zai-cli
Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP. Use when user needs image/video analysis, OCR, UI-to-code conversion, error diagnosis, real-time web search, web page to markdown extraction, or GitHub code exploration. Trigger with phrases like "analyze this image", "search the web for", "read this page", "explore this repo", or "use zai". Requires Z_AI_API_KEY.
69
63%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/community/zai-cli/skills/zai-cli/SKILL.mdQuality
Discovery
92%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 well-structured skill description that clearly articulates multiple concrete capabilities and provides explicit trigger guidance with example phrases. Its main weakness is the breadth of capabilities bundled together (vision, search, reading, GitHub), which could cause overlap with more specialized skills in those individual domains. The inclusion of the tool name 'zai' as a trigger and the API key requirement help with distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: image/video analysis, OCR, UI-to-code conversion, error diagnosis, real-time web search, web page to markdown extraction, and GitHub code exploration. These are clearly defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (vision, search, reader, GitHub exploration with specific sub-capabilities) and 'when' (explicit 'Use when' clause with specific scenarios and a 'Trigger with phrases like' section). Also notes the API key requirement. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'analyze this image', 'search the web for', 'read this page', 'explore this repo', 'use zai'. Also includes domain terms like OCR, UI-to-code, and file type references (image/video). Good coverage of natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | While the z.AI CLI branding and 'use zai' trigger are distinctive, several capabilities like 'web search', 'image analysis', and 'read this page' could overlap with other skills that provide similar functionality (e.g., a general web search skill or an image analysis skill). The bundling of many diverse capabilities into one skill increases conflict risk. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is structurally organized but lacks substantive actionable content. It reads more like a README stub than a skill that teaches Claude how to use the tool — the instructions boil down to 'run --help' and all real examples and error handling are deferred to reference files. The main file needs at least a few concrete, copy-paste-ready command examples to be useful.
Suggestions
Add 2-3 concrete, executable command examples directly in the SKILL.md (e.g., `npx zai-cli vision --image ./screenshot.png 'describe this UI'`) with expected output snippets, rather than deferring all examples to a reference file.
Replace the vague instructions (steps 4-6) with specific workflows for the main use cases: vision analysis, web search, page reading, and repo exploration, each with a concrete command.
Remove the overview paragraph that restates the skill description and the prerequisites that Claude already knows (e.g., what Node.js is), and use that space for actionable content instead.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview paragraph restates what Claude would already know from the description/frontmatter. The prerequisites section explaining what an API key is and listing Node.js is somewhat unnecessary. However, it's not egregiously verbose. | 2 / 3 |
Actionability | The instructions are vague and generic ('Try basic commands like vision, search, read, or repo'). There are no concrete executable examples, no actual command invocations with arguments, and no expected outputs shown. The real examples are deferred entirely to a reference file. | 1 / 3 |
Workflow Clarity | There is a numbered setup sequence (get key, export, verify with doctor), which is reasonable. However, the actual usage workflow is absent — steps 4-6 are essentially 'use --help', providing no real guidance on how to accomplish specific tasks. No validation checkpoints for actual operations. | 2 / 3 |
Progressive Disclosure | References to errors.md and examples.md are well-signaled and one level deep, which is good. However, the main SKILL.md is too thin — it delegates almost all useful content to reference files while providing almost no actionable quick-start content inline. The overview should include at least one concrete example before pointing elsewhere. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
70e9fa4
- 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.