CtrlK
BlogDocsLog inGet started
Tessl Logo

serper-search

Search the public web through Serper instead of the built-in WebSearch tool. Use when an agent needs current information, general web sources, or URLs not available from local files and project APIs. SERPER_API_KEY is available in the environment.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A tight, well-structured single-purpose skill body with executable code, clear failure-handling feedback loops, and clean sectioning. The only meaningful gap is that query-refinement guidance is described rather than shown as a concrete API parameter.

Suggestions

Show the concrete request-body or query parameter for refinement (e.g., "type":"search" vs "news", or a date-range field) alongside the "Refine the query" rule so the guidance is directly executable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence—no padding, no generic explanations—every line is an API-specific fact (endpoint, auth header, response fields, failure branches), matching anchor 5.

5 / 5

Actionability

A complete, copy-paste-ready curl command with endpoint, auth, content-type, and body covers the common case, but the "Refine the query when freshness, date…matters" guidance lacks the concrete API parameter to actually do it, leaving a minor gap per anchor 4.

4 / 5

Workflow Clarity

The single action (curl to the endpoint) is unambiguous, and the numbered Failure Handling section provides explicit conditional feedback loops while "Verify important claims against the linked source" acts as a validation checkpoint; the simple-skill exception applies since this is read-only, not destructive or batch.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references and clearly organized sections (Rules, API, Curl, Response Use, Failure Handling), satisfying the rubric's simple-skill exception for anchor 5.

5 / 5

Total

19

/

20

Passed

Description

78%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 concise, well-constructed description that clearly states both the capability and an explicit Use-when trigger clause. It is held back from the top tier only by single-action specificity and some trigger overlap with the built-in web search tool.

Suggestions

Add one or two concrete search variations (e.g., news vs. general, or date-filtered search) to the capability clause to lift specificity.

Include a couple more natural trigger phrases (e.g., "search the web", "look this up online", "find the latest on…") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("Search the public web through Serper") but offers no further distinct actions, matching anchor 3; it is not 4 because there is no list of several specific actions.

3 / 5

Completeness

It explicitly answers both what ("Search the public web through Serper instead of the built-in WebSearch tool") and when ("Use when an agent needs current information, general web sources, or URLs…") with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

"current information, general web sources, or URLs not available from local files and project APIs" are natural trigger phrases with good coverage, but common synonyms like "search the web" or "look this up" are absent, so it falls short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"instead of the built-in WebSearch tool" carves a clear niche, but the triggers ("current information", "general web sources") overlap the built-in web-search domain, giving minor overlap risk per anchor 4 rather than the minimal risk of anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentscope-ai/ReMe
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.