Reference guide for using google-genai Python library to generate images with gemini-3-pro-image-preview model. Use this skill when building new projects that need Gemini image generation capabilities, to understand the correct API patterns, configuration options, and best practices.
Perform forensic-level analysis of a single company's financial statements, evaluating earnings quality, financial health, fraud risk, and operational efficiency. Use when the user asks for a deep dive into a company's financials, DuPont analysis, earnings quality check, balance sheet analysis, cash flow analysis, Altman Z-score, Beneish M-score, working capital analysis, or any detailed single-company financial examination.
Standards for creating new High-Density Agent Skills.
IBC occupancy load calculator — calculates maximum occupant loads per area from IBC Table 1004.5, with gross vs net area handling, use group classification, and exportable reports.
Generate interactive 3D zoning envelope viewers from zoning analysis reports. Requires a zoning analysis report as input.
Smart Excel/CSV file parsing with intelligent routing based on file complexity analysis. Analyzes file structure (merged cells, row count, table layout) using lightweight metadata scanning, then recommends optimal processing strategy - either high-speed Pandas mode for standard tables or semantic HTML mode for complex reports. Use when processing Excel/CSV files with unknown or varying structure where optimization between speed and accuracy is needed.
Build or rebuild the knowledge graph from existing memories using TF-IDF entity extraction and Leiden clustering. Use when search results seem poor, after bulk imports, or to optimize performance. Automatically discovers relationships between memories and creates topic clusters.
Search and retrieve memories using semantic similarity, knowledge graph relationships, and full-text search. Use when the user asks to recall information, search memories, find past decisions, or query stored knowledge. Returns ranked results with relevance scores.
Modern tidyverse patterns for R including pipes, joins, grouping, purrr, and stringr. Use when writing tidyverse R code.
R style guide covering naming conventions, spacing, layout, and function design best practices. Use when writing R code.
统一的股票数据助手 Skill，整合： (1) 数据查询 — 通过 MCP 协议查询历史 K 线、财务报表等（A 股/港股/ETF/指数）； (2) 实时搜索 — 通过 WebSocket 订阅实时行情推送（每 3~5 秒更新）； (3) 微信联动 — 通过 picoclaw + WeChat Channel 实现微信端操作数据库和订阅实时数据。 触发此 Skill 时会自动下载 picoclaw、复用项目 LLM 配置、启动微信登录。
Integrate multiple plot point analysis results into comprehensive reports, generating high-quality analysis through deduplication, classification, sorting, and summarization. Suitable for integrating multiple analysis sources, generating unified reports
Analyze multi-round evaluation result scoring data, calculate various metrics, calculate rating grades. Suitable for analyzing scoring trends, calculating S/A/B ratings
整合多情点分析结果为综合报告，通过去重、分类、排序、总结生成高质量分析。适用于整合多分析源、生成统一报告
Search for existing cases related to specific indicators or entities. Use to find correlation with other investigations before starting new analysis. Takes search terms and returns matching case IDs.
