juicebox-data-handling

Juicebox data privacy and GDPR. Trigger: "juicebox data privacy", "juicebox gdpr".

Quality

56%

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 ./plugins/saas-packs/juicebox-pack/skills/juicebox-data-handling/SKILL.md

Quality

Content

65%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 is concise and offers concrete, mostly-executable code for the core data operations, but it is a topical reference rather than a sequenced workflow and lacks validation checkpoints around its batch and destructive operations. The implementation-guide.md reference is orphaned, never linked from the body, undercutting progressive disclosure.

Suggestions

Reframe the import/export/deletion sections as a sequenced workflow with explicit validation checkpoints (e.g. validate profiles before storage, verify deletion cascaded across all tables).

Link the existing references/implementation-guide.md from the body (e.g. 'See implementation-guide.md for the data-classifier, PII handler, and retention-policy modules') instead of inlining overlapping code.

Fix the CSV export to escape values containing commas/quotes, and either inline a field-level encryption example or point to where the encryption implementation lives.

Dimension	Reasoning	Score
Conciseness	The body is lean: tight tables and executable TypeScript with no padding explaining what GDPR or PII is, and the Overview is substantive rather than tutorial. It is not a 5 because the Overview paragraph and a few comments could still be trimmed.	4 / 5
Actionability	Concrete, mostly executable TypeScript is provided for import, export, and validation covering the common cases. It is not a 5 because of minor gaps such as unescaped CSV values and the absence of an actual encryption implementation in the body despite it being required.	4 / 5
Workflow Clarity	The body is organized by topic rather than as a sequenced workflow, and the batch import and destructive GDPR deletion paths have no wired validation checkpoints. Per the rubric, batch/destructive operations without validation cap workflow clarity at 3.	3 / 5
Progressive Disclosure	A references/implementation-guide.md bundle file exists with deeper code, but it is never referenced or signaled from the body, and the body inlines code that overlaps with it. This matches the anchor where references are present but not clearly signaled and content that should be separate is inline.	3 / 5
	Total	14 / 20 Passed

Description

48%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 identifies a clear, branded niche with explicit trigger phrases, but it is thin: it names the domain without stating any concrete actions and offers only two narrow trigger terms. Adding verbs describing what the skill does and a few more natural trigger variations would materially raise the score.

Suggestions

Add concrete verbs describing capabilities, e.g. 'Classify, encrypt, export, and purge Juicebox people data for GDPR/CCPA compliance'.

Expand the trigger list with natural variations users might say, such as 'juicebox pii', 'juicebox data deletion', or 'juicebox candidate privacy'.

Make the 'what' explicit by stating the data-handling actions (classification, consent tracking, deletion, field-level encryption) rather than only naming the topic.

Dimension	Reasoning	Score
Specificity	The description 'Juicebox data privacy and GDPR' names the domain but contains no concrete actions or verbs, matching the anchor where actions are minimal or generic. It is not a 1 because it identifies a specific domain rather than being entirely vague, and not a 3 because no concrete capabilities are enumerated.	2 / 5
Completeness	An explicit Trigger clause answers 'when' to use the skill, but the 'what' is only a vague topic label with no described actions. The explicit trigger guidance lifts it above a 2, but the vague 'what' prevents a 4.	3 / 5
Trigger Term Quality	The trigger phrases 'juicebox data privacy' and 'juicebox gdpr' are natural terms a user might say, but only two narrow phrases are provided with no synonyms or common variations. This matches the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The Juicebox-branded trigger phrases create a clear niche with minimal conflict risk against other skills, though the broad 'data privacy and GDPR' topic carries minor overlap risk with general privacy skills. It is not a 5 because the topic wording is not fully distinctive.	4 / 5
	Total	12 / 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: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/juicebox-pack/skills/juicebox-data-handling/SKILL.md
Commit: 8585d6d

Reviewed: 6 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.