$ account alchaincyf
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.
This repository defines a reusable AI agent skill for role-playing as Zhang Xuefeng, a Chinese education influencer. The core artifact is SKILL.md, a meticulously crafted markdown file with YAML frontmatter that encodes five mental models, eight decision heuristics, a complete expression DNA, and an agentic workflow (research → analyze → respond). It is not a running service or library; it is a configuration file consumed by compatible agent runtimes (Claude Code, Codex, Cursor, etc.) to transform the agent's behavior. The repository also includes six research files (references/research/) that document the persona's writings, conversations, expression style, external views, decisions, and timeline, serving as the evidence base for the skill. The skill demonstrates advanced prompt engineering, cognitive modeling, and agentic protocol design, making it a high-quality example of the Agent Skills pattern. It is actively maintained and has no technical drift as it consists solely of static markdown files.
Darwin-skill is a meta-skill (SKILL.md) and supporting tooling for autonomously optimizing agent skills (SKILL.md files). It implements a ratchet-based hill-climbing loop that evaluates skills across 9 dimensions (structure, effectiveness, meta-skill), spawns independent LLM judges for paired comparison, and only retains improvements validated by human-in-the-loop checkpoints. The repo includes a Node.js screenshot script for generating result cards, HTML templates, documentation, and references integrating Microsoft Research's SkillLens and SkillOpt papers. Despite being primarily a markdown document, it exhibits high craftsmanship: rigorous empirical grounding, explicit anti-pattern blacklist, versioned design philosophy, and detailed operational procedures. The actual executable code is minimal (one utility script), but the skill definition itself is a sophisticated artifact that demonstrates deep understanding of LLM evaluation pitfalls and optimization strategies.
This repository is a comprehensive guide (Orange Book) for Hermes Agent, an open-source AI agent framework by Nous Research. It contains PDFs of the second edition (v0.16.0), screenshots, and a single Python utility script for adding PDF bookmarks. The codebase is minimal: there is no application, library, or data pipeline. The primary value is the book's content, not the software. The Python script (tools/add_toc_bookmarks.py) is a well-documented, self-contained tool that uses pypdf to scan PDFs for section headers and automatically generates a hierarchical outline. The project is clearly organized with bilingual READMEs, an errata section, and a MIT license. While the repository is not a reusable software project in the traditional sense, the bookmark utility is a practical component that could be extracted for similar PDF processing tasks. Overall, the repository serves its purpose as educational documentation rather than a functional application.
This repository is a knowledge package designed to create an AI agent skill that embodies Charlie Munger's thinking framework. It doesn't contain executable code but rather curates and structures Munger's mental models, decision heuristics, and communication style into a usable format for AI agent runtimes. The core output is the SKILL.md file, which provides detailed instructions for how an AI agent should adopt Munger's perspective when responding to user queries, including role-playing rules, a response workflow requiring research before answering, and specific guidelines for expressing Munger's characteristic communication style. The repository represents a sophisticated approach to expertise capture and encoding for AI systems. It synthesizes information from over 50 sources including Berkshire Hathaway shareholder meetings, USC/Harvard speeches, interview records, and external criticisms to distill Munger's approach into five core mental models, eight decision heuristics, and a detailed expression DNA. The references/ directory contains the source research materials, demonstrating transparency about the knowledge foundation. Examples/show how the skill works in practice through sample conversations about investment decisions, team management, and content creation. While primarily a knowledge resource, the structure of the SKILL.md file itself offers potential reusability as a template for creating similar 'thinking style' skills for other experts or domains. The systematic approach to encoding expertise through role-playing protocols, mental model collections, decision frameworks, and communication guidelines represents a pattern that could be adapted with domain-specific content substitution for other AI agent skills.