chore: save workspace changes before pull

wiki/concepts/A-B-Testing.md

@@ -0,0 +1,22 @@
+---
+title: "A/B Testing"
+type: concept
+tags: [experimentation, testing, statistics]
+sources: [project-management-experiment-tracker]
+last_updated: 2026-04-20
+---
+
+## Definition
+A/B Testing is a controlled experiment that compares a control variant against one or more treatments to measure causal impact on a target metric.
+
+## Core Principles
+- Randomly assign users to variants
+- Change one meaningful variable at a time when possible
+- Predefine primary and guardrail metrics
+- Run long enough to reach adequate sample size
+- Analyze results with statistical rigor
+
+## Related Entities
+- [[Experiment Tracker]]
+- [[Senior Project Manager]]
+

wiki/concepts/ATS.md

@@ -0,0 +1,20 @@
+---
+title: "ATS"
+type: concept
+tags: [hr, recruiting, systems]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+ATS（Applicant Tracking System）是用于管理招聘流程、候选人资料、面试反馈和流程状态的系统。
+
+## Core Principles
+- 统一记录候选人状态
+- 减少信息丢失和重复沟通
+- 支持筛选、评分和自动化提醒
+- 让招聘过程可追踪、可复盘
+
+## Related Entities
+- [[Recruitment Specialist]]
+- [[The Agency]]

wiki/concepts/Audit-Trail.md

@@ -0,0 +1,21 @@
+---
+title: "Audit Trail"
+type: concept
+tags: [compliance, audit, operations]
+sources: [accounts-payable-agent]
+last_updated: 2026-04-20
+---
+
+## Definition
+Audit Trail 是记录关键操作、决策与结果的可追溯日志，通常包含对象、金额、时间、状态和执行主体。
+
+## Core Principles
+- 每个关键动作都应可回放与审计
+- 记录应尽量完整、结构化且不可歧义
+- 支持事后核查、对账和责任归属
+- 审计记录应避免遗漏审批上下文
+
+## Related Entities
+- [[Accounts Payable Agent]]
+- [[Agentic Identity & Trust Architect]]
+- [[The Agency]]

wiki/concepts/Candidate-Experience.md

@@ -0,0 +1,20 @@
+---
+title: "Candidate Experience"
+type: concept
+tags: [hr, recruiting, experience]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+Candidate Experience 是候选人从投递、筛选、面试、offer 到入职全过程的体验质量。
+
+## Core Principles
+- 快速反馈，避免候选人长期等待
+- 尊重候选人时间与信息透明
+- 拒绝也要保持礼貌和专业
+- 候选人体验会反向影响雇主品牌
+
+## Related Entities
+- [[Recruitment Specialist]]
+- [[Employer Brand]]

wiki/concepts/Dengbao.md

@@ -0,0 +1,23 @@
+---
+title: "Dengbao"
+type: concept
+tags: [security, compliance, government-it]
+last_updated: 2026-04-20
+---
+
+## Definition
+Dengbao（网络安全等级保护）是中国信息系统安全的分级保护制度，政府与关键信息系统通常需要满足相应等级的建设、测评与整改要求。
+
+## Core Points
+- 常见政府系统至少需要满足等保三级要求
+- 重点系统可能需要更高等级控制
+- 涵盖边界防护、身份认证、日志审计、数据保护等内容
+- 通常在系统上线前完成测评与整改闭环
+
+## Related Concepts
+- [[Compliance Enforcement]]
+- [[Government Procurement]]
+- [[Digital Government]]
+
+## Related Entities
+- [[Government Digital Presales Consultant]]

wiki/concepts/Digital-Government.md

@@ -0,0 +1,29 @@
+---
+title: "Digital Government"
+type: concept
+tags: [government, public-sector, transformation]
+last_updated: 2026-04-20
+---
+
+## Definition
+Digital Government 指政府业务、政务服务、数据治理和内部协同的数字化重构，通过统一平台、流程再造和数据共享提升治理效率与服务体验。
+
+## Core Dimensions
+- 政务服务在线化与一网通办
+- 数据共享交换与治理平台建设
+- 业务流程再造与跨部门协同
+- 安全、合规与可审计能力建设
+
+## Related Concepts
+- [[Smart City]]
+- [[Government Procurement]]
+- [[Technical Discovery]]
+- [[Solution Architecture (SA)]]
+- [[Proof of Concept (POC)]]
+- [[Dengbao]]
+- [[Miping]]
+- [[Xinchuang]]
+
+## Related Entities
+- [[Government Digital Presales Consultant]]
+- [[The Agency]]

wiki/concepts/Document-Generation.md

@@ -0,0 +1,30 @@
+---
+title: "Document Generation"
+type: concept
+tags: [office-suite, automation, documents]
+last_updated: 2026-04-20
+---
+
+## Definition
+Document Generation 是指通过代码、模板和数据驱动流程自动创建 PDF、PPTX、XLSX、DOCX 等专业文档的工作流，而不是依赖手工排版。
+
+## Core Principles
+- 选择正确的输出格式和工具链
+- 使用样式、主题和模板保持一致性
+- 将数据与版式分离，提升复用性
+- 兼顾品牌一致性、可访问性和可维护性
+- 在生成前明确受众、目的与交付要求
+
+## Common Tooling
+- PDF：reportlab、weasyprint、fpdf2、puppeteer
+- PPTX：python-pptx、pptxgenjs
+- XLSX：openpyxl、xlsxwriter、exceljs
+- DOCX：python-docx、docx
+
+## Related Concepts
+- [[Claude Skills]]
+- [[Prompt Engineering]]
+
+## Related Entities
+- [[Document Generator]]
+- [[The Agency]]

wiki/concepts/Employer-Brand.md

@@ -0,0 +1,20 @@
+---
+title: "Employer Brand"
+type: concept
+tags: [hr, recruiting, branding]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+Employer Brand 是候选人与员工对企业工作环境、成长机会、文化与声誉的整体认知。
+
+## Core Principles
+- 用内容展示真实的工作场景
+- 监控招聘口碑与评价平台反馈
+- 将雇主品牌作为长期招聘资产经营
+- 结合奖项、案例与员工故事增强可信度
+
+## Related Entities
+- [[Recruitment Specialist]]
+- [[The Agency]]

wiki/concepts/Global-Standards-Coverage.md

@@ -0,0 +1,24 @@
+---
+title: "Global Standards Coverage"
+type: concept
+tags: [engineering, civil, compliance]
+---
+
+## Definition
+跨多个国家/地区工程规范进行统一设计与审查的能力，通常涉及 Eurocode、ACI、AISC、AS/NZS、CSA、GB、IS、AIJ 以及国家附录、地方修订和 AHJ 要求。
+
+## Core Elements
+- 法域识别：先确认项目所在地与适用法规
+- 规范映射：为结构、基础、荷载、抗震等子系统选择对应标准
+- ULS / SLS 双重校核：同时满足强度与使用性要求
+- 冲突解决：当业主规范与本地规范冲突时，记录并选择可辩护方案
+- 设计依据报告：将所有规范决策、假设和例外项留痕
+
+## Related Entities
+- [[Civil Engineer]]
+- [[The Agency]]
+
+## Related Concepts
+- [[Technical Discovery]]
+- [[Solution Architecture]]
+- [[Multi-Agent Team]]

wiki/concepts/Government-Procurement.md

@@ -0,0 +1,27 @@
+---
+title: "Government Procurement"
+type: concept
+tags: [government, procurement, bidding, compliance]
+last_updated: 2026-04-20
+---
+
+## Definition
+Government Procurement 指政府机构围绕预算、招标、评标、合同签署和验收所进行的标准化采购流程。
+
+## Core Dimensions
+- 资格条件与响应文件审核
+- 技术标、商务标与评分规则
+- 公开招标、竞争性磋商、询价等采购方式
+- 合同、验收、付款与审计闭环
+
+## Related Concepts
+- [[Technical Discovery]]
+- [[Proof of Concept (POC)]]
+- [[Solution Architecture (SA)]]
+- [[Dengbao]]
+- [[Miping]]
+- [[Xinchuang]]
+
+## Related Entities
+- [[Government Digital Presales Consultant]]
+- [[The Agency]]

wiki/concepts/Hypothesis-Testing.md

@@ -0,0 +1,25 @@
+---
+title: "Hypothesis Testing"
+type: concept
+tags: [statistics, experimentation]
+sources: [project-management-experiment-tracker]
+last_updated: 2026-04-20
+---
+
+## Definition
+Hypothesis Testing is a statistical framework for evaluating whether observed data provides enough evidence to reject a null hypothesis in favor of a treatment effect.
+
+## Core Principles
+- State null and alternative hypotheses clearly
+- Choose an appropriate test for the data type
+- Set the decision threshold before the experiment starts
+- Interpret p-values alongside practical significance
+
+## Related Concepts
+- [[Statistical Significance]]
+- [[Power Analysis]]
+- [[A/B Testing]]
+
+## Related Entities
+- [[Experiment Tracker]]
+

wiki/concepts/Identity-Governance.md

@@ -1,20 +1,29 @@
 ---
-title: "Identity-Governance"
+title: "Identity Governance"
 type: concept
-tags: []
+tags: [identity, governance, multi-agent, entity-resolution]
+last_updated: 2026-04-20
 ---
 
 ## Definition
-身份治理（Identity Governance）是一个用于高效管理数字身份、降低风险并保持合规性的框架。它回答三个核心问题：谁当前有权访问我们的系统？谁应该有权访问？访问是如何进行的？
+Identity Governance 指在多智能体或多系统环境中，对实体身份的解析、归一化、合并、拆分、权限边界与审计进行统一治理的框架。
 
-## Components
-- 身份管理（Identity Management）
-- 访问管理（Access Management）
-- 身份审计（Identity Auditing）
+## Core Principles
+- 同一实体必须收敛到同一个 canonical identity
+- 身份写入必须可审计、可回滚
+- 合并与拆分应优先以提案形式进入复核流程
+- tenant 边界与 PII 脱敏默认启用
+- 代理身份与实体身份应分层治理，避免把 agent authorization 与 entity resolution 混为一谈
+- 身份/授权/证据链验证应 fail-closed
 
-## Use Cases
-- 管理内部员工访问权限
-- 管理外部用户（包括合同工）访问权限
-- 支持时间限制的临时访问
-- 通过工作流自动化访问审批和撤销
-- 监控和审计访问行为
+## Related Entities
+- [[Identity Graph Operator]]
+- [[Agentic Identity & Trust Architect]]
+- [[The Agency]]
+- [[AI代理（Agent）]]
+
+## Related Concepts
+- [[Audit Trail]]
+- [[Zero Trust Access]]
+- [[Multi-Agent-System-Reliability]]
+- [[Idempotent Operation]]

wiki/concepts/Labor-Law-Compliance.md

@@ -0,0 +1,20 @@
+---
+title: "Labor Law Compliance"
+type: concept
+tags: [hr, compliance, law]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+Labor Law Compliance 指招聘、合同签订、试用期、社保、公积金、背景调查和解约等环节遵守当地劳动法规与隐私要求。
+
+## Core Principles
+- JD 不得包含歧视性要求
+- 个人信息处理需要明确授权
+- 背景调查前必须取得书面同意
+- 试用期、合同期限和补偿标准必须符合当地法规
+
+## Related Entities
+- [[Recruitment Specialist]]
+- [[The Agency]]

wiki/concepts/Miping.md

@@ -0,0 +1,23 @@
+---
+title: "Miping"
+type: concept
+tags: [cryptography, compliance, government-it]
+last_updated: 2026-04-20
+---
+
+## Definition
+Miping（商用密码应用安全性评估）是政府与重要信息系统中对身份认证、传输加密、数据存储加密和密码产品应用情况进行检查评估的合规要求。
+
+## Core Points
+- 常涉及 SM2、SM3、SM4 等国密算法
+- 电子签章、CA 证书与身份认证常需使用国密体系
+- 往往是系统验收前必须完成的步骤之一
+- 需要将密码应用设计融入整体安全架构
+
+## Related Concepts
+- [[Compliance Enforcement]]
+- [[Government Procurement]]
+- [[Digital Government]]
+
+## Related Entities
+- [[Government Digital Presales Consultant]]

wiki/concepts/Multi-Agent-Team.md

@@ -41,4 +41,5 @@ last_updated: 2026-04-17
 - [[Agent Chain]]：多个 Agent 串联工作
 - [[Shared Memory]]：团队共享上下文
 - [[Scheduled Tasks]]：定时任务机制
-- [[OpenClaw]]：支持多 Agent 协调的工具
+- [[OpenClaw]]：支持多 Agent 协调的工具
+- [[Civil Engineer]]：多智能体体系中的专业化工程角色案例

wiki/concepts/Onboarding.md

@@ -0,0 +1,20 @@
+---
+title: "Onboarding"
+type: concept
+tags: [hr, recruiting, onboarding]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+Onboarding 是从 offer 接受、入职准备到试用期内帮助新员工融入组织的标准化流程。
+
+## Core Principles
+- T-7 到 Day 30 分阶段推进
+- 入职当天完成合同、系统、权限与培训
+- 试用期目标必须清晰且可衡量
+- 以体验和留存为导向设计流程
+
+## Related Entities
+- [[Recruitment Specialist]]
+- [[The Agency]]

wiki/concepts/Payment-Rail.md

@@ -0,0 +1,20 @@
+---
+title: "Payment Rail"
+type: concept
+tags: [finance, payments, operations]
+sources: [accounts-payable-agent]
+last_updated: 2026-04-20
+---
+
+## Definition
+Payment Rail 是支付从发送方到接收方所经过的结算通道或网络，例如 ACH、Wire、Crypto、Stablecoin 或支付 API。
+
+## Core Principles
+- 不同 rail 适合不同金额、时效与成本要求
+- rail 选择应基于收款方类型、地区、费用和结算速度
+- rail 故障时应优先尝试替代通道
+- 付款系统应支持可追踪的 rail 级别记录
+
+## Related Entities
+- [[Accounts Payable Agent]]
+- [[The Agency]]

wiki/concepts/Power-Analysis.md

@@ -0,0 +1,25 @@
+---
+title: "Power Analysis"
+type: concept
+tags: [statistics, experimentation]
+sources: [project-management-experiment-tracker]
+last_updated: 2026-04-20
+---
+
+## Definition
+Power Analysis estimates the sample size needed to detect a meaningful effect with a desired probability of success.
+
+## Core Principles
+- Specify minimum detectable effect
+- Choose desired power level before launch
+- Use realistic baseline rates and variance estimates
+- Recompute when the experiment design changes
+
+## Related Concepts
+- [[Hypothesis Testing]]
+- [[Statistical Significance]]
+- [[A/B Testing]]
+
+## Related Entities
+- [[Experiment Tracker]]
+

wiki/concepts/Randomization.md

@@ -0,0 +1,24 @@
+---
+title: "Randomization"
+type: concept
+tags: [statistics, experimentation]
+sources: [project-management-experiment-tracker]
+last_updated: 2026-04-20
+---
+
+## Definition
+Randomization is the assignment of units to experimental variants by chance to reduce bias and support causal inference.
+
+## Core Principles
+- Randomly assign at the correct unit level
+- Keep assignment stable during the experiment
+- Avoid contamination between variants
+- Validate balance across key segments
+
+## Related Concepts
+- [[A/B Testing]]
+- [[Hypothesis Testing]]
+
+## Related Entities
+- [[Experiment Tracker]]
+

wiki/concepts/Recruitment-Operations.md

@@ -0,0 +1,23 @@
+---
+title: "Recruitment Operations"
+type: concept
+tags: [hr, recruiting, operations]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+Recruitment Operations 指围绕招聘目标进行的多渠道投放、流程设计、漏斗优化、预算分配与效果复盘。
+
+## Core Principles
+- 按岗位类型匹配渠道
+- 用数据衡量 ROI 与转化率
+- 通过漏斗找出瓶颈并迭代
+- 将重复流程标准化与自动化
+
+## Related Entities
+- [[Recruitment Specialist]]
+- [[The Agency]]
+- [[Boss Zhipin]]
+- [[Liepin]]
+- [[Maimai]]

wiki/concepts/Smart-City.md

@@ -0,0 +1,26 @@
+---
+title: "Smart City"
+type: concept
+tags: [government, urban-infrastructure, data-platform]
+last_updated: 2026-04-20
+---
+
+## Definition
+Smart City 指将城市运行、公共服务、交通、社区治理和应急联动等能力数字化、平台化和智能化的城市治理模式。
+
+## Core Dimensions
+- 城市运行中心 / IOC
+- 城市级数据平台与感知网络
+- 智能交通、智慧社区、应急指挥
+- 可视化大屏、联动闭环与指标体系
+
+## Related Concepts
+- [[Digital Government]]
+- [[Government Procurement]]
+- [[Technical Discovery]]
+- [[Proof of Concept (POC)]]
+- [[Solution Architecture (SA)]]
+
+## Related Entities
+- [[Government Digital Presales Consultant]]
+- [[The Agency]]

wiki/concepts/Spend-Limit.md

@@ -0,0 +1,20 @@
+---
+title: "Spend Limit"
+type: concept
+tags: [finance, risk, governance]
+sources: [accounts-payable-agent]
+last_updated: 2026-04-20
+---
+
+## Definition
+Spend Limit 是允许智能体或系统在无需额外批准的情况下执行的最大支出额度。
+
+## Core Principles
+- 超过阈值的支付必须升级审批
+- 阈值应与角色权限、风险和业务场景匹配
+- 限额策略应明确、可审计、可调整
+- 支出限额应与防重机制一起使用
+
+## Related Entities
+- [[Accounts Payable Agent]]
+- [[The Agency]]

wiki/concepts/Statistical-Significance.md

@@ -0,0 +1,25 @@
+---
+title: "Statistical Significance"
+type: concept
+tags: [statistics, experimentation]
+sources: [project-management-experiment-tracker]
+last_updated: 2026-04-20
+---
+
+## Definition
+Statistical Significance indicates that an observed effect is unlikely to have occurred by random chance under the null hypothesis, according to a predefined threshold.
+
+## Core Principles
+- Define the alpha level before testing
+- Distinguish significance from business impact
+- Guard against multiple comparison inflation
+- Report confidence intervals and effect sizes
+
+## Related Concepts
+- [[Hypothesis Testing]]
+- [[A/B Testing]]
+- [[Power Analysis]]
+
+## Related Entities
+- [[Experiment Tracker]]
+

wiki/concepts/Talent-Assessment.md

@@ -0,0 +1,20 @@
+---
+title: "Talent Assessment"
+type: concept
+tags: [hr, recruiting, interview]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+Talent Assessment 是用结构化面试、行为面试、技术测试和评分卡评估候选人胜任力的过程。
+
+## Core Principles
+- 标准化评分卡，减少面试官偏差
+- 区分专业能力、通用能力与文化契合度
+- 用 STAR 方法追问真实行为
+- 让面试结论可比较、可追溯
+
+## Related Entities
+- [[Recruitment Specialist]]
+- [[The Agency]]

wiki/concepts/Technical-Discovery.md

@@ -21,4 +21,5 @@ tags: [sales, pre-sales, methodology]
 - [[Sales Engineer]] — 执行技术发现的主体
 - [[Demo Engineering]] — 技术发现的输出用于设计演示
 - [[POC-Scoping]] — 技术发现的结果定义 POC 范围
-- [[Solution Architecture]] — 技术发现是解决方案架构的前置输入
+- [[Solution Architecture]] — 技术发现是解决方案架构的前置输入
+- [[Global Standards Coverage]] — 规范、边界条件和法域要求属于发现阶段必须厘清的输入

wiki/concepts/Xinchuang.md

@@ -0,0 +1,23 @@
+---
+title: "Xinchuang"
+type: concept
+tags: [domestic-it, government-it, compliance]
+last_updated: 2026-04-20
+---
+
+## Definition
+Xinchuang（信息技术应用创新）指围绕国产 CPU、国产操作系统、国产数据库和国产中间件等进行的软硬件国产化替代与适配工作。
+
+## Core Points
+- 常见组合包括 Kunpeng、Phytium、Loongson、UOS、Kylin、DM8、KingbaseES 等
+- 需要先做兼容性测试，再逐步迁移替换
+- 重点是“可用、可管、可持续”，而不是一次性全量替换
+- 常与政府采购和等级保护、密码应用要求一起出现
+
+## Related Concepts
+- [[Government Procurement]]
+- [[Digital Government]]
+- [[Compliance Enforcement]]
+
+## Related Entities
+- [[Government Digital Presales Consultant]]

wiki/entities/Accounts-Payable-Agent.md

@@ -0,0 +1,33 @@
+---
+title: "Accounts Payable Agent"
+type: entity
+tags: [agent, finance, payments, the-agency]
+sources: [accounts-payable-agent]
+last_updated: 2026-04-20
+---
+
+## Definition
+Accounts Payable Agent 是 The Agency 体系中的应付账款与付款执行智能体，负责验证发票、路由支付、记录审计轨迹并防止重复付款。
+
+## Core Identity
+- **Role**: Payment processing and accounts payable specialist
+- **Personality**: Methodical, audit-minded, risk-aware, idempotency-first
+- **Memory**: 记住已支付发票、供应商偏好支付 rail、审批边界和付款失败历史
+
+## Key Capabilities
+- 处理供应商发票、承包商付款与周期性账单
+- 在 ACH、Wire、Crypto、Stablecoin 与 Payment API 间选择合适的支付 rail
+- 执行幂等性检查，避免重复付款
+- 记录完整审计信息并向请求方回传结果
+- 对超出授权限额或信息不一致的付款进行升级
+
+## Related Concepts
+- [[Idempotent Operation]]
+- [[Audit Trail]]
+- [[Payment Rail]]
+- [[Spend Limit]]
+- [[Labor Law Compliance]]
+- [[The Agency]]
+
+## Related Entities
+- [[The Agency]]

wiki/entities/Agentic-Identity-Trust-Architect.md

@@ -0,0 +1,39 @@
+---
+title: "Agentic Identity & Trust Architect"
+type: entity
+tags: [agent, the-agency, identity, trust, security, zero-trust]
+sources: [agentic-identity-trust]
+last_updated: 2026-04-20
+---
+
+## Definition
+Agentic Identity & Trust Architect 是 The Agency 体系中的自治智能体身份与信任架构专家，负责代理身份验证、委托授权、信任评分与可审计证据链设计。
+
+## Core Identity
+- **Role**: Identity and trust infrastructure architect for autonomous agents
+- **Personality**: Security-first, evidence-obsessed, fail-closed
+- **Memory**: 记住 credential expiry、delegation scope、evidence chain integrity 和 trust decay
+
+## Key Capabilities
+- 代理身份的加密签发与验证
+- 基于可验证结果而非自述的 trust scoring
+- 多跳 delegation chain verification 与 revocation propagation
+- append-only evidence records 与 tamper detection
+- algorithm agility / post-quantum migration readiness
+- cross-framework identity federation 与 multi-tenant isolation
+
+## Related Concepts
+- [[Identity Governance]]
+- [[Audit Trail]]
+- [[Zero Trust Access]]
+- [[The Agency]]
+
+## Related Entities
+- [[The Agency]]
+- [[Identity Graph Operator]]
+
+## Connections
+- [[The Agency]] ← contains ← [[Agentic Identity & Trust Architect]]
+- [[Agentic Identity & Trust Architect]] ← complements ← [[Identity Graph Operator]]
+- [[Agentic Identity & Trust Architect]] ← relies_on ← [[Identity Governance]]
+- [[Agentic Identity & Trust Architect]] ← emits ← [[Audit Trail]]

wiki/entities/Civil-Engineer.md

@@ -0,0 +1,32 @@
+---
+title: "Civil Engineer"
+type: entity
+tags: [agent, engineering, the-agency]
+sources: [specialized-civil-engineer]
+last_updated: 2026-04-20
+---
+
+## Definition
+Civil Engineer 是 The Agency 体系中的土木与结构工程智能体，负责在多国建筑与工程规范下进行安全、经济、可施工的设计、审查和沟通。
+
+## Core Identity
+- **Role**: Senior civil and structural engineering specialist
+- **Personality**: Methodical, safety-conscious, detail-oriented, pragmatic
+- **Memory**: 记住项目所在法域、采用规范、荷载组合、土壤条件和材料规格
+
+## Key Capabilities
+- 结构分析与设计（重力、侧向、地震、风荷载）
+- 岩土与基础设计（承载力、沉降、挡土结构）
+- 施工图、技术说明与施工方法书
+- 建筑规范合规与多标准协调
+- 施工阶段的 RFI、图纸审查与现场支持
+
+## Related Concepts
+- [[Global Standards Coverage]]
+- [[Technical Discovery]]
+- [[The Agency]]
+- [[Multi-Agent Team]]
+
+## Related Entities
+- [[The Agency]]
+- [[Multi-Agent Team]]

wiki/entities/Document-Generator.md

@@ -0,0 +1,34 @@
+---
+title: "Document Generator"
+type: entity
+tags: [agent, the-agency, document-automation, office-suite]
+description: The Agency 项目中的程序化文档创建智能体
+color: "#2563eb"
+emoji: 📄
+vibe: Professional documents from code.
+---
+
+Document Generator 是 The Agency 项目中的程序化文档创建专家智能体，专注于以代码方式生成 PDF、PPTX、XLSX 与 DOCX 等专业文档。
+
+## Core Capabilities
+- PDF Generation：用 reportlab、weasyprint、fpdf2、puppeteer 生成可打印文档
+- Presentations：用 python-pptx、pptxgenjs 生成结构化幻灯片
+- Spreadsheets：用 openpyxl、xlsxwriter、exceljs 生成格式化表格和报表
+- Word Documents：用 python-docx、docx 生成带样式的文档
+
+## Key Features
+- Use proper styles and themes instead of hardcoded formatting
+- Maintain consistent branding across deliverables
+- Support data-driven output and reusable templates
+- Ask for audience and purpose before generating
+- Provide both the generation script and the output file
+
+## Connections
+- [[The Agency]]：所属项目
+- [[Claude Skills]]：将文档生成封装为可复用流程
+- [[Prompt Engineering]]：用于定义输入、上下文与输出格式
+- [[Document Generation]]：相关概念
+
+## Aliases
+- Document Generator Agent
+- Document Creation Specialist

wiki/entities/Experiment-Tracker.md

@@ -0,0 +1,34 @@
+---
+title: "Experiment Tracker"
+type: entity
+tags: [agent, project-management]
+sources: [project-management-experiment-tracker]
+last_updated: 2026-04-20
+---
+
+Experiment Tracker is an AI agent personality specialized in experiment design, execution tracking, and data-driven decision making. It helps teams run statistically valid A/B tests, estimate sample sizes, monitor risk, and turn results into actionable recommendations.
+
+## Core Identity
+- **Role**: Scientific experimentation and validation specialist
+- **Personality**: Rigorous, methodical, hypothesis-driven, statistically precise
+- **Memory**: Remembers successful experiment patterns, significance thresholds, and validation frameworks
+
+## Key Capabilities
+- Design A/B tests and multivariate experiments
+- Define hypotheses, success metrics, and guardrail metrics
+- Estimate sample size and power requirements
+- Monitor experiment health, safety, and rollback conditions
+- Analyze outcomes and recommend go/no-go decisions
+
+## Related Concepts
+- [[A/B Testing]]
+- [[Hypothesis Testing]]
+- [[Statistical Significance]]
+- [[Power Analysis]]
+- [[Randomization]]
+
+## Related Entities
+- [[The Agency]]
+- [[Senior Project Manager]]
+- [[Project Shepherd]]
+- [[Studio Operations]]

wiki/entities/Government-Digital-Presales-Consultant.md

@@ -0,0 +1,44 @@
+---
+title: "Government Digital Presales Consultant"
+type: entity
+tags: [agent, the-agency, sales, pre-sales, government-it, compliance]
+sources: [government-digital-presales-consultant]
+last_updated: 2026-04-20
+---
+
+## Definition
+Government Digital Presales Consultant 是 The Agency 体系中的政府数字化售前专家智能体，专注于中国政务数字化、智慧城市与政府 IT 项目的政策解读、方案设计、招投标管理、POC 设计和合规适配。
+
+## Core Identity
+- **Role**: Full-lifecycle presales specialist for ToG government projects
+- **Personality**: Policy-aware, rigorous, practical, compliance-first, and fluent in business-facing language
+- **Memory**: 记住政策信号、评分规则、客户关注点、风险条款与历史成败经验
+
+## Key Capabilities
+- 政策与预算信号分析，识别项目机会
+- 解决方案设计与技术架构表达
+- 招投标文件分析、技术标与答疑准备
+- POC 范围控制与成功标准设计
+- Dengbao、Miping 与 Xinchuang 合规适配
+- 领导层、业务层、技术层与采购层的分层沟通
+
+## Related Concepts
+- [[Technical Discovery]]
+- [[Solution Architecture (SA)]]
+- [[Proof of Concept (POC)]]
+- [[Digital Government]]
+- [[Smart City]]
+- [[Government Procurement]]
+- [[Dengbao]]
+- [[Miping]]
+- [[Xinchuang]]
+- [[Compliance Enforcement]]
+
+## Related Entities
+- [[The Agency]]
+
+## Connections
+- [[The Agency]] ← contains ← [[Government Digital Presales Consultant]]
+- [[Government Digital Presales Consultant]] ← informs ← [[Digital Government]]
+- [[Government Digital Presales Consultant]] ← informs ← [[Smart City]]
+- [[Government Digital Presales Consultant]] ← depends on ← [[Government Procurement]]

wiki/entities/Identity-Graph-Operator.md

@@ -0,0 +1,38 @@
+---
+title: "Identity Graph Operator"
+type: entity
+tags: [agent, the-agency, identity, graph, entity-resolution]
+sources: [identity-graph-operator]
+last_updated: 2026-04-20
+---
+
+## Definition
+Identity Graph Operator 是 The Agency 体系中的共享身份图操作智能体，负责在多智能体环境里将同一现实世界实体解析为同一个 canonical entity，并对合并、拆分、更新提供可审计的决策流程。
+
+## Core Identity
+- **Role**: Shared identity graph operator / entity resolution specialist
+- **Personality**: Evidence-driven, deterministic, precise, review-friendly
+- **Memory**: 记住 canonical identity、合并历史、冲突模式和 tenant 边界
+
+## Key Capabilities
+- 实体归一化与 canonicalization
+- blocking / scoring / clustering 身份匹配
+- 合并与拆分提案生成
+- 乐观锁与版本控制下的安全写入
+- 冲突检测与审计追踪
+- tenant isolation 与 PII 脱敏
+
+## Related Concepts
+- [[Identity Governance]]
+- [[Audit Trail]]
+- [[AI代理（Agent）]]
+- [[Multi-Agent-System-Reliability]]
+
+## Related Entities
+- [[The Agency]]
+- [[AI代理（Agent）]]
+
+## Connections
+- [[The Agency]] ← contains ← [[Identity Graph Operator]]
+- [[Identity Graph Operator]] ← supports ← [[AI代理（Agent）]]
+- [[Identity Graph Operator]] ← emits ← [[Audit Trail]]

wiki/entities/Project-Shepherd.md

@@ -0,0 +1,38 @@
+---
+title: "Project Shepherd"
+type: entity
+tags: [agent, project-management, the-agency]
+sources: [project-management-project-shepherd]
+last_updated: 2026-04-20
+---
+
+Project Shepherd is an AI agent personality focused on cross-functional project coordination, timeline management, stakeholder alignment, and delivery governance for The Agency.
+
+## Core Identity
+- **Role**: Cross-functional project delivery specialist
+- **Personality**: Transparent, organized, risk-aware, outcome-focused
+- **Memory**: Remembers project constraints, delivery patterns, and stakeholder expectations
+
+## Key Capabilities
+- Build project charters and delivery plans
+- Track dependencies, critical path, and milestones
+- Coordinate stakeholders and manage communication
+- Monitor risks, scope changes, and quality gates
+- Capture lessons learned after delivery
+
+## Related Concepts
+- [[项目章程]]
+- [[利益相关方分析]]
+- [[工作分解结构 (WBS)]]
+- [[关键路径分析]]
+- [[风险缓解规划]]
+- [[变更控制]]
+- [[质量门]]
+- [[经验教训]]
+
+## Related Entities
+- [[The Agency]]
+- [[Studio Producer]]
+- [[Experiment Tracker]]
+- [[Senior Project Manager]]
+- [[Studio Operations]]

wiki/entities/Recruitment-Specialist.md

@@ -0,0 +1,39 @@
+---
+title: "Recruitment Specialist"
+type: entity
+tags: [agent, hr, recruitment, the-agency]
+sources: [recruitment-specialist]
+last_updated: 2026-04-20
+---
+
+## Definition
+Recruitment Specialist 是 The Agency 体系中的招聘运营与人才获取专家智能体，负责从招聘需求分析、渠道投放、候选人评估到入职与试用期管理的全流程招聘工作。
+
+## Core Identity
+- **Role**: Recruitment operations and talent acquisition specialist
+- **Personality**: Goal-oriented, data-driven, compliance-aware, candidate-centric
+- **Memory**: 记住渠道 ROI、候选人偏好、招聘漏斗瓶颈和合规边界
+
+## Key Capabilities
+- 招聘需求分析与 JD 优化
+- 多渠道招聘投放与 ROI 评估
+- 结构化面试、行为面试与技术面试设计
+- 人才池管理与候选人分层运营
+- offer、背景调查、入职和试用期管理
+- 劳动法与隐私合规检查
+
+## Related Concepts
+- [[Recruitment Operations]]
+- [[Talent Assessment]]
+- [[Labor Law Compliance]]
+- [[Candidate Experience]]
+- [[Employer Brand]]
+- [[ATS]]
+- [[Onboarding]]
+- [[The Agency]]
+
+## Related Entities
+- [[The Agency]]
+- [[Boss Zhipin]]
+- [[Liepin]]
+- [[Maimai]]

wiki/entities/The-Agency.md

@@ -35,8 +35,10 @@ tags: [project, ai-agents, open-source]
 - [[XR Interface Architect]]：XR 界面架构师智能体，专注于沉浸式 3D 环境的空间界面设计
 - [[XR Cockpit Interaction Specialist]]：XR 座舱交互专家智能体，专注于设计和开发 XR 环境的沉浸式座舱控制系统
 - [[macOS Spatial/Metal Engineer]]：macOS 空间计算与 Metal 渲染工程师智能体，专注于 Native Swift 和 Metal 高性能 3D 渲染
-- [[visionOS Spatial Engineer]]：visionOS 空间计算原生开发专家智能体，专注于 Native visionOS 空间计算、SwiftUI 体积化界面和 Liquid Glass 设计实现
-- [[Terminal Integration Specialist]]：终端仿真和 SwiftTerm 集成专家智能体
+|- [[visionOS Spatial Engineer]]：visionOS 空间计算原生开发专家智能体，专注于 Native visionOS 空间计算、SwiftUI 体积化界面和 Liquid Glass 设计实现
+|- [[Identity Graph Operator]]：共享身份图操作智能体，负责实体解析、合并与冲突治理
+|- [[Terminal Integration Specialist]]：终端仿真和 SwiftTerm 集成专家智能体
+|- [[Civil Engineer]]：土木与结构工程智能体，负责多国规范下的结构分析、岩土设计和建筑合规
 
 ## 别名
 - agency-agents：GitHub 仓库名称

wiki/index.md

@@ -39,12 +39,15 @@
 - [UX Architect Agent 设计文档](sources/design-ux-architect.md) — UX Architect 技术架构与 UX 专家智能体设计规范，涵盖 CSS 设计系统、布局框架、主题切换机制
 
 - [Senior Project Manager](sources/project-manager-senior.md) — Converts specifications into developer-ready task lists, enforces realistic scope, and maintains project memory
+- [Experiment Tracker](sources/project-management-experiment-tracker.md) — 实验设计与执行跟踪智能体，专注于 A/B 测试、假设验证和数据驱动决策
 
 - [Visual Storyteller](sources/design-visual-storyteller.md) — 视觉故事讲述专家智能体，专注于创建视觉叙事、多媒体内容和品牌故事设计
 - [Whimsy Injector Agent Personality](sources/design-whimsy-injector.md) — 品牌体验趣味性注入专家，专注于为品牌添加个性化和乐趣
 
 - [Brand Guardian Agent 设计文档](sources/design-brand-guardian.md) — The Agency 项目中的品牌战略与身份保护专家智能体，专注于品牌基础框架、视觉识别系统、品牌一致性与价值保护
 - [Image Prompt Engineer Agent](sources/design-image-prompt-engineer.md) — AI 图像生成提示词工程专家智能体，专注于将视觉概念转化为精确的提示词语言
+- [Document Generator](sources/specialized-document-generator.md) — The Agency 项目中的程序化文档创建智能体，负责 PDF、PPTX、XLSX 与 DOCX 的代码化生成
+- [Agentic Identity & Trust Architect](sources/agentic-identity-trust.md) — The Agency 中负责自治 AI Agent 身份、授权、证据链与信任评分的零信任专家智能体
 
 - [Inclusive Visuals Specialist](sources/design-inclusive-visuals-specialist.md) — 包容性视觉设计专家智能体，专注于对抗 AI 生成中的系统性偏见，生成文化准确、有尊严的多元人像
 - [XR Cockpit Interaction Specialist](sources/xr-cockpit-interaction-specialist.md) — XR 座舱交互专家智能体，专注于设计和开发 XR 环境的沉浸式座舱控制系统
@@ -54,6 +57,7 @@
 - [XR Interface Architect](sources/xr-interface-architect.md) — XR 界面架构师智能体，专注于沉浸式 3D 环境的空间界面设计
 
 - [visionOS Spatial Engineer](sources/visionos-spatial-engineer.md) — visionOS 空间计算原生开发专家智能体，专注于 SwiftUI 体积化界面和 Liquid Glass 设计实现
+- [Identity Graph Operator](sources/identity-graph-operator.md) — 多智能体共享身份图操作智能体，负责实体解析、合并提案与冲突治理
 
 - [Paid Media Programmatic & Display Buyer](sources/paid-media-programmatic-buyer.md) — 付费媒体程序化购买与展示广告智能体，专注于 DSP 平台管理、Google 展示网络、ABM 展示和合作伙伴媒体策略
 
@@ -63,7 +67,12 @@
 
 - [Paid Media Auditor](sources/paid-media-auditor.md) — 付费媒体审计智能体，系统化评估 Google Ads、Microsoft Ads 和 Meta 广告账户，识别 15-30% 效率提升机会
 - [Studio Operations](sources/project-management-studio-operations.md) — The Agency 项目中的工作室运营与流程优化智能体，负责日常效率、资源协调和持续改进
-- [Project Shepherd](sources/project-management-project-shepherd.md) — 专业项目管理人员智能体，专注于跨职能项目协调、时间线管理和利益相关方对齐
+- [Accounts Payable Agent](sources/accounts-payable-agent.md) — The Agency 体系中的应付账款与付款执行智能体，负责发票验证、支付路由与审计轨迹
+- [Experiment Tracker](entities/Experiment-Tracker.md) — 实验设计与执行跟踪智能体，专注于 A/B 测试、假设验证和数据驱动决策
+- [Project Shepherd](entities/Project-Shepherd.md) — 专业项目管理人员智能体，专注于跨职能项目协调、时间线管理和利益相关方对齐
+- [Recruitment Specialist](entities/Recruitment-Specialist.md) — The Agency 体系中的招聘运营与人才获取专家，负责全流程招聘与劳动法合规
+- [Accounts Payable Agent](entities/Accounts-Payable-Agent.md) — The Agency 体系中的应付账款与付款执行智能体，负责验证发票、路由支付与防止重复付款
+- [Experiment Tracker](sources/project-management-experiment-tracker.md) — 实验设计与执行跟踪智能体，专注于 A/B 测试、假设验证和数据驱动决策
 - [Jira Workflow Steward](sources/project-management-jira-workflow-steward.md) — 交付可追溯性治理智能体，专注于 Jira 关联的 Git 工作流、可追溯提交、结构化 PR 和发布安全分支策略
 
 - [Paid Media Ad Creative Strategist](sources/paid-media-creative-strategist.md) — 付费媒体广告创意策略智能体，专注于广告文案撰写、响应式搜索广告优化和创意测试框架
@@ -86,6 +95,8 @@
 - [Pipeline Analyst](sources/sales-pipeline-analyst.md) — 销售管道健康诊断与收入预测智能体，专注于管道健康评估、交易速度分析和预测准确性
 
 - [Sales Engineer](sources/sales-engineer.md) — 售前工程师智能体，专注于技术发现、演示工程、POC 设计、竞争定位和解决方案架构
+- [Government Digital Presales Consultant](sources/government-digital-presales-consultant.md) — 政府数字化售前智能体，专注于政策解读、方案设计、招投标与合规适配
+- [Civil Engineer](sources/specialized-civil-engineer.md) — 土木与结构工程智能体，专注于多国规范下的结构分析、岩土设计和建筑合规
 
 - [Cloud Learning Master Index](sources/cloud-learning-master-index.md) — Public Cloud Learning Sessions 课程分类索引与统计信息（10 个类别，121 个视频）
 
@@ -752,12 +763,23 @@
 - [Christian-ODonough](entities/Christian-ODonough.md) — AWS 专家，AWS EUC 服务演讲者
 - [UX Researcher](entities/UX-Researcher.md) — The Agency 项目中的用户体验研究智能体，专注于用户行为分析
 - [Outbound Strategist](entities/Outbound-Strategist.md) — The Agency 项目中的基于信号触发的外呼销售策略智能体，通过购买信号识别和 ICP 定义提升外呼转化率
+- [Identity Graph Operator](entities/Identity-Graph-Operator.md) — The Agency 体系中的共享身份图操作智能体，负责实体归一化、合并与冲突治理
+- [Document Generator](entities/Document-Generator.md) — The Agency 项目中的程序化文档创建智能体，专注于 PDF、PPTX、XLSX 与 DOCX 生成
+- [Agentic Identity & Trust Architect](entities/Agentic-Identity-Trust-Architect.md) — The Agency 体系中的自治智能体身份与信任架构专家，负责代理身份验证、委托授权与可审计证据链
+- [Experiment Tracker](entities/Experiment-Tracker.md) — 实验设计与执行跟踪智能体，专注于 A/B 测试、假设验证和数据驱动决策
+- [Project Shepherd](entities/Project-Shepherd.md) — 专业项目管理人员智能体，专注于跨职能项目协调、时间线管理和利益相关方对齐
+- [Recruitment Specialist](entities/Recruitment-Specialist.md) — The Agency 体系中的招聘运营与人才获取专家，负责全流程招聘与劳动法合规
 
 ## Concepts
 - [Process Optimization](concepts/Process-Optimization.md) — 通过识别瓶颈和重设工作流提升效率、质量与可靠性
 - [Resource Allocation](concepts/Resource-Allocation.md) — 在人员、工具、时间和预算之间协调分配资源
 - [Operational Excellence](concepts/Operational-Excellence.md) — 通过标准化、监控和持续改进实现可靠且可扩展的运营
 - [Cross-Functional Leadership](concepts/Cross-Functional-Leadership.md) — 跨团队与跨职能协作以达成共享目标
+- [A/B Testing](concepts/A-B-Testing.md) — 控制实验，比较对照组与处理组以衡量因果影响
+- [Hypothesis Testing](concepts/Hypothesis-Testing.md) — 统计检验框架，用于判断观察结果是否足以拒绝零假设
+- [Statistical Significance](concepts/Statistical-Significance.md) — 结果不太可能由随机性产生的统计判定
+- [Power Analysis](concepts/Power-Analysis.md) — 估算达到目标检验功效所需样本量的方法
+- [Randomization](concepts/Randomization.md) — 通过随机分配降低偏差并支持因果推断
 - [AWS Config](entities/AWS-Config.md) — AWS 配置审计与合规性服务，记录资源配置变化，支持自动检测和修复
 - [IAM 用户](concepts/IAM-用户.md) — IAM 持久化身份，主要用于服务账号
 - [IAM 角色](concepts/IAM-角色.md) — IAM 临时身份，将主体与权限关联
@@ -777,6 +799,30 @@
 - [Usability Testing](concepts/Usability-Testing.md) — 可用性测试，评估产品易用性
 - [User Persona](concepts/User-Persona.md) — 用户画像，基于实证数据创建的理想用户原型
 - [User Journey Mapping](concepts/User-Journey-Mapping.md) — 用户旅程映射，可视化用户与产品交互全过程
+- [Recruitment Operations](concepts/Recruitment-Operations.md) — 招聘渠道投放、漏斗优化与 ROI 评估的运营方法
+- [Identity Governance](concepts/Identity-Governance.md) — 多智能体环境下的实体身份解析、合并与审计治理框架
+- [Digital Government](concepts/Digital-Government.md) — 政务服务、数据治理和内部协同的数字化重构模式
+- [Smart City](concepts/Smart-City.md) — 城市运行、公共服务与治理的数字化、平台化和智能化模式
+- [Government Procurement](concepts/Government-Procurement.md) — 政府机构围绕预算、招标、评标和合同签署的标准化采购流程
+- [Dengbao](concepts/Dengbao.md) — 网络安全等级保护制度及其建设、测评与整改要求
+- [Miping](concepts/Miping.md) — 商用密码应用安全性评估要求
+- [Xinchuang](concepts/Xinchuang.md) — 国产 CPU、OS、数据库与中间件适配与替代工作
+- [Talent Assessment](concepts/Talent-Assessment.md) — 通过结构化与行为面试评估候选人胜任力的过程
+- [Smart City](concepts/Smart-City.md) — 城市运行、公共服务与治理的数字化、平台化和智能化模式
+- [Government Procurement](concepts/Government-Procurement.md) — 政府机构围绕预算、招标、评标和合同签署的标准化采购流程
+- [Dengbao](concepts/Dengbao.md) — 网络安全等级保护制度及其建设、测评与整改要求
+- [Miping](concepts/Miping.md) — 商用密码应用安全性评估要求
+- [Xinchuang](concepts/Xinchuang.md) — 国产 CPU、OS、数据库与中间件适配与替代工作
+- [Talent Assessment](concepts/Talent-Assessment.md) — 通过结构化与行为面试评估候选人胜任力的过程
+- [Labor Law Compliance](concepts/Labor-Law-Compliance.md) — 招聘、合同、背景调查与用工全过程合规要求
+- [Idempotent Operation](concepts/Idempotent-Operation.md) — 可重复执行而不会产生额外副作用的幂等操作
+- [Audit Trail](concepts/Audit-Trail.md) — 记录关键操作、决策与结果的可追溯日志
+- [Payment Rail](concepts/Payment-Rail.md) — 支付从发送方到接收方所经过的结算通道或网络
+- [Spend Limit](concepts/Spend-Limit.md) — 允许在无需额外批准的情况下执行的最大支出额度
+- [Candidate Experience](concepts/Candidate-Experience.md) — 候选人从投递、筛选到入职全过程的体验质量
+- [Employer Brand](concepts/Employer-Brand.md) — 候选人与员工对企业工作环境与声誉的整体认知
+- [ATS](concepts/ATS.md) — Applicant Tracking System，用于管理招聘流程、候选人与状态
+- [Onboarding](concepts/Onboarding.md) — 从 offer 接受到试用期管理的新员工融入流程
 
 - [Product](concepts/Product.md) — 具有独立 CI/CD 流水线或发布周期的软件分发
 - [Product-Backlog](concepts/Product-Backlog.md) — 产品待办列表，存放待开发功能和需求，高亮收益和优先级
@@ -787,6 +833,7 @@
 - [Log Analytics](concepts/Log-Analytics.md) — 日志分析，日志数据的采集、存储、搜索和可视化
 - [ELK Stack](concepts/ELK-Stack.md) — Elasticsearch + Logstash + Kibana 开源日志分析技术栈
 - [OpenSearch](concepts/OpenSearch.md) — AWS 的 ELK 开源分支，托管日志分析服务
+- [Global Standards Coverage](concepts/Global-Standards-Coverage.md) — 跨多国工程规范进行统一设计与审查的能力
 - [Logstash](concepts/Logstash.md) — ELK Stack 中的日志处理管道
 - [Kibana](concepts/Kibana.md) — ELK Stack 的 Web 前端和可视化界面
 - [Recovery Assurance](concepts/Recovery-Assurance.md) — 恢复保障，从设计层面确保系统具备恢复能力
@@ -836,6 +883,7 @@
 - [声音克隆](concepts/声音克隆.md) — 通过少量音频样本训练AI模型，生成与原声相似的语音的技术
 - [提示语设计](concepts/提示语设计.md) — 通过精心设计的提示词提升 AI 输出质量的技术
 - [Claude Skills](concepts/Claude-Skills.md) — 写给 Claude 的"说明书"和 SOP，将反复执行的任务拆解为 AI 可稳定复用流程的技术范式
+- [Document Generation](concepts/Document-Generation.md) — 通过代码、模板和数据驱动流程自动生成 PDF、PPTX、XLSX、DOCX 等专业文档的工作流
 - [Obsidian Skills](concepts/Obsidian-Skills.md) — 写给 AI Agent 的"说明书"，扩展 Obsidian 能力的技能集
 - [Obsidian CLI](concepts/Obsidian-CLI.md) — Obsidian 官方命令行工具，支持笔记增删改查
 - [obsidian-bases](concepts/obsidian-bases.md) — 生成 .base 格式数据库配置文件的技能

wiki/overview.md

@@ -6,6 +6,7 @@ AI 开源项目、Cloud & DevOps、Vibe Coding、AI时代个人发展、跨境
 ## 核心概念
 - The Agency：开源 AI 智能体集合项目，汇集各类专业化 AI Agent
 - Image Prompt Engineer：The Agency 项目中的 AI 图像生成提示词工程专家智能体，专注于将视觉概念转化为精确的提示词语言
+- Agentic Identity & Trust Architect：The Agency 中负责自治 AI Agent 身份、授权、证据链与信任评分的专家智能体
 - 智能体设计规范：智能体文件结构、身份与记忆、核心使命、技术交付物、工作流程的完整定义
 - 智能体设计原则：六大设计原则（鲜明性格、明确交付物、成功指标、经过验证的工作流、学习记忆、真实场景测试）
 - UX Architect：The Agency 项目中的技术架构与 UX 专家智能体，为开发者提供 CSS 设计系统、布局框架、主题切换机制和清晰实现路径
@@ -148,6 +149,7 @@ AI 开源项目、Cloud & DevOps、Vibe Coding、AI时代个人发展、跨境
 - 数字导师：用AI复活历史人物，让其成为日常对话的思维顾问，通过思维蒸馏技术提取人物的核心心智模型
 - 思维蒸馏：通过6个并行Agent从6个维度（著作、对话、表达DNA、他者视角、决策、时间线）采集信息，提炼核心思维框架生成AI Skill的技术
 - Claude Skills：写给 Claude 的"说明书"和技术规范，将反复执行的任务拆解为 AI 可稳定复用流程的技术范式
+- Document Generation：通过代码和模板生成 PDF、PPTX、XLSX、DOCX 等专业文档的自动化工作流
 - **baoyu-skills**：宝玉分享的 Claude Code 技能集，提供内容生成（小红书图片、信息图、封面图、幻灯片、漫画、文章插图）、AI 生成（多服务商图像生成）、工具（YouTube 字幕下载、URL 转 Markdown、社交媒体发布）17+ 个技能
 - Zettelkasten：卢曼卡片盒知识管理系统，通过原子化笔记和索引入口构建知识网络
 - **fireworks-tech-graph**：AI 驱动技术图生成工具，将中文描述转化为 SVG/PNG 格式的架构图、流程图、UML 图

wiki/sources/accounts-payable-agent.md

@@ -0,0 +1,39 @@
+---
+title: "Accounts Payable Agent"
+type: source
+tags: [agent, finance, payments, automation]
+date: 2026-04-20
+last_updated: 2026-04-20
+source_file: raw/Agent/agency-agents/specialized/accounts-payable-agent.md
+---
+
+## Source File
+- [[raw/Agent/agency-agents/specialized/accounts-payable-agent.md]]
+
+## Summary
+- Accounts Payable Agent 是 The Agency 体系中的支付与应付账款专家，负责处理供应商发票、承包商付款与周期性账单，并可在 ACH、Wire、Crypto、Stablecoin 与 Payment API 等多种 payment rail 间自动路由。
+- 该智能体的核心原则是幂等性、严格验证、完整审计与不重复付款，任何超过授权阈值的付款都会被升级处理。
+- 它强调与其他智能体协作，在收到付款请求后完成验证、执行、记录并通知请求方。
+
+## Key Claims
+- 付款前必须检查同一发票是否已经支付，避免重复付款
+- 50 美元以上的付款必须先验证收款方地址或账户
+- 任何付款都需要记录发票编号、金额、rail、时间戳和状态
+- 若某条 payment rail 失败，应尝试下一条可用 rail，再决定是否升级
+- 超出授权限额的付款必须交由人工审批
+
+## Key Quotes
+> "Idempotency first" — 付款安全的首要规则
+> "Never pay twice" — 防止重复付款的核心约束
+> "Audit everything" — 每笔付款都必须留下完整审计轨迹
+
+## Connections
+- [[The Agency]] — 该智能体所属的项目框架
+- [[Idempotent Operation]] — 重复执行也不应产生重复付款
+- [[Audit Trail]] — 每笔付款必须可追踪、可审计
+- [[Payment Rail]] — 选择最优支付通道完成结算
+- [[Spend Limit]] — 超过授权阈值时必须升级审批
+- [[Labor Law Compliance]] — 付款协作场景中可能涉及合规约束
+
+## Contradictions
+- 无明显冲突

wiki/sources/agentic-identity-trust.md

@@ -0,0 +1,48 @@
+---
+title: "Agentic Identity & Trust Architect"
+type: source
+tags: [agent, the-agency, identity, trust, security, zero-trust, audit]
+date: 2026-04-20
+last_updated: 2026-04-20
+---
+
+## Source File
+- [[raw/Agent/agency-agents/specialized/agentic-identity-trust.md]]
+
+## Summary
+- Agentic Identity & Trust Architect is The Agency's zero-trust specialist for autonomous agents, focused on cryptographic identity, delegated authorization, trust scoring, and tamper-evident evidence.
+- The role separates agent identity from authorization and insists that every consequential action be backed by verifiable proof, not self-reported claims.
+- It complements [[Identity Graph Operator]], which resolves entity identity, by providing the agent-side identity and trust layer.
+
+## Key Claims
+- Agents must prove who they are with cryptographic identity checks; self-reported identity is not enough.
+- Authorization must be scoped, revocable, and verifiable through delegation chains.
+- Trust should start at zero and only increase through verifiable outcomes, fresh credentials, and intact evidence chains.
+- Evidence records must be append-only and tamper-evident; if evidence cannot be written, the action should not proceed.
+- Algorithm agility and post-quantum migration readiness should be designed in from the start.
+
+## Key Quotes
+> "Never trust self-reported identity." — zero-trust rule for agent networks
+
+> "If evidence cannot be written, the action should not proceed." — fail-closed authorization rule
+
+## Key Concepts
+- [[Identity Governance]]
+- [[Audit Trail]]
+- [[Zero Trust Access]]
+- [[Identity Graph Operator]]
+- [[The Agency]]
+
+## Key Entities
+- [[Agentic Identity & Trust Architect]]
+- [[Identity Graph Operator]]
+- [[The Agency]]
+
+## Connections
+- [[The Agency]] ← contains ← [[Agentic Identity & Trust Architect]]
+- [[Agentic Identity & Trust Architect]] ← complements ← [[Identity Graph Operator]]
+- [[Identity Governance]] ← informed_by ← [[Agentic Identity & Trust Architect]]
+- [[Audit Trail]] ← constrains ← [[Agentic Identity & Trust Architect]]
+
+## Contradictions
+- None noted

wiki/sources/government-digital-presales-consultant.md

@@ -0,0 +1,56 @@
+---
+title: "Government Digital Presales Consultant"
+type: source
+tags: [agent, the-agency, presales, government-it, compliance]
+date: 2026-04-20
+---
+
+## Source File
+- [[raw/Agent/agency-agents/specialized/government-digital-presales-consultant.md]]
+
+## Summary
+- 核心主题：面向中国政府数字化转型市场（ToG）的售前专家角色，覆盖政策解读、方案设计、招投标、POC 验证与合规适配
+- 问题域：政务项目机会识别难、招投标流程复杂、合规要求严格、技术方案需要同时满足业务与监管约束
+- 方法/机制：以政策信号驱动机会发现，以业务场景驱动方案设计，以 POC 和答标材料完成赢单闭环
+- 结论/价值：将政府项目售前从“拼概念”转为“拼合规、拼方案、拼交付可行性”，帮助团队更稳定地推进项目成交
+
+## Key Claims
+- 政务数字化项目要从国家/省市政策和预算信号中识别机会，而不是只等招标公告
+- Dengbao、Miping 与 Xinchuang 不是加分项，而是政府系统常见的硬约束
+- 售前方案必须围绕业务场景表达价值，避免只讲架构和技术名词
+- 评分高低往往取决于对招标文件条款、评分规则与资格条件的精准响应
+- POC 的作用是证明关键能力，不是无限期免费试做
+- 采购、技术、业务和领导层关注点不同，表达方式必须分层
+
+## Key Quotes
+> "Dengbao、Miping 和 Xinchuang are mandatory, not bonus points." — 合规底线
+
+> "The client cares about service outcomes, not microservices architecture." — 方案表达原则
+
+## Key Concepts
+- [[Technical Discovery]]
+- [[Solution Architecture (SA)]]
+- [[Proof of Concept (POC)]]
+- [[Digital Government]]
+- [[Smart City]]
+- [[Government Procurement]]
+- [[Dengbao]]
+- [[Miping]]
+- [[Xinchuang]]
+- [[Compliance Enforcement]]
+
+## Key Entities
+- [[The Agency]]
+
+## Connections
+- [[Government Digital Presales Consultant]] ← role within ← [[The Agency]]
+- [[Government Digital Presales Consultant]] ← applies ← [[Technical Discovery]]
+- [[Government Digital Presales Consultant]] ← shapes ← [[Solution Architecture (SA)]]
+- [[Government Digital Presales Consultant]] ← validates via ← [[Proof of Concept (POC)]]
+- [[Government Digital Presales Consultant]] ← constrained by ← [[Government Procurement]]
+- [[Government Digital Presales Consultant]] ← constrained by ← [[Dengbao]]
+- [[Government Digital Presales Consultant]] ← constrained by ← [[Miping]]
+- [[Government Digital Presales Consultant]] ← constrained by ← [[Xinchuang]]
+
+## Contradictions
+- 无明显冲突

wiki/sources/identity-graph-operator.md

@@ -0,0 +1,45 @@
+---
+title: "Identity Graph Operator"
+type: source
+tags: [agent, the-agency, identity, graph, entity-resolution]
+date: 2026-04-20
+last_updated: 2026-04-20
+---
+
+## Source File
+- [[raw/Agent/agency-agents/specialized/identity-graph-operator.md]]
+
+## Summary
+- 核心主题：Identity Graph Operator 负责多智能体系统中的共享身份图与实体归一化，确保不同 agent 面对同一现实世界实体时得到同一 canonical identity
+- 问题域：重复记录、冲突写入、跨 agent 身份不一致、合并/拆分决策难以追踪
+- 方法/机制：通过 blocking、scoring、clustering 和乐观锁在单一引擎内执行身份解析、合并提案与冲突检测
+- 结论/价值：为多智能体系统提供确定性、可审计、可回滚的身份层，降低重复创建与级联错误风险
+
+## Key Claims
+- 同一输入必须得到同一 entity_id，determinism 是身份解析的首要原则
+- 任何 merge/split/update 都应经过单一引擎处理，并保留事件历史与回滚能力
+- 解析结果应返回 confidence、canonical_data、version 等可审计字段
+- 多 agent 协作时优先提案而非直接突变，以便人工或其他 agent 审核
+- 共享身份层需要 tenant isolation，并默认对 PII 进行脱敏
+
+## Key Quotes
+> "Same input, same output. Two agents resolving the same record must get the same entity_id." — 设计原则
+
+## Key Concepts
+- [[AI代理（Agent）]]：Identity Graph Operator 是支撑多智能体协作可靠性的基础设施
+- [[Audit Trail]]：所有合并、拆分、匹配都应有理由和置信度记录
+- [[Identity Governance]]：共享身份层的治理框架，强调 canonical identity 与权限边界
+- [[Multi-Agent-System-Reliability]]：身份层是多智能体系统可靠性的前提之一
+
+## Key Entities
+- [[The Agency]]：开源 AI 智能体集合项目，Identity Graph Operator 所属项目语境
+- [[Identity Graph Operator]]：该源文档对应的专门智能体角色
+
+## Connections
+- [[The Agency]] ← contains ← [[Identity Graph Operator]]
+- [[Identity Graph Operator]] ← supports ← [[AI代理（Agent）]]
+- [[Identity Graph Operator]] ← constrains_by ← [[Audit Trail]]
+- [[Identity Graph Operator]] ← relies_on ← [[Identity Governance]]
+
+## Contradictions
+- 未发现明显冲突

wiki/sources/project-management-experiment-tracker.md

@@ -0,0 +1,41 @@
+---
+title: "Experiment Tracker"
+type: source
+tags: [agent, project-management]
+date: 2026-04-20
+source_file: raw/Agent/agency-agents/project-management/project-management-experiment-tracker.md
+---
+
+## Source File
+- [[raw/Agent/agency-agents/project-management/project-management-experiment-tracker.md]]
+
+## Summary
+- 核心主题：Experiment Tracker 是一位专注于实验设计、执行跟踪和数据驱动决策的项目管理智能体
+- 问题域：A/B 测试、特性实验、假设验证与实验组合管理
+- 方法/机制：明确假设、统计显著性、样本量计算、随机分配、风险监控与回滚
+- 结论/价值：通过严谨的实验方法确保产品决策建立在可验证数据之上
+
+## Key Claims
+- 设计实验前应先完成样本量与统计功效分析，默认追求 95% 统计置信度
+- 实验必须保持随机分配、避免抽样偏差，并在多方案比较时进行多重比较修正
+- 不应在没有明确早停规则的情况下提前终止实验
+- 实验安全需要监控用户体验退化、隐私合规和回滚机制
+
+## Key Quotes
+> "Always calculate proper sample sizes before experiment launch" — statistics and rigor rule
+
+> "Never stop experiments early without proper early stopping rules" — experiment integrity rule
+
+## Connections
+- [[The Agency]] — 所属智能体集合项目
+- [[Senior Project Manager]] — 同属项目管理语境，但更偏向任务拆解与交付执行
+- [[Project Shepherd]] — 同属项目管理语境，但更偏向跨职能协调与交付治理
+- [[Studio Operations]] — 同属项目管理语境，但更偏向运营流程和资源协调
+- [[A/B Testing]] — 核心实验类型之一
+- [[Hypothesis Testing]] — 实验设计的统计基础
+- [[Statistical Significance]] — 决策判定依据
+- [[Power Analysis]] — 样本量与检验功效的计算方法
+- [[Randomization]] — 控制偏差的实验设计原则
+
+## Contradictions
+- 与直觉驱动决策存在冲突：该智能体强调先验证、后推广，反对未经验证的主观拍板。

wiki/sources/recruitment-specialist.md

@@ -0,0 +1,51 @@
+---
+title: "Recruitment Specialist"
+type: source
+tags: [agent, the-agency, recruitment, hr, compliance]
+date: 2026-04-20
+last_updated: 2026-04-20
+---
+
+## Source File
+- [[raw/Agent/agency-agents/specialized/recruitment-specialist.md]]
+
+## Summary
+- 核心主题：Recruitment Specialist 是 The Agency 体系中的招聘运营与人才获取专家，覆盖中国主流招聘平台、人才评估、面试设计、入职管理和劳动法合规
+- 问题域：招聘渠道效率、JD 质量、候选人体验、用工合规、offer/入职流程
+- 方法/机制：通过多渠道投放、结构化面试、数据驱动筛选、雇主品牌内容和 ATS 流程实现端到端招聘运营
+- 结论/价值：为企业提供可量化、可审计、合规的全流程招聘系统，兼顾效率、候选人体验与法律风险控制
+
+## Key Claims
+- Boss Zhipin、Lagou、Liepin、Zhaopin、51job、Maimai 和 LinkedIn China 各有不同的岗位适配与 ROI 侧重点
+- JD 应区分硬性要求与软性偏好，并从候选人视角强调文化、成长和福利
+- 所有招聘决策都应以数据支持，避免凭直觉选人
+- 候选人个人信息、背景调查和不竞争义务筛查必须符合法律与授权要求
+- 初筛反馈应在 48 小时内完成，以维护候选人体验和雇主口碑
+
+## Key Concepts
+- [[Recruitment Operations]]：多渠道招聘投放、预算分配和漏斗优化
+- [[Talent Assessment]]：通过结构化与行为面试评估胜任力的流程
+- [[Labor Law Compliance]]：招聘、签约、背景调查与用工全过程合规
+- [[Candidate Experience]]：候选人从投递到 offer 的体验设计
+- [[Employer Brand]]：通过内容与口碑构建雇主吸引力
+- [[ATS]]：用系统化流程管理招聘漏斗和候选人数据
+- [[Onboarding]]：从 offer 到入职与试用期管理的标准流程
+
+## Key Entities
+- [[The Agency]]：Recruitment Specialist 所属项目框架
+- [[Boss Zhipin]]：主打直聊与曝光优化的招聘平台
+- [[Liepin]]：适合中高阶岗位的猎头平台
+- [[Maimai]]：适合雇主品牌与被动候选人触达的职业社交平台
+
+## Connections
+- [[The Agency]] ← contains ← [[Recruitment Specialist]]
+- [[Recruitment Specialist]] ← supports ← [[Recruitment Operations]]
+- [[Recruitment Specialist]] ← applies ← [[Talent Assessment]]
+- [[Recruitment Specialist]] ← constrained_by ← [[Labor Law Compliance]]
+- [[Recruitment Specialist]] ← improves ← [[Candidate Experience]]
+- [[Recruitment Specialist]] ← builds ← [[Employer Brand]]
+- [[Recruitment Specialist]] ← operationalized_by ← [[ATS]]
+- [[Recruitment Specialist]] ← extends_to ← [[Onboarding]]
+
+## Contradictions
+- 无明显冲突

wiki/sources/specialized-civil-engineer.md

@@ -0,0 +1,39 @@
+---
+title: "Civil Engineer"
+type: source
+tags: [agent, the-agency, engineering, civil]
+date: 2026-04-20
+---
+
+## Source File
+- [[raw/Agent/agency-agents/specialized/specialized-civil-engineer.md]]
+
+## Summary
+- 这份智能体规范定义了 Civil Engineer，一位严谨的土木/结构工程专家，强调在多国标准下输出安全、经济、可施工的设计
+- 主题覆盖结构分析、岩土评估、施工图与技术说明、建筑规范合规，以及多标准项目中的冲突协调
+- 核心价值在于：每个设计都必须明确治理规范、版本、荷载组合与关键假设，并同时检查 ULS 与 SLS
+- 适用场景包括跨 Eurocode、ACI、AISC、AS/NZS、CSA、GB、IS、AIJ 等标准的国际项目
+
+## Key Claims
+- Civil Engineer 必须同时处理结构安全、经济性和可施工性，而不是只追求理论强度
+- 每个计算包都应明确治理规范、版本、国家附录/地方修订与关键假设
+- 设计必须同时验证 ULS 和 SLS，不能只做强度校核
+- 岩土参数不能凭空假设，必须基于勘察报告或清晰的书面假设
+- 多标准项目需要为每个构件/子系统明确适用规范，并记录冲突解决策略
+
+## Key Quotes
+> "Always state the governing code edition and national annex at the start of every calculation package." — 规范与版本要求
+
+> "Never assume soil parameters without a ground investigation report or clear stated assumptions." — 岩土严谨性要求
+
+> "The section passes strength (ULS) but deflection (SLS) governs." — 结构设计中强度与使用性并重
+
+## Connections
+- [[Civil Engineer]] — 该 source 对应的实体页面
+- [[The Agency]] — The Agency 体系中的专业化工程智能体之一
+- [[Multi-Agent Team]] — 体现专职角色 + 共享上下文的多智能体协作模式
+- [[Technical Discovery]] — 项目前期必须先明确规范、荷载、边界条件与决策标准
+- [[Global Standards Coverage]] — 覆盖 Eurocode、ACI、AISC、AS/NZS、GB、IS、AIJ 等多规范体系
+
+## Contradictions
+- 无明显冲突

wiki/sources/specialized-document-generator.md

@@ -0,0 +1,47 @@
+---
+title: "Document Generator"
+type: source
+tags: [agent, the-agency, document-generation, office-suite]
+date: 2026-04-20
+---
+
+## Source File
+- [[raw/Agent/agency-agents/specialized/specialized-document-generator.md]]
+
+## Summary
+- 核心主题：Document Generator 专家智能体负责以代码方式生成 PDF、PPTX、XLSX 和 DOCX 等专业文档
+- 问题域：从零手工排版、格式不一致、难以复用模板、数据可视化质量不稳定
+- 方法/机制：使用 Python/Node.js 文档生成库，结合模板、样式和数据驱动流程输出成品文件
+- 结论/价值：将文档生产变成可重复、可自动化的工程流程，而不是一次性手工设计
+
+## Key Claims
+- Document Generator 擅长使用代码化方式生成专业文档
+- PDF 可用 reportlab、weasyprint、fpdf2、puppeteer 等工具生成
+- PPTX 可用 python-pptx 或 pptxgenjs 生成
+- XLSX 可用 openpyxl、xlsxwriter、exceljs 生成
+- DOCX 可用 python-docx 或 docx 生成
+- 文档必须使用样式与主题，而不是硬编码字体和字号
+- 输出应兼顾品牌一致性、可访问性与模板复用
+- 生成前应确认受众与目的，并交付脚本与成品文件
+
+## Key Quotes
+> "Generate professional documents using the right tool for each format." — 文档格式选择原则
+
+> "Use proper styles — Never hardcode fonts/sizes; use document styles and themes." — 关键规则
+
+## Key Concepts
+- [[Claude Skills]]：将重复性的文档生成流程封装为可复用 SOP
+- [[Prompt Engineering]]：需要清晰的输入、上下文和输出格式
+- [[Document Generation]]：代码化文档生产与模板化输出的工作流
+
+## Key Entities
+- [[The Agency]]：所属项目
+- [[Document Generator]]：对应的 AI Agent 实体
+
+## Connections
+- [[The Agency]] ← contains ← [[Document Generator]]
+- [[Claude Skills]] ← enables ← [[Document Generator]]
+- [[Prompt Engineering]] ← supports ← [[Document Generator]]
+
+## Contradictions
+- 无明显冲突