Merge e7833c2239 into a33691242e

README.md

@@ -150,6 +150,7 @@ Skills are not MCP servers and not tools. MCP defines how an agent connects to e
 - [CSV Data Summarizer](https://github.com/coffeefuelbump/csv-data-summarizer-claude-skill) - Automatically analyzes CSV files and generates comprehensive insights with visualizations without requiring user prompts. *By [@coffeefuelbump](https://github.com/coffeefuelbump)*
 - [deep-research](https://github.com/sanjay3290/ai-skills/tree/main/skills/deep-research) - Execute autonomous multi-step research using Gemini Deep Research Agent for market analysis, competitive landscaping, and literature reviews. *By [@sanjay3290](https://github.com/sanjay3290)*
 - [postgres](https://github.com/sanjay3290/ai-skills/tree/main/skills/postgres) - Execute safe read-only SQL queries against PostgreSQL databases with multi-connection support and defense-in-depth security. *By [@sanjay3290](https://github.com/sanjay3290)*
+- [rcl-score](https://github.com/ZhenyuanPAN822/rcl-score-skill) - Turn a two-person chat (WeChat CSV / JSON / TXT) into a relationship K-line candlestick chart. The IDE LLM scores every turn with v3.1 semantic deltas across 10 dimensions; a local web frontend renders OHLC + MA / BB / MACD / RSI / KDJ with per-bar attribution. Everything runs locally — chat data never leaves the machine. Bilingual (EN+中文). *By [@ZhenyuanPAN822](https://github.com/ZhenyuanPAN822)*
 - [recursive-research](https://github.com/Anjos2/recursive-research) - Recursive research up to PhD level across any domain (science, tech, business, arts, humanities) with source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction. *By [@Anjos2](https://github.com/Anjos2)*
 - [root-cause-tracing](https://github.com/obra/superpowers/tree/main/skills/root-cause-tracing) - Use when errors occur deep in execution and you need to trace back to find the original trigger.