CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini-openai-api

Gemini 模型通过 OpenAI 兼容 API 接入指南。包含:(1) 辅助 API 配置(summary/correction/emotion/vision),(2) extra_body 格式用于控制 thinking,(3) 响应格式处理(markdown 代码块)。当需要将 Gemini 作为辅助模型接入、配置 thinking 参数、或处理 Gemini API 返回格式时使用。

74

Quality

92%

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

100%

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

A dense, code-first integration reference that is lean, fully actionable, clearly sectioned, and self-contained with no padding. It demonstrates strong token efficiency and concrete guidance throughout.

DimensionReasoningScore

Conciseness

No padding with concepts Claude already knows; each section (base URL, model table, extra_body snippets, response handling, config locations, troubleshooting) earns its place and stays actionable, matching the lean-and-efficient anchor.

3 / 3

Actionability

Provides fully executable, copy-paste-ready code: the extra_body dicts, markdown-stripping snippet, and api_providers.json block, matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

As a config/integration reference it is clearly sectioned Base URL → model config → thinking → response handling → config locations → troubleshooting, with cause→solution feedback loops in the FAQ; no destructive batch operation triggers the cap.

3 / 3

Progressive Disclosure

A self-contained SKILL.md with no bundle files, well-organized sections, and no nested references, satisfying the well-organized-sections anchor for skills with no external-reference needs.

3 / 3

Total

12

/

12

Passed

Description

85%

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 specific, well-structured description with explicit what-and-when coverage and low conflict risk. Its only weakness is trigger phrasing that mixes internal jargon ('extra_body', '辅助模型') with natural terms, keeping trigger-term quality at 2.

Suggestions

Add natural-language trigger variants users would actually say (e.g. '接入 Gemini 辅助模型', '让 Gemini 不思考', '解析 Gemini 返回的 JSON 代码块') alongside the technical terms to broaden trigger coverage.

Consider dropping or de-emphasizing internal jargon like 'extra_body' in the description in favor of user-facing phrasing such as '控制 thinking 行为'.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — auxiliary API config (summary/correction/emotion/vision), extra_body for thinking control, and markdown response handling — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (three numbered capabilities) and when via the '当需要...时使用' trigger clause, matching the 'clearly answers both what AND when' anchor rather than the implied-when score-2 anchor.

3 / 3

Trigger Term Quality

The '当需要...接入、配置 thinking 参数、或处理 Gemini API 返回格式时使用' clause gives relevant triggers, but they lean internal/technical ('辅助模型', 'extra_body') rather than the broad natural-user vocabulary of the score-3 anchor.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Gemini via OpenAI-compatible endpoint, thinking config, markdown-wrapped JSON) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
Project-N-E-K-O/N.E.K.O
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.