基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Piebald-AI/splitrail --skill mcp命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | mcp |
| description | Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface. |
Splitrail can run as an MCP server, allowing AI assistants to query usage statistics programmatically.
cargo run -- mcp
src/mcp/mod.rs - Module exportssrc/mcp/server.rs - Server implementation and tool handlerssrc/mcp/types.rs - Request/response typesget_daily_stats - Query usage statistics with date filteringget_model_usage - Analyze model usage distributionget_cost_breakdown - Get cost breakdown over a date rangeget_file_operations - Get file operation statisticscompare_tools - Compare usage across different AI coding toolslist_analyzers - List available analyzerssplitrail://summary - Daily summaries across all datessplitrail://models - Model usage breakdownsrc/mcp/server.rs using the #[tool] macrosrc/mcp/types.rs if neededSee existing tools in src/mcp/server.rs for the pattern.
resource_uris module in src/mcp/server.rslist_resources() methodread_resource() methodGuide for updating model pricing in Splitrail. Use when adding new AI model costs or updating existing pricing data.
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.
Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.