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

86%

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

82%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.

The body is an efficient, actionable overview that defers implementation to real bundle scripts and provides copy-paste usage examples with a validated consent flow. Minor over-explanation and the absence of an auth error-recovery loop keep it from the top band.

Suggestions

Trim the CDP-vs-Chrome-DevTools-MCP aside in Authentication to a single clause; it explains context Claude does not need to act.

Add an explicit error-recovery note for authentication (e.g., 'if cookie refresh fails, retry with --login or a dedicated --profile-dir') to give the fragile auth path a feedback loop.

Make script references navigational rather than tabular where detail lives in the bundle (e.g., 'See scripts/gemini-webapi/ for the client implementation') so progressive disclosure is clearly signaled.

Dimension	Reasoning	Score
Conciseness	Largely lean with tables and code blocks and no beginner-concept padding, but a few lines over-explain (e.g., the CDP-vs-DevTools-MCP aside and the AskUserQuestion runtime-equivalent guidance), keeping it just short of fully lean.	4 / 5
Actionability	Copy-paste-ready commands cover the common cases (text, image, vision, multi-turn, JSON), the options and env-var tables give concrete flags, and the {baseDir}/${BUN_X} placeholders are resolved via explicit substitution instructions.	5 / 5
Workflow Clarity	The consent flow is a clearly sequenced numbered list with a validation checkpoint (check consent file for accepted:true and disclaimerVersion) and accept/decline branching, but there is no error-recovery feedback loop for the fragile auth/cookie path.	4 / 5
Progressive Disclosure	Well-organized sections with real one-level-deep bundle references (scripts/main.ts, scripts/gemini-webapi/*) listed in a reference table and EXTEND.md paths in a priority table; references are real but script pointers are listed rather than navigational 'See X for details' links.	4 / 5
	Total	17 / 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, third-person description that clearly states capabilities and provides explicit 'Use when' trigger guidance. It is specific and comprehensive, with only minor overlap risk from broad terms like 'vision-capable AI generation'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'text generation, image generation from prompts, reference images for vision input, and multi-turn conversations' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Generates images and text via reverse-engineered Gemini Web API...') and when ('Use when other skills need image generation backend, or when user requests...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('generate image with Gemini', 'Gemini text generation') but is missing common synonyms and variations that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	The Gemini-specific naming creates a clear niche, but phrases like 'vision-capable AI generation' and 'image generation backend' introduce minor overlap risk with other image/vision skills.	4 / 5
	Total	18 / 20 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
Path: skills/baoyu-danger-gemini-web/SKILL.md
Commit: 1567581

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.