LLM-powered multi-attribute reranking of candidate sets via pairwise comparison. Supports canonical attributes (clarity, technical_depth, insight), custom prompts, model tier selection, and TopK configuration. Use when the task involves: rerank, rank by clarity, rank by insight, rank by depth, best items, quality tier, LLM judge, pairwise comparison, multi-attribute rank, rerank from sql or list. NOT for: simple SQL sorting (ORDER BY date/upvotes/score -- use scry), semantic search or embedding algebra (use vector-composition), or people identity resolution (use people-graph).
LLM-powered multi-attribute reranking of candidate sets via pairwise comparison. Supports canonical attributes (clarity, technical_depth, insight), custom prompts, model tier selection, and TopK configuration. Use when the task involves: rerank, rank by clarity, rank by insight, rank by depth, best items, quality tier, LLM judge, pairwise comparison, multi-attribute rank, rerank from sql or list. NOT for: simple SQL sorting (ORDER BY date/upvotes/score -- use scry), semantic search or embedding algebra (use vector-composition), or people identity resolution (use people-graph).
基于 LLM 的通过成对比较对候选集合进行多属性重排序。支持规范属性(清晰度、技术深度、洞察力)、自定义提示、模型层级选择和 TopK 配置。适用于以下任务:重排序、按清晰度排名、按洞察力排名、按深度排名、最佳项、质量分层、LLM 评判、成对比较、多属性排名、从 SQL 或列表重排序。不适用于:简单的 SQL 排序(ORDER BY date/upvotes/score —— 请使用 scry)、语义搜索或嵌入代数(请使用 vector-composition)、或人物身份解析(请使用 people-graph)。
Category: developer (开发工具) · Author: ExoPriors · Version: @main · License: MIT
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer