CtrlK
BlogDocsLog inGet started
Tessl Logo

web-search-andi

Fast, high-quality web search with intelligent ranking and instant answers

44

Quality

46%

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-andi/SKILL.md
SKILL.md
Quality
Evals
Security

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 is a usable, executable reference with a clear curl example and parameter list, but it is padded with repeated marketing copy, lacks validation checkpoints, and inlines a long parameter reference that would be better split out. No bundle files exist to offload detail.

Suggestions

Remove the duplicated 'Fast, high-quality search...' tagline from the Setup and Capabilities sections; keep it once.

Move the long parameter reference into a references/ file and link to it, keeping only the essential parameters inline.

Add a quick validation checkpoint after credential loading (e.g. echo/test the key) and note how to interpret a search response.

DimensionReasoningScore

Conciseness

The body is mostly efficient with executable curl examples, but the parameter list repeats the marketing phrase 'Fast, high-quality search with intelligent ranking, instant answers...' three times across Setup/Capabilities/Usage, which is padding.

3 / 5

Actionability

It provides a concrete, copy-paste curl command with auth headers and a populated request body, plus a parameter reference; minor gaps are error handling and response parsing guidance.

4 / 5

Workflow Clarity

Setup → search → discover flow is implied and the credential-loading steps are concrete, but there is no validation/checkpoint (e.g. verifying the API key loaded or that a search returned results) for what is effectively a batch/network operation.

3 / 5

Progressive Disclosure

Content is organized into sections and the long parameter table is inline rather than split into a reference file, with no bundle files present; structure exists but the bulk reference material is not separated.

3 / 5

Total

13

/

20

Passed

Description

36%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 names the web-search domain with a couple of feature phrases, but it lacks concrete capability enumeration and any explicit 'use when' trigger guidance. It is functional but thin and generic.

Suggestions

Add concrete actions the skill performs (e.g. 'runs web searches, returns ranked results with source extracts and instant answers').

Append an explicit trigger clause such as 'Use when the user asks to search the web, look something up, or find cited sources.'

Add natural synonyms users say (look up, research, find sources) to broaden trigger coverage.

DimensionReasoningScore

Specificity

Description states 'Fast, high-quality web search with intelligent ranking and instant answers' — it names the domain (web search) but the only concrete actions are generic 'search' and 'instant answers', with no enumeration of concrete capabilities.

2 / 5

Completeness

It gives a vague 'what' (web search with ranking/answers) but no 'when'/Use-when clause; per guidelines a missing trigger clause caps completeness at 3, and the weak 'what' pulls it to 2.

2 / 5

Trigger Term Quality

'web search' is a natural term users would say, and 'instant answers' is reasonable, but common variations like 'look up', 'research', or 'find sources' are absent.

3 / 5

Distinctiveness Conflict Risk

'web search' is a recognizable niche but the phrasing is broad enough that it could overlap with other search/research skills; not clearly differentiated.

3 / 5

Total

10

/

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.