$ show alchaincyf/nuwa-skill
This repository, nuwa-skill, is a data_research project that functions as a cognitive framework extraction engine. Its primary output is a collection of structured, testable AI 'perspective skills' (SKILL.md files) that model the thinking patterns, decision heuristics, and expression DNA of prominent public figures (e.g., Elon Musk, Richard Feynman, Steve Jobs, Donald Trump). The system does not run a live service; instead, it provides a rigorous methodology and a set of reusable artifacts for transforming unstructured biographical research into executable AI personas. The core value lies in its extraction framework, fidelity scorecard, and standardized skill template, which together form a complete pipeline for persona distillation. The architecture is a hybrid of a research methodology and a data artifact repository. The data flow begins with a 6-dimension research pipeline (writings, conversations, expression DNA, external views, decisions, timeline) that collects and structures raw source material. This is followed by the application of the Extraction Framework, which uses triple verification to identify mental models and quantify expression DNA. The output is validated against the Fidelity Scorecard through independent dual-agent testing. Supporting scripts (quality_check.py, merge_research.py, srt_to_transcript.py) automate parts of the validation and data processing pipeline, while the CI system (community-pr-check.yml) enforces structural quality gates for community contributions. The most reusable components are the methodology documents (extraction-framework.md, fidelity-scorecard.md, skill-template.md), which solve the recurring data engineering problem of converting unstructured text about a person into a structured, testable cognitive model. The project is actively maintained with a clear contribution model and low technical drift, as its core value is in its markdown-based methodology rather than complex software dependencies. However, reproducibility for creating *new* skills from scratch is low due to the lack of a formalized, dependency-managed environment, making the existing bundled skills the primary reusable asset.
The LLM identified 5 files worth highlighting for reuse:
Defines the core methodology for extracting cognitive frameworks from unstructured research. It specifies triple verification (cross-domain replication, generative power, exclusivity) for mental models, quantifies expression DNA (sentence length, analogy density, certainty spectrum), and provides rules for handling contradictions. This is the most valuable reusable asset, solving the fundamental data engineering problem of transforming biographical text into a structured, testable cognitive model.
Provides a structured quality assurance framework for persona skills. It defines a 100-point rubric across 5 dimensions (position consistency, style recognition, edge honesty, source transparency, structural completeness) and mandates independent dual-agent testing. This solves the hard problem of objectively measuring AI persona fidelity and is directly reusable for any persona evaluation pipeline.
Standardized template for generating new perspective skills. Ensures portability across 50+ AI runtimes via the Agent Skills protocol. Includes YAML frontmatter, role-playing rules, Agentic Protocol (Classify-Research-Answer), identity card, mental models, decision heuristics, expression DNA, values/anti-patterns, honest limits, and failure mode fallback trees. A reusable schema for structuring AI persona data.
Automated structural validation script for SKILL.md files. Checks for required sections (mental models, decision heuristics, honest boundaries), valid YAML frontmatter, and proper formatting. Designed to be run in CI pipelines (as demonstrated by community-pr-check.yml) to enforce data quality gates on community contributions. Reusable for any project generating structured markdown artifacts.
The most complex example in the repository, demonstrating the framework applied to a domain (X/Twitter growth) rather than a person. Features user data persistence, diagnostic workflows for analyzing content strategy, and extensive failure mode fallback trees. Showcases the full expressive power and flexibility of the skill template for non-persona applications.