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:
- System identity
- Task mode
- User question
- Selected passage
- Current book
- Current chapter
- Retrieved chunks
- Interpretive background knowledge
- User notes
- User highlights
- Conversation summary
- Long-term memory
- 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:
- Explain which context layer is affected.
- Explain what context is static vs dynamic.
- Keep context small and focused.
- Explain what is textual evidence vs interpretive background.
- Add a verification method.
04 同仓库更多 Skills
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".
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".
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".
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
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.
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.