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

62%

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 ./glm-skills/web-search/SKILL.md

Quality

Content

42%

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

The skill provides excellent actionable code examples with complete, executable implementations, but is severely bloated with redundant examples and unnecessary explanations. The content would benefit greatly from splitting advanced use cases, integration examples, and best practices into separate referenced files, reducing the main skill to a concise quick-start guide.

Suggestions

Reduce main SKILL.md to ~100 lines covering basic usage, CLI commands, and the SearchFunctionResultItem type, moving advanced patterns to ADVANCED.md

Extract integration examples (Express.js, AI Summary) to a separate INTEGRATIONS.md file with clear references

Remove redundant code examples - the basic search pattern is shown 5+ times with minor variations

Add explicit validation steps in multi-step workflows like 'Search and Summarize' (e.g., validate search returned results before proceeding to summarization)

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 700+ lines with extensive redundancy. Multiple implementations of the same concepts (basic search shown 5+ times), unnecessary class wrappers, and explanations of concepts Claude knows (caching, rate limiting, Express.js setup). Could be reduced to ~100 lines.	1 / 3
Actionability	Provides fully executable, copy-paste ready code examples throughout. CLI commands are complete with all parameters, TypeScript interfaces are well-defined, and code examples are production-ready with proper imports and error handling.	3 / 3
Workflow Clarity	Steps are present but validation checkpoints are implicit. The 'Search with AI Summary' shows a two-step process but lacks explicit validation between steps. Troubleshooting section exists but isn't integrated into workflows as feedback loops.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files despite mentioning 'scripts/web_search.ts' and 'FORMS.md' style references would help. All content is inline including advanced patterns, integration examples, and best practices that should be separate files.	1 / 3
	Total	7 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid description that clearly communicates both purpose and usage triggers. It excels at providing natural trigger terms and explicit 'Use when' guidance. The main weakness is moderate specificity - it could benefit from listing more concrete actions/features, and the distinctiveness could be improved by clarifying what makes this SDK-based approach unique.

Suggestions

Add more specific concrete actions like 'filter by date range', 'limit results', 'search specific domains' to improve specificity

Clarify what distinguishes this from other potential web search skills - is it the SDK integration, specific output format, or particular use cases?

Dimension	Reasoning	Score
Specificity	Names the domain (web search) and mentions some actions like 'search the web', 'retrieve current information', and 'returns structured search results', but doesn't list multiple concrete specific actions like query filtering, pagination, or specific API methods.	2 / 3
Completeness	Clearly answers both what ('Implement web search capabilities using the z-ai-web-dev-sdk', 'Returns structured search results with URLs, snippets, and metadata') and when ('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').	3 / 3
Trigger Term Quality	Good coverage of natural terms users would say: 'search the web', 'retrieve current information', 'find relevant content', 'real-time web search'. These are phrases users would naturally use when needing this functionality.	3 / 3
Distinctiveness Conflict Risk	Somewhat specific to web search but could overlap with other search-related skills or general web development skills. The SDK name 'z-ai-web-dev-sdk' helps distinguish it, but 'web search capabilities' is fairly broad.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 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	10 / 11 Passed

Repository: answerzhao/agent-skills
Path: glm-skills/web-search/SKILL.md
Commit: aad73ed

Reviewed: about 10 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.