juicebox-debug-bundle

Collect Juicebox debug evidence. Trigger: "juicebox debug", "juicebox support ticket".

Quality

56%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/saas-packs/juicebox-pack/skills/juicebox-debug-bundle/SKILL.md

Quality

Content

64%

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

This is a solid, actionable debug skill with executable scripts and a useful diagnostic table. Its main weaknesses are the lack of validation checkpoints in the workflow (e.g., verifying archive integrity before cleanup) and some redundancy between the bash script and TypeScript health check. The content could be tightened by removing the duplicate health check and trimming the overview.

Suggestions

Add a validation step after tar creation (e.g., `tar -tzf "$BUNDLE.tar.gz" > /dev/null && rm -rf "$BUNDLE"`) to verify archive integrity before deleting the source directory.

Remove or move the TypeScript health check to a separate reference file — it duplicates the bash script's functionality and adds ~15 lines without new information.

Fix the 'juicebox-common-errors' reference to use a proper relative path or markdown link format.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary elements — the TypeScript health check duplicates functionality already in the bash script, and the overview paragraph explains what a debug bundle does which Claude can infer. The common issues table is valuable and dense though.	2 / 3
Actionability	The bash script is fully executable and copy-paste ready with proper error handling. The analysis commands are concrete with specific jq queries. The common issues table provides specific, actionable fixes for each symptom.	3 / 3
Workflow Clarity	The collection and analysis steps are clear and sequenced, but there's no validation checkpoint after collection (e.g., verifying the bundle contains expected files or that API responses aren't empty). The destructive rm -rf after tar has no verification that the archive was created successfully beyond set -e.	2 / 3
Progressive Disclosure	The content is reasonably structured with clear sections, but the TypeScript health check could be a separate reference file. The 'See juicebox-common-errors' reference is good but the link format is unclear (not a proper file path or markdown link). No bundle files exist to offload content to.	2 / 3
	Total	9 / 12 Passed

Description

47%

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 extremely terse and product-specific. While its narrow scope to 'Juicebox' makes it distinctive and unlikely to conflict with other skills, the lack of detail about what debug evidence is collected and what concrete actions are performed makes it weak on specificity and completeness.

Suggestions

Expand the 'what' by listing specific actions, e.g., 'Collects logs, configuration files, error traces, and system state for Juicebox debugging and support tickets.'

Add a 'Use when...' clause with broader trigger scenarios, e.g., 'Use when the user needs to troubleshoot Juicebox issues, gather diagnostic information, or prepare evidence for a Juicebox support ticket.'

Include additional natural trigger terms like 'juicebox logs', 'juicebox troubleshoot', 'juicebox diagnostics', 'juicebox error'.

Dimension	Reasoning	Score
Specificity	The description says 'Collect Juicebox debug evidence' which is a single vague action. It doesn't specify what kind of evidence, what concrete steps are involved, or what outputs are produced.	1 / 3
Completeness	It has a minimal 'what' (collect debug evidence) and explicit trigger terms serving as a 'when' clause, but the 'what' is too thin and the 'when' is not framed as a 'Use when...' clause — it's just labeled 'Trigger'. The triggers partially satisfy the 'when' requirement but lack context about scenarios.	2 / 3
Trigger Term Quality	It includes two explicit trigger phrases ('juicebox debug', 'juicebox support ticket') which are relevant and natural, but coverage is limited — missing variations like 'juicebox logs', 'juicebox troubleshoot', 'juicebox issue', or 'debug info'.	2 / 3
Distinctiveness Conflict Risk	The skill is highly specific to 'Juicebox' which is a named product, making it very unlikely to conflict with other skills. The trigger terms are distinctive and narrowly scoped.	3 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 4e7c0e3

Reviewed: 2 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.