CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini-3-pro-api

Gemini 3 Pro API/SDK integration for text generation, reasoning, and chat. Covers setup, authentication, thinking levels, streaming, and production deployment. Use when working with Gemini 3 Pro API, Python SDK, Node.js SDK, text generation, chat applications, or advanced reasoning tasks.

67

Quality

81%

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

75%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 highly actionable with executable code and clear workflows, but suffers from duplicated quick-start content and a broken reference path. Progressive disclosure is solid though some inline production code could be split into references.

Suggestions

Remove the duplicated Quick Start section (it overlaps Workflow 1) or merge them into a single canonical setup path to tighten token usage.

Fix the broken reference at references/thought-signatures.md (line 178) — either add the file or remove the inline pointer.

Move the long production-deployment code blocks (rate limiter, monitoring, cost logging) into references/best-practices.md or error-handling.md to reduce body length while keeping them discoverable.

DimensionReasoningScore

Conciseness

Mostly efficient actionable content, but the Quick Start section and Workflow 1 duplicate the same setup steps, and overview/summary sections restate capabilities already in the description — more than minor over-explanation.

3 / 5

Actionability

Fully executable, copy-paste-ready code in both Python and Node.js covering chat, streaming, error handling, rate limiting, and monitoring — specific examples span the common cases.

5 / 5

Workflow Clarity

Three workflows have clear numbered sequences and explicit 'Expected Outcome' markers, with a verify step in Workflow 1 and retry feedback loops in error handling; validation checkpoints are present but somewhat soft.

4 / 5

Progressive Disclosure

Good structure with a references/ bundle of seven well-signaled one-level-deep files linked inline and in a References section; one referenced path (references/thought-signatures.md) does not exist, and some large production code could live in references.

4 / 5

Total

16

/

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 well-constructed with explicit what/when structure and concrete capability listing. Trigger coverage is strong but could add synonyms to fully distinguish from adjacent LLM skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'text generation, reasoning, and chat' plus 'setup, authentication, thinking levels, streaming, and production deployment' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (integration covering setup, auth, thinking levels, streaming, deployment) and 'when' ('Use when working with Gemini 3 Pro API, Python SDK, Node.js SDK, text generation, chat applications, or advanced reasoning tasks') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural triggers ('text generation', 'chat applications', 'advanced reasoning tasks', 'Python SDK', 'Node.js SDK') but lacks synonyms and generic variations a user might say (e.g., 'LLM', 'Google AI'), so not quite comprehensive.

4 / 5

Distinctiveness Conflict Risk

Clear Gemini 3 Pro niche with distinct triggers, but generic terms like 'text generation' and 'chat applications' create minor overlap risk with other LLM-integration skills.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (614 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

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.