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%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 well-structured with strong progressive disclosure and largely actionable, executable guidance. The main gap is the absence of explicit validation/verification checkpoints for the batch extraction workflow, which caps workflow clarity.

Suggestions

Add an explicit verify/validation step for batch extraction (e.g., after `exa_extract.py` runs on multiple URLs, check the output JSON for per-URL success/failure and retry only failed URLs).

Trim concept-level explanations Claude already knows — e.g., the sentence on Exa's index and the rationale for preferring peer-reviewed sources — to tighten conciseness.

Include one inline example of an actual search invocation with a query in SKILL.md (not just `--help`) so the primary capability is runnable without opening a reference file.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — routing table, decision guide, and executable `uv run` commands carry the body — but includes mild over-explanation (e.g., "Exa's index combines high-quality keyword and semantic retrieval..." and the academic-source-value rationale) that could be trimmed.	4 / 5
Actionability	Provides concrete, copy-paste-ready commands (`uv run --with exa-py python "$SKILL_PATH/scripts/exa_search.py" --help`, `export EXA_API_KEY=...`) and routes to detailed reference files; minor gap is that no inline example of an actual query invocation appears in SKILL.md itself.	4 / 5
Workflow Clarity	Routing and setup are sequenced with a clear decision table, but the skill performs batch URL extraction and SKILL.md shows no explicit validation/verification checkpoint after batch operations, so the batch-operation cap holds it at 3.	3 / 5
Progressive Disclosure	Clear overview (routing + setup) with well-signaled one-level-deep references to real files `references/web-search.md` and `references/web-extract.md`, plus a "Files in this skill" manifest — content is appropriately split and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

92%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.

The description is specific, complete, and distinctive, clearly stating both the toolkit's capabilities and its trigger conditions in third person. Trigger term coverage is strong but could add a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain plus multiple concrete capabilities — "search the web or fetch/extract URL content", "semantic lookups, research, current info", "fetching pages, articles, academic PDFs in batch", "scholarly filtering via category=research paper" — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ("Web toolkit powered by Exa... web search and URL extraction") and when ("Use this skill when the user needs to search the web or fetch/extract URL content", "Triggers on requests to search, look up, fetch a page, or extract an article") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users say ("search the web", "look up", "fetch a page", "extract an article") but misses common synonyms like "scrape"/"crawl" and any file extensions, fitting the 'good coverage, a few terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — "tuned for scientific and technical content", "scholarly filtering via category=research paper", "academic PDFs in batch" — with distinct triggers and minimal overlap with generic search skills.	5 / 5
	Total	19 / 20 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
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/exa-search/SKILL.md
Commit: b2a92ba

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.