exa-debug-bundle

Collect Exa debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Exa problems. Trigger with phrases like "exa debug", "exa support bundle", "collect exa logs", "exa diagnostic".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

A highly actionable skill body built on complete, executable code with clear sequencing and a useful error table. Its main gaps are the duplicated connectivity test, feedback loops separated from the workflow, and a standalone script kept inline rather than externalized as a bundle file.

Suggestions

Deduplicate the connectivity curl test: have the Step 3 bundle script source or reuse the Step 1 logic rather than repeating the full curl block.

Move the bundle script into a scripts/ file (e.g. scripts/exa-debug-bundle.sh) and reference it from the body, improving progressive disclosure for a skill this long.

Integrate a brief validate-fix-retry loop inline (e.g. 'if UNHEALTHY, consult the error table, fix, and rerun Step 1') so the recovery path is part of the workflow rather than only the separate table.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code with no concept-explaining fluff, but the Step 1 connectivity curl test is duplicated inside the Step 3 bundle script, so it could be tightened.	2 / 3
Actionability	Three complete, copy-paste-ready code blocks (bash connectivity test, TypeScript debug function, bash bundle script) plus a concrete cause/solution error table give fully executable guidance.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1 -> Step 2 -> Step 3) with a HEALTHY/UNHEALTHY status check and a review-before-sharing note, but the error-recovery feedback loop lives in a separate table rather than an integrated validate-fix-retry cycle.	2 / 3
Progressive Disclosure	Sections are well organized, but for a >50-line skill a full standalone bash script (with its own shebang, 'exa-debug-bundle.sh') is inlined rather than split into a bundle file, and no external references offload the detail.	2 / 3
	Total	9 / 12 Passed

Description

90%

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

A strong, third-person description with an explicit 'Use when' clause and natural trigger phrases that make it highly discoverable and distinct. Its only weakness is specificity, as it describes essentially one action rather than enumerating multiple concrete capabilities.

Suggestions

Enumerate a few more concrete actions in the opening sentence (e.g., 'Run connectivity tests, capture request/response details, and package a redacted diagnostic archive') to lift specificity toward the score-3 anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('Exa debug') and a single concrete action ('Collect Exa debug evidence for support tickets and troubleshooting'), but does not list multiple distinct concrete actions as the score-3 anchor requires.	2 / 3
Completeness	Clearly states what it does and includes an explicit 'Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information' clause plus trigger phrases, satisfying both what and when.	3 / 3
Trigger Term Quality	Provides varied, natural phrases a user would actually say — 'exa debug', 'exa support bundle', 'collect exa logs', 'exa diagnostic' — giving good coverage of trigger terms.	3 / 3
Distinctiveness Conflict Risk	The Exa-specific scope and 'exa'-prefixed trigger phrases form a clear niche that is unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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
Commit: 02d6341

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.