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

85%

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

Quality

Content

80%Weight 40%Scale 1-3

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

A highly actionable, code-driven skill with executable diagnostics and a complete bundle script. Its main weaknesses are implicit validation checkpoints in the workflow and monolithic inline scripts that would benefit from extraction into bundle files.

Suggestions

Add an explicit validation checkpoint before sharing, e.g. a 'Step 4: Verify & redact' step that checks the bundle for API keys/PII (grep for EXA_API_KEY, $EXA_API_KEY) before packaging.

Extract the bundle script and TypeScript debug helper into scripts/ files (e.g. scripts/exa-debug-bundle.sh, scripts/debug-search.ts) and reference them from SKILL.md to improve progressive disclosure and reduce duplication.

De-duplicate the connectivity test between Step 1 and Step 3 by having the bundle script reuse or reference the same test logic.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-dominant with no concept explanation Claude already knows; every section earns its place through executable scripts and tables rather than prose padding. Borderline with level 2 because the curl connectivity test is duplicated between Step 1 and Step 3's bundle script, but the absence of unnecessary explanation keeps it at level 3.	3 / 3
Actionability	Provides fully executable, copy-paste-ready bash scripts (with shebang, set flags, real curl calls) and a complete TypeScript debug helper, matching the level-3 anchor for concrete executable guidance.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1-3), but validation checkpoints are implicit rather than built into the flow; the redaction/sensitive-data guidance is a post-hoc reminder, not an explicit 'verify bundle is redacted before sharing' checkpoint.	2 / 3
Progressive Disclosure	Sections are well-organized and cross-skill references in Next Steps are clearly signaled, but no bundle files exist and full scripts (the bundle script, TypeScript helper) are inline rather than split into scripts/ files, fitting the level-2 anchor 'content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 well-constructed description that clearly states purpose, use-conditions, and natural triggers in a distinct, low-conflict niche. The only weakness is that the listed capabilities are narrow variants of a single action rather than multiple distinct concrete actions.

Suggestions

Broaden the capability statement to enumerate distinct concrete actions, e.g. 'Collect Exa debug evidence, run connectivity and API diagnostics, and package a shareable support bundle for Exa issues.'

Consider naming the concrete bundle artifact in the what-clause (e.g. 'generates a redacted .tar.gz diagnostic bundle') to sharpen the action beyond 'collect evidence'.

Dimension	Reasoning	Score
Specificity	Names the Exa/debugging domain and a few near-synonymous actions ('Collect Exa debug evidence', 'preparing support tickets', 'collecting diagnostic information'), but these are variants of one core task rather than multiple distinct concrete actions as the level-3 anchor requires.	2 / 3
Completeness	Explicitly answers both what ('Collect Exa debug evidence for support tickets and troubleshooting') and when ('Use when encountering persistent issues, preparing support tickets...') with explicit triggers, matching the level-3 anchor.	3 / 3
Trigger Term Quality	Provides natural trigger phrases a user would actually say ('exa debug', 'exa support bundle', 'collect exa logs', 'exa diagnostic'), giving good coverage of likely invocations.	3 / 3
Distinctiveness Conflict Risk	The narrow Exa-debug niche plus 'exa'-prefixed trigger phrases make it clearly distinguishable and unlikely to fire for the wrong skill.	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
Path: plugins/saas-packs/exa-pack/skills/exa-debug-bundle/SKILL.md
Commit: 0540a62

Reviewed: about 2 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.