve trigger-term coverage.

Mention specific resource types (User, Device, Alert, Audit Log) from the body in the description to reduce conflict risk with other data/security skills.

Dimension	Reasoning	Score
Specificity	It names the Code42 domain but the listed actions — 'Manage data, records, and automate workflows' — are minimal and generic rather than concrete Code42-specific operations like legal holds or alert review.	2 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Code42 data') are present, though the 'when' is slightly generic rather than listing concrete trigger phrases.	4 / 5
Trigger Term Quality	'Code42' is a strong, specific trigger keyword and the 'Use when' clause names a natural phrase, but common variations a user would actually say (alerts, legal hold, exfiltration, file events) are missing.	3 / 5
Distinctiveness Conflict Risk	The specific product name 'Code42' gives it a clear niche with low conflict risk, but the generic 'manage data, records' wording introduces minor overlap with other data skills.	4 / 5
	Total	13 / 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/code42/SKILL.md
Commit: f484c82

Reviewed: ~12 hours 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.