CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

exa-search

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

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

The body is a lean, highly actionable reference for a two-tool MCP skill: complete parameter tables, realistic call examples, and a copy-paste-ready server config, with no padding or background-concept explanation. The only trims available are mild redundancy between Core Tools and Usage Patterns, and the absence of any external reference file for the parameter/usage detail.

DimensionReasoningScore

Conciseness

The body stays lean — compact parameter tables, no explanations of concepts Claude already knows — but the Usage Patterns section partially repeats invocations already shown under Core Tools, and Tips restates tool-choice guidance, fitting 'efficient; minor instances of over-explanation that could be trimmed'.

4 / 5

Actionability

The MCP config JSON is copy-paste ready (with a clearly marked API-key placeholder), every tool call is shown with real query syntax (e.g., web_search_exa(query: "Vercel funding valuation 2026", numResults: 3, category: "company")), and parameter tables give types, defaults, and valid ranges (tokensNum 1000-50000), matching 'fully executable; copy-paste ready; specific examples cover the common cases'.

5 / 5

Workflow Clarity

This is a simple single-purpose skill and the single action — pick the right Exa tool and call it — is unambiguous: 'When to Activate' gives entry conditions, the MCP config block gives setup, and Tips disambiguates tool choice. No destructive or batch operations exist, so no validation steps are required.

5 / 5

Progressive Disclosure

Sections are clear and logically ordered (activation, setup, tools, patterns, tips, related skills), but the ~93-line body exceeds the simple-skill threshold and keeps all parameter detail and usage patterns inline with no one-level-deep references, fitting 'good structure; most content appropriately placed; minor organization gaps'.

4 / 5

Total

18

/

20

Passed

Description

78%Weight 40%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.

A well-formed description that clearly and explicitly answers both what the skill does and when to use it, with natural trigger phrases and third-person voice. Its only weaknesses are the single-verb action set and minor trigger overlap with general web-search/deep-research capabilities.

Suggestions

Replace the single verb 'search' with several distinct concrete actions to lift specificity (e.g., 'Finds web pages, retrieves code examples and API docs, researches companies, and locates professional profiles via the Exa MCP server').

Add one or two common natural synonyms for triggers, such as 'look up' or 'find', alongside 'web search' to broaden keyword coverage.

Sharpen the trigger boundary against adjacent skills (e.g., say 'quick targeted lookups' rather than 'AI-powered deep research') to reduce overlap with a dedicated deep-research skill.

DimensionReasoningScore

Specificity

"Neural search via Exa MCP for web, code, and company research" names the domain and mechanism, but the only concrete action is a single verb (search) applied to several targets, matching the anchor for 'names domain and 1-2 concrete actions, but not comprehensive' rather than the several-distinct-actions anchor at 4.

3 / 5

Completeness

"Neural search via Exa MCP for web, code, and company research" explicitly answers what it does, and "Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research" explicitly answers when with concrete trigger phrases — a direct match to the top anchor.

5 / 5

Trigger Term Quality

Natural phrases like "web search", "code examples", "company intel", "people lookup", and "deep research" give good keyword coverage, but common synonyms users would say ("find", "look up", "google it") are missing, matching the 'good keyword coverage; a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

The Exa/neural-search branding carves a mostly distinct niche, but "web search" and "AI-powered deep research" overlap with a generic web-search capability and the referenced deep-research skill, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor at 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

valeriibeck-star/claude-skills

Path

skills/exa-search/SKILL.md

Revision

0bda8b8

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill