$ show alchaincyf/zhangxuefeng-skill
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.
The LLM identified 3 files worth highlighting for reuse:
The core skill definition file. It implements a complete agent persona with: (1) a structured agentic workflow (Step 1-3) that forces research before answering, (2) a fallback tree with 9 failure modes and recovery paths, (3) five mental models with evidence and limitations, (4) eight decision heuristics, (5) a detailed expression DNA (syntax, vocabulary, rhythm, humor, certainty), (6) a version checking mechanism using git tags, and (7) explicit role-playing rules. This is a reusable pattern for defining any complex agent persona, demonstrating non-obvious skill in prompt engineering and agent behavior design.
A thorough research document cataloging Zhang Xuefeng's interviews, debates, and live interactions. It includes verbatim quotes with source attribution, analysis of response patterns (e.g., 'simple assertion', 'data crushing', 'redefining the question'), and a taxonomy of debate strategies. The document is structured with clear sections, source indexing, and honesty about limitations (e.g., 'quote accuracy may vary'). This pattern is reusable for any persona research project, demonstrating rigorous qualitative data collection and analysis.
A structured analysis of 11 key decisions in Zhang Xuefeng's life, each with background, decision, result, and a 'consistency score' rating how well his actions matched his stated beliefs. It identifies five recurring behavioral patterns (e.g., 'controversy equals traffic', 'apology strategy: admit tone not fact') and a summary table of contradictions. This is a reusable framework for analyzing any public figure's decision-making and identifying gaps between rhetoric and action.