web-search

Implement web search capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to search the web, retrieve current information, find relevant content, or build applications with real-time web search functionality. Returns structured search results with URLs, snippets, and metadata.

Quality

73%

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 ./skills/web-search/SKILL.md

Quality

Content

63%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 is highly actionable with abundant executable examples, but it is significantly over-padded: a single API call is re-demonstrated across a dozen near-duplicate sections, and material that belongs in separate reference files is inlined. Tightening and splitting would materially improve token efficiency and navigation.

Suggestions

Collapse the redundant Basic/Custom-Count/Formatted/News/ResearchAssistant/Validation sections into one concise core example plus a short parameters table; remove wrapper classes that merely re-wrap functions.invoke('web_search').

Move the advanced use cases (SearchProcessor, ResearchAssistant, Express integration, AI-summary, caching, rate-limiting) into a references/ file (e.g. ADVANCED.md) and link to it from SKILL.md to fix progressive disclosure.

Trim generic restatements Claude already knows in 'Performance Tips', 'Security Considerations', and 'Remember' down to the few non-obvious points (e.g. backend-only constraint, instance reuse).

Dimension	Reasoning	Score
Conciseness	The ~900-line body repeatedly demonstrates the same trivial call (zai.functions.invoke('web_search', {query, num})) across Basic, Custom-Count, Formatted, SearchProcessor, News, ResearchAssistant, Validation, Caching, Rate-Limiting, Express, and AI-Summary sections — heavily padded with redundant wrapper examples rather than explaining known concepts, fitting the 2 anchor's "several unnecessary padded sections".	2 / 5
Actionability	Provides fully executable, copy-paste-ready code throughout (imports, ZAI.create, invoke calls, result processing) with concrete CLI commands and parameter tables covering the common cases, matching the 5 anchor.	5 / 5
Workflow Clarity	The single core action is unambiguous and decision guidance ("When to Use CLI vs SDK") plus multi-step examples (search-then-summarize) are clearly sequenced; minor validation gaps are acceptable since operations are read-only, keeping it just below the explicit-checkpoint 5 anchor.	4 / 5
Progressive Disclosure	Section headers and one real reference (scripts/web_search.ts, signaled in the body) provide some structure, but the bulk of content — advanced use cases, integration examples, and full API reference — is inlined in SKILL.md rather than split into separate reference files, matching the 3 anchor.	3 / 5
	Total	14 / 20 Passed

Description

83%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 well-crafted: third-person voice, explicit what-and-when structure, and concrete trigger phrases. It is slightly below top marks on specificity and trigger-term breadth, where a few more distinct operations and synonyms would push it to 5.

Dimension	Reasoning	Score
Specificity	Names the web-search domain and several concrete actions ("search for real-time information", "retrieve up-to-date content beyond the knowledge cutoff", "find the latest news and data", "Returns structured search results with URLs, snippets, and metadata"), but stops short of the comprehensive multi-operation list of the 5 anchor.	4 / 5
Completeness	Explicitly states what it does ("Implement web search capabilities... Returns structured search results with URLs, snippets, and metadata") and when to use it ("Use this skill when the user needs to search for real-time information... or find the latest news and data") with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("search for real-time information from the web", "find the latest news and data", "retrieve up-to-date content") with good coverage, but lacks the synonym/extension breadth of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear web-search niche with distinct triggers, but phrases like "real-time information" and "up-to-date content" create minor overlap risk with general research/info-retrieval skills, keeping it just below the 5 anchor.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (913 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: jjyaoao/HelloAgents
Path: skills/web-search/SKILL.md
Commit: 93e77ea

Reviewed: 5 days 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.