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

56%

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

42%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 unfinished template scaffolding: it leaves placeholder guidance ("Structuring This Skill", "Resources") inline rather than replacing it with real skill content, and gives only minimal actionable instruction about running the search script. The single real bundle file (scripts/web_search.py) is referenced but the script itself is a near-empty stub.

Suggestions

Delete the 'Structuring This Skill' and 'Resources (optional)' template sections and replace them with real, skill-specific content.

Add a concrete invocation example showing the exact command to run scripts/web_search.py and what its JSON output means, since the current script is a 3-line stub.

Add a short validation/verification step (e.g., how to check the returned JSON or handle an empty result) so the workflow has an explicit checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is dominated by template scaffolding ("Structuring This Skill", "Resources (optional)") that explains concepts and gives generic guidance unrelated to this skill, noticeably verbose and padded with boilerplate that should have been removed.	2 / 5
Actionability	It only states that the skill will execute scripts/web_search.py and gives a single vague example, with no concrete command, invocation syntax, or output handling; this is high-level hinting without the specific steps to execute.	2 / 5
Workflow Clarity	A rough single-step sequence is implied (provide query -> run script -> fetch results), but it lacks validation checkpoints or explicit sequencing beyond the example, matching the anchor with a present but checkpoint-thin sequence.	3 / 5
Progressive Disclosure	There is section structure (Overview, Usage, Resources), but most of it is unused template guidance that should be separate or deleted, and the one real reference (scripts/web_search.py) is mentioned in prose rather than clearly signaled as a navigable bundle file.	3 / 5
	Total	10 / 20 Passed

Description

70%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 clear, uses third person, and answers both what and when, with relevant natural trigger terms. It is solid but slightly generic in the 'when' clause and not fully comprehensive in action coverage.

Dimension	Reasoning	Score
Specificity	It names the domain (web fetch / Google search results) and one concrete action ("retrieve information"), matching the anchor that names the domain with 1-2 concrete actions but is not comprehensive.	3 / 5
Completeness	It states both what it does ("Performs a web fetch request to Google based on a user-provided query") and when to use it ("Use this skill when you need to retrieve information from Google search results"), matching the anchor with both present but the 'when' clause fairly generic.	4 / 5
Trigger Term Quality	It includes natural terms a user might say ("Google search results", "query", "retrieve information") with good coverage; a few common synonyms or variants are missing, so it sits above the score-3 anchor but below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	It is mostly distinct, scoped specifically to fetching Google search results rather than generic web fetching, with only minor overlap risk against a general WebFetch capability.	4 / 5
	Total	15 / 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: 030c20b

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.