exa-search

Semantic search, similar content discovery, and structured research using Exa API. Use when you need semantic/embeddings-based search, finding similar content, or searching by category (company, people, research papers, etc.).

Quality

54%

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 ./skills/exa-search/SKILL.md

Quality

Content

18%Scale 1-5

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

This skill is essentially a placeholder that provides no actionable content. It contains no code examples, no API usage patterns, no configuration details, and no real workflow — everything meaningful is deferred to an external GitHub repository. The skill fails to teach Claude anything about how to actually use the Exa API for semantic search.

Suggestions

Add concrete, executable code examples showing how to perform semantic search, find similar content, and search by category using the Exa API (e.g., actual API calls with request/response formats).

Provide specific configuration instructions including how to set the API key environment variable (e.g., `export EXA_API_KEY=...`) and any required setup steps.

Replace the vague 3-step guide with a real workflow: show a complete example from API key setup through making a search request to processing results, with expected output formats.

Inline the essential examples and troubleshooting content rather than deferring everything to an external GitHub repository that Claude cannot access during conversations.

Dimension	Reasoning	Score
Conciseness	The content is relatively short but includes unnecessary sections like 'When to Use' that largely repeat the description, and 'Best Practices' with a single trivial bullet. The 'Troubleshooting' section adds no value. Some padding exists but it's not egregiously verbose.	3 / 5
Actionability	The skill provides almost no concrete, executable guidance. There are no code examples, no API usage patterns, no actual commands beyond the install command. 'Use naturally in Claude Code conversations' and 'Configure Exa API key' are entirely vague. All substantive content is deferred to an external GitHub repository.	1 / 5
Workflow Clarity	The 3-step guide ('Install, configure API key, use naturally') is essentially meaningless — it provides no real workflow, no specifics on configuration, no validation steps, and no concrete sequence of operations for performing searches.	1 / 5
Progressive Disclosure	The skill references a GitHub repository for examples and troubleshooting, but provides no bundle files and no actual content at any level. There's nothing to progressively disclose — the skill is a hollow shell pointing externally with no substantive inline content to anchor the references.	2 / 5
	Total	7 / 20 Passed

Description

91%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.

This is a strong skill description that clearly communicates what the skill does and when to use it. It includes excellent trigger terms covering natural user language and specific use cases. Minor improvements could include more specific output/action details and further differentiation from generic search skills.

Dimension	Reasoning	Score
Specificity	Lists several specific actions: semantic search, similar content discovery, and structured research. Mentions the Exa API by name. Could be more comprehensive by listing specific output formats or additional capabilities.	4 / 5
Completeness	Clearly answers both 'what' (semantic search, similar content discovery, structured research using Exa API) and 'when' (explicit 'Use when' clause with concrete trigger phrases like semantic/embeddings-based search, finding similar content, searching by category).	5 / 5
Trigger Term Quality	Excellent coverage of natural trigger terms: 'semantic search', 'embeddings-based search', 'similar content', 'category', 'company', 'people', 'research papers'. These are terms users would naturally use when needing this functionality.	5 / 5
Distinctiveness Conflict Risk	Fairly distinct due to the Exa API mention and focus on semantic/embeddings-based search. However, 'search' is broad and could overlap with other search-related skills. The specificity of 'Exa API' and 'embeddings-based' helps differentiate it.	4 / 5
	Total	18 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/exa-search/SKILL.md
Commit: 57c135b

Reviewed: 3 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.