菜单
Designs production-grade RAG systems with document chunking, embedding generation, vector store configuration, hybrid search pipelines, reranking, and retrieval quality evaluation.
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。
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is unreliable across sessions — forgets context, drifts out of scope, claims "done" before tests pass, or starts each session inconsistently — or when creating or assessing AGENTS.md, CLAUDE.md, feature_list.json, init.sh, progress.md, or session-handoff files. Reach for it even if the user never says the word "harness."
Generate a consolidated digest from multiple information sources
Track and report on progress toward defined goals
Review the agent's own recent outputs for quality and accuracy
Generate changelogs from recent commits and merged PRs
Implement features on branches from issue descriptions
基于 SOC 职业分类
| name | rag-architect |
| description | Designs production-grade RAG systems with document chunking, embedding generation, vector store configuration, hybrid search pipelines, reranking, and retrieval quality evaluation. |
| metadata | {"sources":[{"kind":"github-file","repo":"jeffallan/claude-skills","path":"skills/rag-architect/SKILL.md","commit":"3bf9a24b76a7c122f1fc05e83929fbc84e1c207a","attribution":"Jeffallan","license":"MIT","usage":"referenced"}]} |
