CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini-3-advanced

Advanced Gemini 3 Pro features including function calling, built-in tools (Google Search, Code Execution, File Search, URL Context), structured outputs, thought signatures, context caching, batch processing, and framework integration. Use when implementing tools, function calling, structured JSON output, context caching, batch API, LangChain, Vercel AI, or production features.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/gemini-3-advanced/SKILL.md

The canonical home for this skill is gemini-3-advanced in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 content is highly actionable with complete executable examples and well-organized references that all resolve, but it is noticeably verbose and lacks validation checkpoints for its batch and caching operations.

Suggestions

Move the full inline task code blocks into the corresponding references/*.md files and keep only a minimal Quick Start example in the body to cut redundancy with the referenced guides.

Add explicit validation/retry checkpoints to the batch processing and context caching tasks (e.g., verify batch job status before marking complete, confirm cache exists before reuse) to lift workflow clarity above the batch/destructive cap.

Drop or condense the 'Key Capabilities', 'When to Use', and 'Summary' lists that restate the description and the inline examples, since they add tokens without new guidance.

DimensionReasoningScore

Conciseness

The body is noticeably verbose: seven fully-worked inline task code blocks plus a duplicated Quick Start and Production Best Practices, much of which repeats the referenced files and explains concepts Claude already knows, fitting the noticeably-verbose anchor rather than the mid 'mostly efficient' level.

2 / 5

Actionability

Provides copy-paste-ready, executable Python and TypeScript examples for every task (function declarations, structured-output schemas, caching, batch, frameworks) covering the common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

Tasks are sequenced as discrete labeled units, but batch processing, cache deletion, and function-call loops lack explicit validate→fix→retry checkpoints; per the batch/destructive cap this cannot exceed 3.

3 / 5

Progressive Disclosure

Good one-level-deep structure with clearly signaled 'See: references/...' links (all 8 references and 5 scripts exist on disk), but large inline code sections that belong in the reference files keep it below the clear-overview anchor.

4 / 5

Total

14

/

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.

The description is specific, complete, and uses natural trigger language with an explicit 'Use when' clause. It is mostly distinct from sibling Gemini skills with only minor overlap risk.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities by name — 'function calling, built-in tools (Google Search, Code Execution, File Search, URL Context), structured outputs, thought signatures, context caching, batch processing, and framework integration' — matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both 'what' (enumerated advanced features) and 'when' ('Use when implementing tools, function calling, structured JSON output, context caching, batch API, LangChain, Vercel AI, or production features'), matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user-facing triggers ('implementing tools', 'function calling', 'structured JSON output', 'context caching', 'batch API', 'LangChain', 'Vercel AI') but misses common synonyms and file-format variants, landing just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Clearly scoped to Gemini 3 Pro advanced features, distinguishing it from sibling gemini-3 skills, with only minor overlap risk against the basic-API and multimodal skills — between the mostly-distinct and clear-niche anchors.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (629 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.