CtrlK
BlogDocsLog inGet started
Tessl Logo

web-search

Search the web, platforms, and datasets. Use when asked to search, find, look up, research, or discover information from the web, YouTube, Amazon, eBay, news, academic sources, or any online platform.

58

Quality

68%

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/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 body is a broad, well-sectioned API catalog with useful 'Best for' framing, but it is undermined by systematically malformed curl JSON payloads, heavy boilerplate repetition, and an incoherent Discover More section. It functions as a reference wall rather than a lean overview with deferred detail.

Suggestions

Fix the broken JSON payloads (e.g., Tavily /search, /crawl, Exa /search, /findSimilar, Linkup /search) where the object is closed before the fields — merge fields inside the body object so each curl is executable as-is.

De-duplicate the repeated auth/endpoint boilerplate by stating the common curl invocation once and showing only the per-API `{"api","path","body/query"}` deltas.

Split the six per-API references into separate reference files (e.g., references/tavily.md, references/searchapi.md) and keep SKILL.md as a lean overview with one-level-deep links; rewrite 'Discover More' as coherent, working commands.

DimensionReasoningScore

Conciseness

Accurate and free of concept padding, but ~20 near-identical curl blocks repeat the same auth/endpoint boilerplate across six APIs; a shared pattern plus per-API deltas would be markedly leaner.

3 / 5

Actionability

Concrete curl commands with real parameter values are provided per engine, but many JSON payloads are malformed (object closed early, fields dangled outside the body), so a substantial fraction is not copy-paste executable.

3 / 5

Workflow Clarity

Setup-to-API-to-Tips sequencing exists with Step 1/Step 2 for async research, but cross-API selection guidance is loose, output handling is absent, and the 'Discover More' section mixes CLI and JSON fragments incoherently.

3 / 5

Progressive Disclosure

Clear section headers organize the material, but ~390 lines of per-API reference are inlined in SKILL.md with no bundle files or one-level-deep references to split the bulk out.

3 / 5

Total

12

/

20

Passed

Description

86%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 strong, trigger-rich description that clearly states both capability and use-conditions with comprehensive natural-language synonyms. The only weakness is that it asserts a single action (search) across many platforms rather than naming multiple distinct capabilities.

DimensionReasoningScore

Specificity

Names the search domain richly ('web, platforms, and datasets') with concrete targets (YouTube, Amazon, eBay, news, academic sources), but only one concrete action ('Search') rather than multiple distinct actions.

3 / 5

Completeness

Explicitly answers what ('Search the web, platforms, and datasets') and when with a concrete 'Use when...' clause enumerating trigger verbs and platforms.

5 / 5

Trigger Term Quality

Comprehensive natural-language verb coverage ('search, find, look up, research, or discover') plus broad platform terms including synonyms; matches the anchor for comprehensive synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Specific platform triggers (YouTube, Amazon, eBay, ad libraries) carve a niche, though 'any online platform' breadth creates minor overlap risk with narrower search skills.

4 / 5

Total

17

/

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.