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.

Quality

93%

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

Quality

Content

93%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.

Excellent content: lean, copy-paste-ready commands, well-organized sections, and a single clearly-signaled reference file for advanced material. The only soft spot is workflow sequencing, which reads as a command catalog rather than an explicit validate-then-proceed flow.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — a one-line setup, a compact commands table, and copy-paste Quick Start examples with no padding or explanations of concepts Claude already knows, fitting the 'every token earns its place' anchor.	5 / 5
Actionability	Quick Start gives fully executable, copy-paste-ready commands (e.g. `npx zai-cli vision analyze ./screenshot.png "What errors do you see?"`) covering the common cases across vision, search, read, and repo.	5 / 5
Workflow Clarity	Setup → `doctor` (connectivity check) → usage is a clear sequence with a validation checkpoint present via `doctor`, but it is presented as a command catalog rather than an explicitly sequenced workflow with feedback loops, leaving minor gaps.	4 / 5
Progressive Disclosure	A concise overview points cleanly to the one-level-deep `references/advanced.md` (verified to exist) for raw MCP calls, Code Mode, and performance tuning, with the reference clearly signaled — matching the top anchor.	5 / 5
	Total	19 / 20 Passed

Description

88%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 strong description: concrete capabilities, an explicit 'Use for' trigger clause, and a distinct Z.AI niche. Trigger-term synonyms and overlap with generic web-search tools keep it just short of perfect on two dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across six capability areas — 'image/video analysis, OCR, UI-to-code, error diagnosis', 'real-time web search with domain/recency filtering', 'web page to markdown extraction', 'GitHub code search and reading via ZRead' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (the bulleted capability list) and 'when' ('Use for visual content analysis, web search, page reading, or GitHub exploration') with concrete trigger phrases, fitting the top anchor.	5 / 5
Trigger Term Quality	The 'Use for visual content analysis, web search, page reading, or GitHub exploration' clause offers good natural keyword coverage, but misses common synonyms and variants (e.g. 'OCR', 'screenshots', 'scrape') that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Z.AI-specific markers (GLM-4.6V, ZRead, Z_AI_API_KEY) give it a clear niche, but 'web search' and 'page reading' overlap with general web-fetch/browsing skills, leaving minor conflict risk rather than the minimal risk of a 5.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: numman-ali/n-skills
Path: skills/tools/zai-cli/skills/zai-cli/SKILL.md
Commit: fdabc47

Reviewed: 13 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.