MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
typeone-ai-skill-extractor
A minimal prompt repository that provides a single, strict evidence-based template to extract long-term user patterns, collaboration preferences, and decision logic from long AI conversations for seamless context transfer to new windows.
Stars
41
7-day growth
No data
Forks
1
Open issues
0
License
MIT
Last updated
2026-07-04
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It solves the common problem of losing context when starting new AI chat windows, offering a clean, reusable, and privacy-aware method to distill only what matters from lengthy dialogues without adding unnecessary complexity.
Who it is for
- Frequent AI long-chat users working on projects
- Users who need to migrate old conversation context to new windows
- People who want to convert AI understanding into a reusable skill profile
Use cases
- Extracting a stable user profile from a long AI session to use in a new conversation
- Capturing recurring correction moments and preferred AI behavior patterns
- Building a reusable 'Skill' file that helps a new window quickly adapt to your collaboration style
- Separating evidence-backed facts from unverified assumptions for future validation
Strengths
- Extremely focused: only one template, no bloat or prompt collections
- Evidence-based: each conclusion must cite original user words, reducing hallucination
- Privacy-first: includes explicit reminders to avoid leaking sensitive data
- Simple to use: copy-paste the prompt into any existing chat window
Considerations
- Requires manual copying and pasting; no automated integration
- Output needs human review and editing before reuse
- Only captures patterns expressed in text; non-verbal or implicit behaviors may be missed
README quick start
使用前的隐私提醒
Description
把 AI 长对话提炼成可迁移的新窗口上下文 Skill。
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.