Skip to content
View chenhz01's full-sized avatar
2 followers · 3 following
  • Joined Aug 18, 2026

Block or report chenhz01

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
chenhz01/README.md

👋 你好，我是 chenhz01

AI Agent 治理 × Skill 工程 —— 我造两样东西：让自进化 AI「可证明没跑偏」的审计护栏，和让 agent skill 库「真正用起来」的工程工具。 另一面：音乐人。AI 是我的创作伙伴，不是替代者。

🛡️ 治理与审计 — 让"自我改进的 AI"可验证

项目 一句话
⭐ EEL 进化证据账本：为自进化 AI 造不可篡改的进化账本（6 篇 arXiv 论文 → G1–G6 硬性拒绝护栏）
agency AI 智能体的纪律操作系统：对抗审计、发布门禁、37 身份对攻锻造、防篡改演化账本
adversarial-research-audit 用机械门禁抓住"没在撒谎却在撒谎"的研究报告：覆盖率算术、分簇加总、引用完整性
agent-memory-doctor AI 记忆与约定文件的开机体检：抓沉默的约定丢失与注入稀释

恐惧失控是猜测；没有审计轨迹是事实。

🧩 Skill 工程 — 让 skill 库从"收藏夹"变成"生产力"

项目 一句话
skill-audit-kit skill 库健康检查：引用图谱、孤儿检测、冲突、语义近重复（零依赖 CLI）
answer-contract 四条规则，止住 AI 的注水、绕圈和敷衍：隐性需求补齐 / 结构化输出 / 三方案对比 / 假设熔断
zhengming-openai-plugins SKILL.md → OpenAI Codex 插件包转换器（纯标准库，强制官方 manifest 约束）
ai-agent-skill-breakthrough 学→超→破→用：把开源 agent skill 集合真正用起来的方法论

📐 方法论与工程实践

ai-native-process-engine（AI 原生流程引擎 · 七层架构 + L0-L3 自治分级）· fork-to-mainrepo-playbook（衍生项目独立化技术方案）· trending-scout（GitHub Trending 对抗性审核）· PartnerGene（基因中心型 AI 商务建联方法论）

🤝 正在寻找的合作

  • 谁：做 agent 平台 / skill 生态 / AI 治理的团队与独立开发者
  • 我可以带来的：审计引擎集成 · skill 库健康诊断 · SKILL.md→Codex 转换定制 · 深度方法论的 L3 配方层合作交付
  • 怎么找：邮件 shanlun2029@outlook.com，或直接在对应仓库开 Issue

🎵 音乐人的一面

用 AI 写歌、推歌、做封面——把「AI 思维」嵌入创作链路，人定方向与品味，AI 放大执行。

「进化是证据，证据不可篡改。」

Pinned Loading

  1. adversarial-research-audit adversarial-research-audit Public

    Adversarial audit layer for agentic research: mechanical gates that catch reports which lie without lying — coverage arithmetic, cluster sums, filter provenance, citation integrity. Zero-dependency…

    Python 3 1

  2. agent-memory-doctor agent-memory-doctor Public

    Boot-time integrity check for AI agent memory & convention files — catch silent convention loss, injection dilution, broken rollback anchors. Zero dependencies, Python 3.8+.

    Python 2

  3. EEL EEL Public

    EEL — Evolution Evidence Ledger：为自进化 AI 造不可篡改的进化账本（求合作脱敏版）

    1

  4. zhengming-openai-plugins zhengming-openai-plugins Public

    Convert Agent Skills (SKILL.md) format to OpenAI Codex plugin bundles — stdlib-only, enforces official manifest hard constraints

    Python 1

  5. answer-contract answer-contract Public

    Four rules that stop your AI agent from padding, rambling, and shipping one mediocre answer: Implicit-Need Fill, Structured Output, 3-Option-Plus-Premium, Assumption-Circuit-Breaker. A single-file …

  6. skill-audit-kit skill-audit-kit Public

    Health check for an existing skill/rule library: reference graph, orphans, hubs, conflicts, and zero-dependency semantic near-duplicate detection. Offline CLI with JSON + HTML reports.

    JavaScript