exa-search

Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filtering) and URL extraction (fetching pages, articles, academic PDFs in batch). Use this skill for web-related tasks when the user wants high-quality search or scholarly filtering via category=research paper. Triggers on requests to search, look up, fetch a page, or extract an article.

Quality

82%

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

72%

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

A well-structured routing overview with executable setup commands and excellent progressive disclosure. It loses points on conciseness (some general-knowledge filler) and workflow clarity (operational checkpoints live in the references, not the body).

Suggestions

Trim the "Academic source priority" section to the two actionable Exa levers (category and include-domains) and drop the general peer-reviewed-over-blog guidance Claude already knows.

Add a brief inline validation checkpoint for batch extraction (e.g., verify returned contents count matches input URL count) so the body carries a feedback loop rather than deferring entirely to references.

Dimension	Reasoning	Score
Conciseness	Mostly efficient routing and setup, but the "Academic source priority" list (peer-reviewed over blog posts) and "Exa's index combines high-quality keyword and semantic retrieval..." explain general knowledge Claude already has and could be tightened.	2 / 3
Actionability	Provides copy-paste executable commands (uv run --with exa-py ..., export EXA_API_KEY=..., dotenv -f .env run ...) plus specific flags (--category "research paper", --include-domains), meeting the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Routing and setup are clearly sequenced with a --help verification step, but the actual search/extract workflows and their validation checkpoints are deferred to the reference files rather than present in the body.	2 / 3
Progressive Disclosure	SKILL.md is a clean overview with a routing table pointing one level deep to references/web-search.md and references/web-extract.md (both verified to exist), a decision guide, and a "Files in this skill" index — content is appropriately split and easy to navigate.	3 / 3
	Total	10 / 12 Passed

Description

92%

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, specific description with explicit what/when guidance and good trigger-term coverage. Its only weakness is that the broad web-search/fetch triggers create some overlap with built-in web capabilities.

Suggestions

Tighten the primary trigger to emphasize the scholarly/Exa distinction, e.g. "Use when the user wants high-quality or academic web search via Exa, or batch URL/PDF extraction — prefer built-in WebSearch for simple lookups."

Lead with the differentiating capability (scientific/technical search + research-paper filtering) before the generic web-search trigger to reduce conflict with built-in tools.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "search the web", "fetch/extract URL content", "fetching pages, articles, academic PDFs in batch", "scholarly filtering" — matching the anchor for several specific actions rather than vague language.	3 / 3
Completeness	Explicitly states what ("Web toolkit... web search... URL extraction") and when ("Use this skill when the user needs to search the web... Triggers on requests to search, look up, fetch a page, or extract an article"), satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "search", "look up", "fetch a page", "extract an article", "research", "current info" — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The Exa/scholarly niche is distinct, but the primary triggers "search the web" and "fetch a page" overlap with built-in WebSearch/WebFetch, so it could still fire for generic web tasks handled by other tools.	2 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/exa-search/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.