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

43%

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

23%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 content body is largely unfinished template scaffolding: the 'Structuring This Skill' TODO section and the generic resource-directory guidance were meant to be deleted before use. What remains of actual skill content is a brief, vague Usage section that never shows how to invoke the one real script in the bundle.

Suggestions

Delete the entire 'Structuring This Skill' TODO section and the template 'Resources (optional)' section, keeping only content that describes this skill's actual bundle (scripts/web_search.py).

Add an executable invocation example in the Usage section, e.g. `python scripts/web_search.py "OpenClaw skills"`, including argument format and what the script outputs.

State how to handle the script's output (a JSON blob containing tool_code to run via the web_search tool) so the workflow is complete and unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is dominated by an un-deleted '[TODO: Choose the structure...]' template section and a generic 'Resources (optional)' section with examples borrowed from other skills (PDF, DOCX, brand styling), none of which serves this skill's actual task.	1 / 5
Actionability	'The skill will execute the scripts/web_search.py script with the query' names a real script but provides no invocation command, argument format, or output handling; the only example is a dialogue line rather than an executable instruction.	2 / 5
Workflow Clarity	The single step (provide a query, run the script, receive results) is roughly conveyed, but as a simple single-purpose skill its one action is not unambiguous — no command syntax is given — and it is buried in template noise.	3 / 5
Progressive Disclosure	The actual bundle contains only scripts/web_search.py, yet the body's 'Resources' section describes references/ and assets/ directories that do not exist and is filled with other skills' examples, misrepresenting the bundle structure rather than organizing it.	2 / 5
	Total	8 / 20 Passed

Description

62%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 serviceable: it states what the skill does and includes an explicit 'Use when' clause in third person. Its weaknesses are circular trigger guidance (the 'when' restates the 'what'), thin keyword coverage, and a single capability described rather than a concrete set of actions.

Suggestions

Rewrite the 'when' clause with concrete user-side triggers, e.g. 'Use when the user asks to search Google, look something up on the web, or fetch Google search results for a query.'

Broaden natural trigger terms to include synonyms users actually say: 'web search', 'search the web', 'Google something', 'look up'.

Make the capability statement more concrete about what is returned (e.g. search result content/links) so it is distinguishable from generic web-fetch skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('web fetch request to Google') and a concrete action ('retrieve information from Google search results'), but this is essentially one action restated rather than a list of specific capabilities.	3 / 5
Completeness	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') are present, but the 'when' clause largely restates the 'what' rather than offering concrete trigger phrases.	4 / 5
Trigger Term Quality	'Google search results', 'query', and 'web fetch' are relevant keywords, but common natural variations users would say ('web search', 'search the web', 'look up') are missing.	3 / 5
Distinctiveness Conflict Risk	Scoped specifically to fetching Google search results, making it mostly distinct, though it could overlap with generic web-search or web-fetch skills.	4 / 5
	Total	14 / 20 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: a16301c

Reviewed: 1 day 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.