webfetch-google

Performs a web fetch request to Google based on a user-provided query. Use this skill when you need to retrieve information from Google search results.

Quality

51%

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 ./configs/microservice/bff-service/configs/agent-skills/clawhub/webfetch-google/SKILL.md

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is mostly leftover template scaffolding that was never filled in or deleted, with only a thin Overview and Usage section carrying actual content. The one real script reference is valid, but the skill lacks a concrete executable command and is padded with boilerplate.

Suggestions

Delete the 'Structuring This Skill' TODO block and the 'Resources (optional)' boilerplate, keeping only the sections this skill actually uses.

Add the concrete invocation, e.g. `python scripts/web_search.py "<query>"`, so the guidance is copy-paste ready.

Show a real example of the script's output format so Claude knows what to expect from the returned JSON.

Dimension	Reasoning	Score
Conciseness	The body is dominated by unfilled template scaffolding (the 'Structuring This Skill' TODO block and the 'Resources (optional)' boilerplate with examples borrowed from other skills) that the template itself instructs to delete, padding the context with unnecessary tokens.	1 / 3
Actionability	It names the concrete script ('scripts/web_search.py') and the underlying 'web_search' tool, but never shows the executable invocation (e.g. `python scripts/web_search.py "<query>"`), leaving a key detail missing.	2 / 3
Workflow Clarity	For a simple single-action skill the step is named ('execute the script with the query'), but the concrete command form is absent, so the sequence is clear conceptually yet incomplete in execution detail.	2 / 3
Progressive Disclosure	The bundle reference to scripts/web_search.py is real and one level deep, but the body is cluttered with inline template scaffolding that should have been removed, so organization is not clean enough for a 3.	2 / 3
	Total	7 / 12 Passed

Description

67%

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 clearly answers both what the skill does and when to use it with an explicit trigger clause, which is its main strength. Its weaknesses are a single-action scope, some technical jargon in the trigger phrasing, and moderate overlap risk with general web-search skills.

Suggestions

Add more concrete actions to broaden specificity, e.g. 'Returns titles, URLs, and snippets from Google search results.'

Replace the jargon 'web fetch request' with natural user terms like 'search Google' or 'run a Google search'.

Sharpen the trigger to reduce overlap with generic web-search skills, e.g. 'Use when the user specifically asks to search Google or fetch Google search result pages.'

Dimension	Reasoning	Score
Specificity	It names a concrete action ('Performs a web fetch request to Google') and domain ('Google search results'), but only describes a single action rather than listing multiple specific concrete actions like the score-3 anchor.	2 / 3
Completeness	It explicitly states both what ('Performs a web fetch request to Google based on a user-provided query') and when ('Use this skill when you need to retrieve information from Google search results') with an explicit trigger clause.	3 / 3
Trigger Term Quality	'Google search results' is a natural term a user might say, but 'web fetch request' is technical jargon users would not naturally say, and common variations like 'search Google' or 'Google something' are missing.	2 / 3
Distinctiveness Conflict Risk	Tying the skill to Google gives it a niche, but 'retrieve information from Google search results' could still overlap with generic web-search or web-fetch skills, so it is not clearly conflict-free.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/webfetch-google/SKILL.md
Commit: f618458

Reviewed: about 12 hours 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.