← 返回 Skills 市场
top-coding-models
作者
WaiYanNyeinNaing
· GitHub ↗
· v1.0.0
· MIT-0
100
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install top-coding-models
功能描述
Use when user wants benchmark rankings, pricing, token limits, or IDE compatibility info for top 20 agentic coding models. Supports OpenRouter, OpenAI, Anthr...
安全使用建议
This skill includes a Python script that makes live HTTP GET requests to https://benchlm.ai and https://openrouter.ai to gather model and pricing data. It does not request credentials or access local files. If you are comfortable allowing outgoing requests to those two domains, the skill appears safe and coherent with its stated purpose. If you want extra caution: (1) review the full script locally before running, (2) run it in a restricted environment or with network egress only to the two domains, or (3) inspect any dynamic name-matching results before using them for automated actions (the script uses fuzzy matching which can occasionally map names imperfectly).
功能分析
Type: OpenClaw Skill
Name: top-coding-models
Version: 1.0.0
The skill bundle is a legitimate tool designed to fetch and compare AI coding model benchmarks and pricing from BenchLM and OpenRouter. The Python script (fetch_models.py) performs standard API requests to authorized endpoints (benchlm.ai and openrouter.ai) and processes the data for display without any suspicious behavior, unauthorized file access, or credential theft. The documentation (SKILL.md) provides clear, helpful instructions for the AI agent that are entirely consistent with the tool's stated purpose.
能力标签
能力评估
Purpose & Capability
Name/description (top coding models, pricing, token limits, IDE compatibility) match the implementation: the script fetches BenchLM leaderboard data and OpenRouter model data and cross-references them. The declared capabilities are proportional to the required actions.
Instruction Scope
SKILL.md directs the agent to run the included Python script and describes network calls only to BenchLM and OpenRouter. The runtime instructions do not ask the agent to read unrelated local files, environment variables, or to transmit data to other endpoints.
Install Mechanism
No install spec is present (instruction-only skill with an included script). There is no remote download or installer; the included Python script runs with standard library urllib, so install risk is low.
Credentials
The skill declares no required environment variables, credentials, or config paths and the code does not read os.environ or other secrets. The SKILL.md gives example provider env var usage (e.g., ANTHROPIC_BASE_URL) but those are illustrative, not required by the script.
Persistence & Privilege
always is false, the skill is user-invocable and does not request permanent presence or modify other skills/system configuration. It performs only outgoing HTTP GETs at runtime.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install top-coding-models - 安装完成后，直接呼叫该 Skill 的名称或使用
/top-coding-models触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of the top-coding-models skill.
- Fetches live benchmark and pricing data for the top 20 agentic coding models from BenchLM and OpenRouter APIs.
- Outputs structured tables with rankings, costs, capabilities, and IDE compatibility for major coding tools (e.g., Claude Code, Cursor, Windsurf).
- Highlights cost-performance analysis, free-tier models, and integration steps for supported IDEs.
- Includes decision guides, best practices, and a quick start for immediate use.
元数据
常见问题
top-coding-models 是什么？
Use when user wants benchmark rankings, pricing, token limits, or IDE compatibility info for top 20 agentic coding models. Supports OpenRouter, OpenAI, Anthr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 100 次。
如何安装 top-coding-models？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install top-coding-models」即可一键安装，无需额外配置。
top-coding-models 是免费的吗？
是的，top-coding-models 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
top-coding-models 支持哪些平台？
top-coding-models 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 top-coding-models？
由 WaiYanNyeinNaing（@waiyannyeinnaing）开发并维护，当前版本 v1.0.0。
推荐 Skills