zai-cli
Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/recency filtering - Reader: web page to markdown extraction - Repo: GitHub code search and reading via ZRead - Tools: MCP tool discovery and raw calls - Code: TypeScript tool chaining Use for visual content analysis, web search, page reading, or GitHub exploration. Requires Z_AI_API_KEY.
86
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
77%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 description effectively communicates a multi-capability CLI tool with good specificity and completeness, including an explicit 'Use for' clause. However, the broad scope covering multiple domains (vision, search, reading, code) creates potential overlap with more specialized skills, and some trigger terms are overly technical rather than matching natural user language.
Suggestions
Replace technical jargon in trigger terms with natural user phrases (e.g., 'analyze images or screenshots' instead of just 'GLM-4.6V', 'read web pages' instead of 'Reader')
Consider emphasizing what makes this skill unique compared to standalone vision/search/GitHub skills to reduce conflict risk
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions across several domains: image/video analysis, OCR, UI-to-code, error diagnosis, web search with filtering, markdown extraction, GitHub code search, MCP tool discovery, and TypeScript tool chaining. | 3 / 3 |
Completeness | Clearly answers 'what' with detailed capability list and explicitly answers 'when' with 'Use for visual content analysis, web search, page reading, or GitHub exploration.' Also notes the API key requirement. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'image', 'video', 'OCR', 'web search', 'GitHub', but uses technical jargon (GLM-4.6V, MCP, ZRead) and misses common user phrases like 'read webpage', 'analyze screenshot', or 'search the web'. | 2 / 3 |
Distinctiveness Conflict Risk | While the Z.AI branding and specific tool names (GLM-4.6V, ZRead) create some distinctiveness, the broad scope covering vision, search, reading, and code could overlap with dedicated image analysis, web search, or GitHub skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that maximizes token efficiency while providing concrete, executable examples. The table format for commands and the quick start section give Claude everything needed for common use cases. Minor weakness is the lack of error handling guidance or validation steps for setup verification.
Suggestions
Add a brief note after 'npx zai-cli doctor' about what to check if it fails or how to interpret common errors
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what CLI tools are or how npx works. Every line provides actionable information, and the table format maximizes information density. | 3 / 3 |
Actionability | Provides fully executable, copy-paste ready commands covering all major use cases. Examples are concrete with realistic arguments (file paths, URLs, search queries) and demonstrate actual usage patterns. | 3 / 3 |
Workflow Clarity | This is primarily a reference/command skill rather than a multi-step workflow, but the setup -> usage flow is clear. However, there's no validation guidance (e.g., what to do if doctor fails, how to verify API key is working before running commands). | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview, quick start examples, and explicit reference to advanced.md for complex topics. The '--help' guidance for self-documentation is smart progressive disclosure. One-level-deep reference is well-signaled. | 3 / 3 |
Total | 11 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- numman-ali/n-skills
- Commit
8de01ac
- 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.