# DSXiangLi/DecryptPrompt

总结Prompt&LLM论文，开源数据&模型，AIGC应用

Repository: https://github.com/DSXiangLi/DecryptPrompt
Canonical: https://ross.abutalabs.com/products/decryptprompt
License Family: other
Topics: demonstration, in-context-learning, prompt, few-shot-learning, zero-shot-learning, aigc, papers, prompt-tuning, instruction-tuning, chain-of-thought, chatgpt, llm, llm-agent, prompt-engineering
Last push: 2026-05-06T00:21:19+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 80, release rhythm 35, longevity 92
- inputs: {"age_days": 1300, "days_push": 120, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3434, forks 322 (observed 2026-08-28T04:08:04.276950+00:00)

## What it is
A curated Chinese-language collection of LLM and prompt engineering resources, including open-source models, datasets, frameworks, and AIGC applications, paired with a long-running blog series explaining prompt and LLM papers. It serves as a learning hub rather than usable software.

## Use cases
- learn prompt engineering from paper summaries
- find open-source LLM datasets and models
- understand RLHF and instruction tuning
- study chain-of-thought reasoning techniques
- explore LLM agent and RAG research
- keep up with AIGC applications

## When to choose
- you want curated paper explanations and resource lists for LLM research
- you prefer Chinese-language learning material on prompt engineering

## When to avoid
- you need runnable code or a library to integrate
- you need English-only documentation

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, rag, llm-training, agent-framework
- domain: large-language-models, tutorials, artificial-intelligence
- platform: python
- tags: awesome-list, papers, llm, chain-of-thought, instruction-tuning, aigc, chinese-language

## Member repositories
- DSXiangLi/DecryptPrompt (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:04.276950+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:37:43.174306+00:00, confidence not recorded.
  - readme: https://github.com/DSXiangLi/DecryptPrompt (fetched 2026-08-28T04:08:04.276950+00:00, sha 0721e33d7f15)
- Data as of 2026-08-30T08:39:29.467469+00:00.