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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

The body is an efficient, actionable CLI overview with executable examples and a clean main reference split. The main gap is that two bundle files (errors.md, examples.md) are present but not linked or signaled from the SKILL.md body.

Suggestions

Add a brief 'References' or inline pointers in the body to references/errors.md and references/examples.md so users can discover them from SKILL.md.

Optionally surface a one-line hint to examples.md under Quick Start to illustrate common use cases without inlining them.

Dimension	Reasoning	Score
Conciseness	Lean reference with a commands table, concrete quick-start invocations, an output note, and a single advanced pointer; no concept-explanation padding and 'The CLI is self-documenting' assumes competence.	3 / 3
Actionability	Provides concrete copy-paste-ready commands throughout, e.g. 'npx zai-cli vision analyze ./screenshot.png "What errors do you see?"' and 'npx zai-cli repo tree openai/codex --path codex-rs --depth 2'.	3 / 3
Workflow Clarity	Single-tool CLI reference with unambiguous per-command organization and --help pointers; no destructive or batch operations require validation checkpoints, so the simple-skill exception applies.	3 / 3
Progressive Disclosure	The body cleanly splits advanced material to a one-level-deep references/advanced.md, but the bundle files errors.md and examples.md exist yet are never referenced or signaled from SKILL.md, so navigation to them is incomplete.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, well-triggered, complete, and distinctive. It concisely lists concrete capabilities with an explicit 'Use for' clause covering the main trigger scenarios.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions per capability (OCR, UI-to-code, error diagnosis, domain/recency filtering, web page to markdown, GitHub code search/reading, TypeScript tool chaining).	3 / 3
Completeness	Explicitly answers what (capability bullets) and when ('Use for visual content analysis, web search, page reading, or GitHub exploration').	3 / 3
Trigger Term Quality	Natural user phrasings are well covered: image/video analysis, web search, page reading, GitHub exploration, OCR, error diagnosis.	3 / 3
Distinctiveness Conflict Risk	Z.AI CLI with specific markers (GLM-4.6V vision, GitHub via ZRead) carves a clear niche unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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: jeremylongshore/claude-code-plugins-plus-skills
Commit: 607d11b

Reviewed: 3 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.