CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

A tight, highly executable CLI reference: copy-paste commands, complete flag and model tables, and a validated consent gate with explicit branching. The weaker spots are minor redundancy between sections and the absence of error-recovery guidance for auth/cookie failures.

Suggestions

Add error-recovery guidance for auth/cookie failures (e.g., expired cookies → re-run with --login; unwanted debugging-session reuse → set --profile-dir) to strengthen workflow_clarity.

Merge the 'Extension Support' section into 'Preferences (EXTEND.md)' and tighten the 'User Input Tools' rules to improve conciseness.

Trim inline detail such as the PowerShell proxy syntax, or move the Options/Models tables to a reference file, to sharpen progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly lean tables and copy-paste commands with no padding or explanations of concepts Claude already knows, but the 'User Input Tools' meta-rules, the PowerShell proxy syntax note, and the 'Extension Support' section (which merely points back to 'Preferences') could be trimmed. Efficient with minor instances of over-explanation, short of the every-token-earns-its-place of a 5.

4 / 5

Actionability

The 'Usage' section gives nine copy-paste-ready bash commands covering text, image, vision-input, multi-turn, and JSON cases, the Options table enumerates every flag, and the consent file format is specified exactly ("{\"version\":1,\"accepted\":true,...}"). Placeholders like {baseDir} and ${BUN_X} are explicitly resolved in 'Script Directory', so the guidance is fully executable and covers the common cases.

5 / 5

Workflow Clarity

'Consent Check (REQUIRED)' is a clear numbered sequence with an explicit validation gate (verify 'accepted: true' and 'disclaimerVersion: "1.0"') and both accept/decline branches, but there is no error-recovery guidance for failed browser auth, cookie expiry, or failed generations. Most checkpoints are present with minor validation gaps, short of the explicit feedback loops of a 5.

4 / 5

Progressive Disclosure

A well-sectioned ~110-line overview whose only references — 'scripts/main.ts' and 'scripts/gemini-webapi/*' — are real, one level deep, and carry the bulk implementation (verified on disk: client.ts, types/, utils/, components/). Minor organization gaps (the 'Extension Support' section duplicates 'Preferences', and the Options/Models tables sit inline) keep it below the clean split-and-navigation of a 5.

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 description: third-person, concrete capability list, and an explicit 'Use when...' clause with natural trigger phrases. The only gaps are a few missing synonyms ('draw', 'picture', 'chat with Gemini') and mild overlap risk with other image-backend skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "image generation from prompts", "reference images for vision input", "multi-turn conversations", plus "Generates images and text" — covering the tool's full capability surface, matching the comprehensive anchor rather than the 'minor gaps in coverage' of a 4. Voice is third person ('Generates...'), so no voice penalty applies.

5 / 5

Completeness

Explicitly answers both what ("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") and when ("Use when other skills need image generation backend, or when user requests...") with concrete trigger phrases, structurally matching the anchor-5 example. Not a 4, because the 'when' clause is already explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say ("generate image with Gemini", "Gemini text generation", "vision-capable AI generation"), but misses common variations such as 'draw', 'make a picture', 'chat with Gemini', or 'describe an image'. Good keyword coverage with a few natural terms missing, short of the comprehensive synonyms-and-extensions coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

Triggers are Gemini-specific ("generate image with Gemini", "Gemini text generation"), giving a clear niche, but "when other skills need image generation backend" could fire for any image-generation backend skill. Mostly distinct with minor overlap risk against closely related skills, short of the minimal conflict risk of a 5.

4 / 5

Total

18

/

20

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 — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

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.