baoyu-danger-gemini-web

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

The body is well-structured and highly actionable with executable commands, a validated consent workflow, and one-level-deep references to real bundle files. The only weakness is mild verbosity in the User Input Tools and Authentication sections.

Suggestions

Tighten the "User Input Tools" section to a compact rule list; the runtime-substitution note can be one line instead of three numbered items plus a caveat.

Trim the Authentication aside about CDP session reuse vs. Chrome DevTools MCP --autoConnect to a single sentence, since it explains context Claude can infer.

Consider moving the full Options/Models/Environment Variables tables into a separate REFERENCE.md and linking from the body to reduce the inline token footprint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and executable examples, but sections like "User Input Tools" and the Authentication CDP-reuse aside include explanation that could be tightened without losing clarity.	2 / 3
Actionability	Concrete, copy-paste-ready commands ("${BUN_X} {baseDir}/scripts/main.ts --prompt ... --image cat.png") plus full options, models, and env-var tables give fully executable guidance.	3 / 3
Workflow Clarity	The consent-check flow is a clearly sequenced multi-step process with explicit branching (valid consent → proceed; none → ask; decline → stop), and the script-execution instructions are numbered 1–4.	3 / 3
Progressive Disclosure	The Script Reference table points one level deep to real bundle files (scripts/main.ts, scripts/gemini-webapi/*) that exist on disk, and content is organized into clear navigable sections.	3 / 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.

A strong, third-person description that covers concrete capabilities, explicit natural-language triggers, and a clear use-when clause with low conflict risk. All four dimensions hit the top anchor.

Dimension	Reasoning	Score
Specificity	"Generates images and text" and "text generation, image generation from prompts, reference images for vision input, and multi-turn conversations" list multiple specific concrete actions rather than vague language.	3 / 3
Completeness	It states both what it does (generates images/text via reverse-engineered Gemini Web API) and when to use it via an explicit "Use when other skills need image generation backend, or when user requests..." clause.	3 / 3
Trigger Term Quality	Natural user phrasings are quoted directly ("generate image with Gemini", "Gemini text generation", "vision-capable AI generation"), giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The narrow niche (reverse-engineered Gemini Web API) and Gemini-specific triggers make it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: jimliu/baoyu-skills
Commit: c9a50cc

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.