web-search-jina

Jina Search - fast web search returning SERP results

Quality

62%

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/research-tools/capabilities/web-search-jina/SKILL.md

Quality

Content

57%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 has genuinely executable setup and search commands, but is undermined by a truncated Capabilities entry, an instruction ("Use s.jina.ai") that never resolves into actual steps, and a Discover More section that issues two identical requests as if they were different operations. Fixing the broken fragments and clarifying response handling would move this from serviceable to solid.

Suggestions

Fix the truncated Capabilities entry ("**Search**: Use s") and either complete it or remove the section.

Turn "Use s.jina.ai to search the web and get SERP" into a concrete instruction, and show a sample response (fields returned, how to cite URLs/snippets) so the workflow is unambiguous.

Repair the Discover More block: the two curl commands are identical payloads labeled as different operations — differentiate them or collapse to one clearly labeled command, and move the stray "List all endpoints" text into the code block as a comment.

Dimension	Reasoning	Score
Conciseness	The body is lean with executable snippets and no explanations of concepts Claude already knows, matching anchor 4. It falls short of 5 because of the orphaned, redundant line "Simple, fast web search using Jina's search foundation." placed awkwardly after the Setup section.	4 / 5
Actionability	The Setup section and Search curl example are concrete and executable, but "Search: Use s" is truncated, "Use s.jina.ai to search the web and get SERP" never explains how, and the Discover More block sends two identical payloads while labeling them as different operations ("List all endpoints" vs "# Get endpoint details"). This matches anchor 3's incomplete guidance, not anchor 4's "minor gaps".	3 / 5
Workflow Clarity	The implied sequence (read credentials, export env vars, run curl) is present, but the flow is disrupted by the broken Capabilities section, absent response-handling guidance (what the SERP response looks like or how to use it), and confusing discovery commands. For a single-purpose skill to score higher, the single action must be unambiguous, which it is not.	3 / 5
Progressive Disclosure	The skill is short with no bundle files, so it could score 5 on well-organized sections alone, but organization is mediocre: the Capabilities section is a broken fragment, a redundant one-liner floats between sections, and Discover More duplicates commands. This matches anchor 3's "some structure but could be better organized", not anchor 4.	3 / 5
	Total	13 / 20 Passed

Description

50%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 short and truthful but under-specified: it conveys a basic "what" with one concrete action and no "when to use" guidance. Adding a "Use when..." clause and natural trigger phrases would raise completeness and trigger-term quality substantially.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when the user asks to search the web, look up current information, or verify facts online."

List the concrete capabilities (e.g. "Run web searches and return ranked SERP results: titles, URLs, and snippets") to improve specificity.

Include natural trigger synonyms such as "search the internet", "look this up", or "find sources" to reduce overlap with other search skills and improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"fast web search returning SERP results" names the domain and a single concrete action, matching anchor 3. It is not a 4 because no additional specific actions are listed, and not a 2 because the action described is concrete rather than generic.	3 / 5
Completeness	The "what" is stated ("fast web search returning SERP results") but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the "what" is clear rather than vague.	3 / 5
Trigger Term Quality	Terms like "web search" and "SERP" are relevant, but common natural variations ("search the internet", "look this up", "find sources online") are missing, matching anchor 3. It lacks the synonym coverage of anchor 4 but has more than the single generic keyword of anchor 2.	3 / 5
Distinctiveness Conflict Risk	"Jina Search" names a specific service giving it some distinctness, but "web search" is broad and would overlap with any other web-search skill, matching anchor 3. It is not a 4 because the description offers no distinct trigger phrases beyond the generic domain.	3 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/research-tools/capabilities/web-search-jina/SKILL.md
Commit: cc3e518

Reviewed: 7 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.