AGENT SKILL

sophia-context-engineer

Use this skill when working on Sophia's AI context, prompts, RAG context assembly, memory selection, context budget, AI behavior, or provider orchestration.

License 许可
MIT
所属仓库
ziyad455/sophia
最近更新
2026-08-21
Stars
★ 0
Forks
0

01 前言 Front Matter

name
sophia-context-engineer
description
Use this skill when working on Sophia's AI context, prompts, RAG context assembly, memory selection, context budget, AI behavior, or provider orchestration.

03 SKILL.md 正文

Sophia Context Engineer Skill

You are working on Sophia's AI context system.

Sophia is a philosophy reading companion, not a generic chatbot.

Goal

Build AI behavior that helps the user understand philosophical texts using the right context at the right time.

Context Layers

When building AI requests, consider these layers:

  1. System identity
  2. Task mode
  3. User question
  4. Selected passage
  5. Current book
  6. Current chapter
  7. Retrieved chunks
  8. Interpretive background knowledge
  9. User notes
  10. User highlights
  11. Conversation summary
  12. Long-term memory
  13. Output rules

Rules

  • Do not send full books by default.
  • Prefer selected text over broad context.
  • Prefer current chapter over unrelated chunks.
  • Keep prompts structured.
  • Separate instructions from user/book content.
  • Separate textual evidence from interpretive background.
  • Route philosophy, theology, psychology, history, and literary comparisons only when relevant.
  • Make AI providers replaceable.
  • Do not hardcode Gemini, DeepSeek, or OpenAI directly into app logic.
  • If context is insufficient, Sophia should say so.

Files To Check

  • docs/context/context-engineering.md
  • docs/context/ai-behavior.md
  • docs/context/rag-strategy.md
  • backend/src/ai
  • backend/src/ai/context
  • backend/src/ai/prompts
  • backend/src/ai/providers

Output Expected

When making changes:

  1. Explain which context layer is affected.
  2. Explain what context is static vs dynamic.
  3. Keep context small and focused.
  4. Explain what is textual evidence vs interpretive background.
  5. Add a verification method.

04 同仓库更多 Skills

ziyad455
ziyad455/sophia

accessibility

Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

★ 0
ziyad455
ziyad455/sophia

writing-guidelines

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

★ 0
ziyad455
ziyad455/sophia

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

★ 0
ziyad455
ziyad455/sophia

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

★ 0
ziyad455
ziyad455/sophia

vercel-react-view-transitions

Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.

★ 0
ziyad455
ziyad455/sophia

vercel-react-best-practices

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

★ 0