CtrlK
BlogDocsLog inGet started
Tessl Logo

web-search-exa

Neural web search - find similar content, extract pages, and run deep research

52

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/research-tools/capabilities/web-search-exa/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 skill provides organized API reference coverage with concrete curl examples, but several examples are malformed and non-executable, and there is no explicit validation loop for the async research-task workflow. Content is well-sectioned but entirely inline with no bundle files.

Suggestions

Fix the broken curl JSON for /search, /findSimilar, and /contents so the request body is correctly inside the -d string and parameter names match the documented schema (e.g. numResults, not num_results).

Add an explicit create-task → poll-task validation workflow with a checkpoint (e.g. poll GET /research/v1/{researchId} until status is complete; handle failed/error statuses before returning results).

Remove the duplicated Capabilities list or the standalone restatement of the description to tighten conciseness, and consider moving the per-endpoint parameter reference into a bundled reference file.

DimensionReasoningScore

Conciseness

The body is mostly efficient reference material, but the Capabilities list duplicates the per-endpoint descriptions that reappear in Usage, and the standalone line 'Neural search engine for...' restates the frontmatter description.

3 / 5

Actionability

Concrete curl examples are provided per endpoint, but several are malformed (stray JSON lines outside the -d string for /search, /findSimilar, /contents) and parameter names diverge from the docs (num_results vs numResults), making them not copy-paste executable.

3 / 5

Workflow Clarity

Setup and per-endpoint usage are sequenced, but this is reference-style documentation; the async create-then-poll flow mentions polling 'until the task is finished' without an explicit validation checkpoint or error-recovery loop.

3 / 5

Progressive Disclosure

The ~200-line body is organized into clear sections (Setup, Capabilities, Usage, Use Cases, Discover More) with no bundle files, but the per-endpoint parameter reference is inlined rather than split into separate reference files.

3 / 5

Total

12

/

20

Passed

Description

66%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 and reasonably distinct, listing concrete capabilities with natural trigger terms. Its main weakness is the absence of an explicit 'when to use' clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause naming trigger situations (e.g. 'Use when the user needs neural web search, similar-content discovery, page extraction, or deep research with citations').

Include a couple of natural synonyms or phrasings users might say (e.g. 'search the web', 'look up similar pages') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('Neural web search') and three concrete actions ('find similar content, extract pages, and run deep research'), with only minor gaps in coverage relative to the full endpoint set.

4 / 5

Completeness

Clearly states what the skill does, but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes natural terms users would say ('web search', 'find similar content', 'extract pages', 'deep research'), though a few natural synonyms (e.g. 'search the web', 'look up') are missing.

4 / 5

Distinctiveness Conflict Risk

'Neural web search' carves a fairly distinct niche with minimal conflict risk, though 'web search' could overlap slightly with general search skills.

4 / 5

Total

15

/

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.

Validation15 / 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
gooseworks-ai/goose-skills
Reviewed

Table of Contents

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.