exa-core-workflow-a

Execute Exa neural search with contents, date filters, and domain scoping. Use when building search features, implementing RAG context retrieval, or querying the web with semantic understanding. Trigger with phrases like "exa search", "exa neural search", "search with exa", "exa searchAndContents", "exa query".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

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

A code-dense, actionable skill body with excellent executable examples and clean organization. Its main weakness is workflow framing: the five 'Steps' are parallel recipes presented as a sequence without validation checkpoints.

Suggestions

Reframe the five 'Steps' as independent recipe sections (e.g., '### Basic Neural Search', '### Content Extraction') instead of an implied sequential workflow, since they have no dependencies on each other.

Add explicit validation checkpoints — e.g., after each search, check the results array length and relevance scores before proceeding, turning the Error Handling table into inline verify-then-act feedback loops.

Resolve the livecrawl contradiction in Step 5: the comment says 'maxAgeHours controls freshness (replaces deprecated livecrawl)' yet the code uses `livecrawl: 'preferred'` — use the current parameter or clarify which is deprecated.

Dimension	Reasoning	Score
Conciseness	Lean and code-forward; it assumes Claude's competence and avoids explaining basic concepts, with dense tables and inline comments that earn their place rather than padding.	3 / 3
Actionability	Each of the five sections provides complete, executable TypeScript with real parameters and copy-paste-ready examples covering search, contents, filters, categories, and freshness.	3 / 3
Workflow Clarity	Content is organized into labeled 'Steps', but they are independent parallel recipes rather than a dependent sequence, and there are no explicit validation/verification checkpoints despite an Error Handling table that implies error recovery.	2 / 3
Progressive Disclosure	A single, well-organized file with clear sections (Overview, Search Types, Instructions, Error Handling, Examples, Resources) and one-level external links to Exa docs; no nested references and no bundle files to defer.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, well-formed description that states concrete capabilities, gives explicit 'Use when' guidance, and supplies natural trigger phrases in third-person voice. It clearly distinguishes itself as the Exa-specific search skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Execute Exa neural search with contents, date filters, and domain scoping' — naming distinct capabilities rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Execute Exa neural search with contents, date filters, and domain scoping') and when ('Use when building search features, implementing RAG context retrieval, or querying the web with semantic understanding').	3 / 3
Trigger Term Quality	Provides natural phrases users would say ('exa search', 'exa neural search', 'search with exa', 'exa searchAndContents', 'exa query'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Exa-specific niche with distinct 'exa' trigger phrases makes it unlikely to fire for unrelated search skills.	3 / 3
	Total	12 / 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: 3022dd3

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.