@jhm1909/ag-kit 0.1.0

package/.agent/skills/blockchain-engineer/references/deployment.md

@@ -0,0 +1,28 @@
+# Tech: Smart Contract Deployment
+
+## Strategies
+
+- **Immutable**: Simple deployment. Code cannot be changed. High trust, low flexibility.
+- **Upgradeable Proxies**:
+  - **Transparent Upgradeable Proxy**: Admin logic separated. High gas overhead.
+  - **UUPS (Universal Upgradeable Proxy Standard)**: Upgrade logic in implementation. Cheaper gas.
+  - **Diamond (EIP-2535)**: Modular system, unlimited size, complex management.
+
+## Automation & Tooling
+
+- **Hardhat Ignition**: Declarative deployment modules. Handles dependency management and recovery.
+- **Foundry Script**: Solidity-based scripting (`forge script`). Fast and integrated with Forge tests.
+- **Deterministic Deployment**:
+  - Use `CREATE2` to deploy to the same address across multiple chains.
+  - Tool: `Nick's Method` factory / `Arachnid/deterministic-deployment-proxy`.
+
+## Verification
+
+- **Etherscan/Block Explorers**: ALWAYs verify source code.
+- **Sourcify**: Decentralized verification based on metadata hash.
+
+## Operational Safety
+
+- **Multisig (Gnosis Safe)**: Never deploy or manage admin keys with a single EOA (Externally Owned Account).
+- **Timelocks**: Enforce a delay (e.g., 48h) between proposing and executing sensitive admin actions.
+- **Access Control Rotation**: Plan for key rotation procedures.

package/.agent/skills/blockchain-engineer/references/evm.md

@@ -0,0 +1,14 @@
+# Tech: EVM (Ethereum Virtual Machine)
+
+## Stack
+
+- **Solidty**: v0.8.20+
+- **Framework**: Hardhat or Foundry.
+- **Client**: Viem + Wagmi.
+
+## Security Checklist
+
+- [ ] Reentrancy Guards present?
+- [ ] Access Control (Ownable/AccessControl)?
+- [ ] Checked for math overflows (if <0.8.0)?
+- [ ] Validated all external calls?

package/.agent/skills/blockchain-engineer/references/mechanisms.md

@@ -0,0 +1,32 @@
+# Tech: Blockchain Mechanisms & Internals
+
+## Consensus
+
+- **PoS (Proof of Stake)**: Validators stake tokens to propose/attest blocks. (Ethereum, Solana).
+- **PoW (Proof of Work)**: Miners solve cryptographic puzzles. (Bitcoin).
+- **Finality**:
+  - **Probabilistic**: Bitcoin (wait ~6 blocks).
+  - **Deterministic**: Ethereum (after finalized epoch), Tendermint (instant).
+
+## State Management
+
+- **Account Model (Ethereum/Solana)**: Global state tracks account balances and nonce.
+- **UTXO (Bitcoin/Cardano)**: Unspent Transaction Outputs. State is the set of all unspent outputs.
+- **Data Structures**:
+  - **Merkle Patricia Trie (Ethereum)**: Storage, State, Transactions, Receipts.
+  - **Verkle Trees**: Future upgrade for stateless clients.
+
+## Transaction Lifecycle
+
+1.  **Creation**: User signs tx with private key.
+2.  **Propagation**: Gossip protocol sends tx to Mempool.
+3.  **Ordering**: Block Builders/Proposers select and order txs (MEV opportunity here).
+4.  **Execution**: EVM executes logic, updates state trie.
+5.  **Finalization**: Block is added to chain and finalized by consensus.
+
+## EVM Internals
+
+- **Stack**: 1024 depth, 256-bit words. Most gas efficient.
+- **Memory**: Linear, byte-addressable. Expanded in 32-byte chunks.
+- **Storage**: Key-value store (256-bit -> 256-bit). Most expensive. SLOAD/SSTORE.
+- **Logs**: Bloom filters used for event indexing. Cheaper than storage but not accessible by contracts.

package/.agent/skills/blockchain-engineer/references/solidity.md

@@ -0,0 +1,32 @@
+# Tech: Solidity Development
+
+## Best Practices
+
+- **Layout**: Follow [Solidty Style Guide](https://docs.soliditylang.org/en/latest/style-guide.html).
+  - Order: Pragma -> Import -> Interfaces -> Libraries -> Contracts.
+  - Inside Contract: Type declarations -> State vars -> Events -> Modifiers -> Functions.
+- **Naming**: `camelCase` for variables/functions, `CapWords` for contracts/structs/events, `UPPER_CASE` for constants.
+- **Error Handling**: Use custom errors (`error InsufficientFunds()`) instead of strings for gas efficiency.
+
+## Advanced Concepts
+
+- **Storage Layout**: Understand slot packing to minimize storage costs.
+  - Pack `uint128`, `address`, `bool` into single 256-bit slots where possible.
+- **Delegatecall**: Execution in the context of the caller (crucial for proxies).
+- **Assembly (Yul)**: Use `assembly { ... }` for low-level memory manipulation and gas optimization.
+- **EIP Standards**:
+  - **ERC-20/721/1155**: Token standards.
+  - **ERC-4626**: Tokenized Vaults.
+  - **ERC-2535**: Diamond Standard.
+
+## Security Patterns
+
+- **Checks-Effects-Interactions**: Update state _before_ making external calls to prevent reentrancy.
+- **Pull over Push**: Let users withdraw funds rather than pushing them to arrays of addresses (avoids DoS).
+- **Access Control**: Use `OwnableTwoStep` or `AccessControl` (RBAC).
+
+## Gas Optimization
+
+- **Calldata**: Use `calldata` instead of `memory` for read-only function arguments.
+- **Unchecked Math**: Use `unchecked { ... }` when overflow/underflow is impossible (Solidity 0.8+ default checks cost gas).
+- **Constants/Immutable**: Use `constant` for literal values and `immutable` for constructor-set values.

package/.agent/skills/business-analysis/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: business-analysis
+description: >
+  Requirements analysis, technical specs, agile documentation. Use for bridging business goals to technical implementation.
+license: MIT
+compatibility: Claude Code, Cursor, Gemini CLI, GitHub Copilot
+metadata:
+  author: jhm1909
+  version: "2.0.0"
+  domain: analysis
+  estimated_tokens: 8000
+---
+
+# Business Analysis
+
+Bridge the gap between abstract business goals and concrete technical implementation.
+
+## Knowledge Graph
+
+- **extends**: []
+- **requires**: []
+- **suggests**: [[project-manager]], [[lead-architect]], [[designer]], [[frontend-developer]], [[backend-developer]]
+- **conflicts**: []
+- **enhances**: [[qa-tester]] (acceptance criteria), [[lead-architect]] (technical specs)
+- **moc**: [[product-development-moc]]
+
+## Core Philosophy
+
+1. **Gap Analysis First** — Analyze constraint conflicts before solutions
+2. **Sequential Thinking** — Break down step-by-step, don't guess
+3. **Visuals First** — Diagrams are truth (text is ambiguous)
+4. **Obsidian Native** — Graph-ready docs with `[[Wiki-links]]`
+5. **Agile Orthodoxy** — User Stories (INVEST), Acceptance Criteria (Gherkin)
+6. **Multiple Perspectives** — Strategic, Product, Technical
+
+## Perspectives
+
+| Perspective | Focus | Output |
+|:------------|:------|:-------|
+| 🎩 **Strategic** | ROI, KPIs, Roadmap | BRD |
+| 🎩 **Product** | UX, Features, Flows | PRD, User Stories |
+| 🎩 **Technical** | Schema, APIs, States | Technical Spec |
+
+## Workflow
+
+1. **Market & Domain Research** — `search_web` for validation
+2. **Requirement Gathering** — Specific constraints, not "what do you want?"
+3. **Logic & Flow Analysis** — Happy path, negative path, edge cases
+4. **Diagramming** — Mermaid diagrams (state, sequence, class)
+5. **Documentation** — PRD, Specs, User Stories
+6. **Link** — Update MOCs with new documents
+
+## Domain Knowledge
+
+| Domain | Path |
+|:-------|:-----|
+| SaaS | `references/domains/saas.md` |
+| FinTech | `references/domains/fintech.md` |
+| E-Commerce | `references/domains/ecommerce.md` |
+| HealthTech | `references/domains/healthtech.md` |
+| EdTech | `references/domains/education.md` |
+| Blockchain | `references/domains/blockchain-dapp.md` |
+| AI/ML | `references/domains/ai-agent.md` |
+| Marketplace | `references/domains/marketplace.md` |
+
+## Templates
+
+| Template | Purpose |
+|:---------|:--------|
+| `prd-functional.md` | Detailed PRD |
+| `user-story-detailed.md` | Gherkin syntax, dev notes |
+| `brd.md` | Business Requirements |
+| `use-case.md` | Actor flows, exceptions |
+| `change-request.md` | Impact analysis |
+
+## Related Skills
+
+- [[project-manager]] — Planning and coordination
+- [[lead-architect]] — Technical design
+- [[designer]] — UX implementation
+- [[qa-tester]] — Acceptance criteria validation
+
+---
+
+*Requirements to implementation | Domain expertise hub*

package/.agent/skills/business-analysis/references/best-practices/diagrams.md

@@ -0,0 +1,141 @@
+# Mermaid Diagramming Best Practices
+
+## "Visuals First"
+
+Diagrams are not decorations. They are **specifications**.
+
+## 1. Syntax Verification
+
+**ALWAYS** check `verify_mermaid.py` or use `context7` to confirm syntax if unsure. Mermaid syntax evolves.
+
+## 2. Diagram Selection Guide
+
+| Requirement Type       | Diagram Type  | Mermaid Key       | Why?                               |
+| :--------------------- | :------------ | :---------------- | :--------------------------------- |
+| **Logic/Workflow**     | Flowchart     | `flowchart TD`    | Decision trees, yes/no paths.      |
+| **System Interaction** | Sequence      | `sequenceDiagram` | Who calls whom? APIreq/res cycles. |
+| **Data Structure**     | Class Diagram | `classDiagram`    | OOP relationships.                 |
+| **Database Schema**    | ER Diagram    | `erDiagram`       | SQL tables and cardinality.        |
+| **Lifecycle**          | State Diagram | `stateDiagram-v2` | Status transitions.                |
+| **User Journey**       | User Journey  | `journey`         | User sentiment/steps overlay.      |
+| **Architecture**       | C4 Context    | `C4Context`       | High-level system overview.        |
+| **Project Plan**       | Gantt         | `gantt`           | Timeline and milestones.           |
+
+## 3. Style Guidelines
+
+- **Left-to-Right** (`LR`) for long processes.
+- **Top-Down** (`TD`) for hierarchies.
+- **Subgraphs**: Use to group related components (e.g., `subgraph Database`).
+
+## 4. Examples Library
+
+### Sequence Diagram (API Call)
+
+_Use for: API endpoints, service-to-service communication._
+
+```mermaid
+sequenceDiagram
+    autonumber
+    participant Client
+    participant Server
+    participant DB
+
+    Client->>Server: POST /login
+    Server->>DB: SELECT * FROM users
+    DB-->>Server: User Data
+    alt Valid Password
+        Server-->>Client: 200 OK (Token)
+    else Invalid
+        Server-->>Client: 401 Unauthorized
+    end
+```
+
+### State Diagram (Lifecycle)
+
+_Use for: Order status, Auth state, Ticket workflows._
+
+```mermaid
+stateDiagram-v2
+    [*] --> Pending
+    Pending --> Paid: Payment Success
+    Pending --> Failed: Payment Fail
+    Paid --> Shipped
+    Shipped --> [*]
+```
+
+### Class Diagram (OOP/Data)
+
+_Use for: Domain entities, Code architecture._
+
+```mermaid
+classDiagram
+    class User {
+        +String username
+        +login()
+    }
+    class Order {
+        +int id
+        +Date created
+    }
+    User "1" *-- "many" Order : places
+```
+
+### ER Diagram (Database)
+
+_Use for: SQL Schema, Relationships._
+
+```mermaid
+erDiagram
+    USER ||--o{ ORDER : places
+    USER {
+        string username
+        string email
+    }
+    ORDER ||--|{ LINE-ITEM : contains
+    ORDER {
+        int id
+        float total
+    }
+```
+
+### User Journey Map
+
+_Use for: UX Flows, Customer experience._
+
+```mermaid
+journey
+    title Buying a Coffee
+    section Application
+      Log In: 5: Me, Cat
+      Find Product: 3: Me
+    section Checkout
+      Pay: 5: Me
+      Receive Receipt: 5: Me
+```
+
+### C4 Context (Architecture)
+
+_Use for: High-level System Landscape. Requires `C4Context` library support._
+
+```mermaid
+C4Context
+    title System Context for Banking App
+    Person(customer, "Customer", "A customer of the bank.")
+    System(banking_system, "Internet Banking System", "Allows customers to view information.")
+    SystemExt(mainframe, "Mainframe Banking System", "Stores all customer information.")
+    Rel(customer, banking_system, "Uses")
+    Rel(banking_system, mainframe, "Uses")
+```
+
+### Flowchart (Logic Tree)
+
+_Use for: Business rules, Algorithms._
+
+```mermaid
+flowchart TD
+    A[Start] --> B{Is it valid?}
+    B -- Yes --> C[Process]
+    B -- No --> D[Error]
+    C --> E[End]
+    D --> E
+```

package/.agent/skills/business-analysis/references/domains/ai-agent.md

@@ -0,0 +1,94 @@
+# AI Agent Domain Reference
+
+## Core Concepts
+
+### Agent Types
+
+- **Conversational**: Chat-based interaction (ChatGPT, Claude)
+- **Autonomous**: Execute tasks independently
+- **Multi-agent**: Multiple agents collaborating
+- **Tool-using**: Agents with access to external tools
+
+### LLM Foundations
+
+- **Models**: GPT-4, Claude, Gemini, Llama, Mistral
+- **Context window**: Input token limits
+- **Temperature**: Creativity vs. determinism
+- **System prompts**: Agent behavior definition
+
+### Agent Architecture
+
+- **Memory**: Short-term (conversation), Long-term (knowledge base)
+- **Planning**: Task decomposition, goal setting
+- **Tools**: Code execution, web search, API calls
+- **Reflection**: Self-evaluation, error correction
+
+## Building Blocks
+
+### Prompt Engineering
+
+- System prompts (role, behavior, constraints)
+- Few-shot examples
+- Chain-of-thought reasoning
+- Output formatting (JSON, structured)
+
+### Tool Integration
+
+- Function calling / Tool use
+- API integrations
+- Code interpreters
+- Web browsing, search
+
+### Memory Systems
+
+- Conversation history
+- Vector databases (embeddings)
+- Knowledge graphs
+- Long-term memory persistence
+
+### Orchestration
+
+- Agent frameworks: LangChain, LlamaIndex, AutoGen
+- Workflow engines
+- Multi-agent coordination
+- Human-in-the-loop
+
+## Common Patterns
+
+### RAG (Retrieval Augmented Generation)
+
+- Document ingestion
+- Chunking strategies
+- Embedding models
+- Vector similarity search
+- Context injection
+
+### Agents with Tools
+
+- Tool definition and registration
+- Tool selection logic
+- Error handling and retries
+- Result parsing
+
+### Multi-Agent Systems
+
+- Agent roles and specialization
+- Communication protocols
+- Supervisor/router patterns
+- Parallel vs. sequential execution
+
+## Safety & Guardrails
+
+- Input validation
+- Output filtering
+- Rate limiting
+- Prompt injection prevention
+- Content moderation
+
+## Key Metrics
+
+- Response quality (human eval, LLM-as-judge)
+- Latency (time to first token, total time)
+- Token usage, cost
+- Task completion rate
+- User satisfaction

package/.agent/skills/business-analysis/references/domains/blockchain-dapp.md

@@ -0,0 +1,86 @@
+# Blockchain & dApp Domain Reference
+
+## Core Concepts
+
+### Blockchain Fundamentals
+
+- **Consensus mechanisms**: PoW, PoS, DPoS, PBFT
+- **Networks**: Mainnet, Testnet, Devnet
+- **Chains**: Ethereum, Solana, Polygon, BNB Chain, Arbitrum, Base
+
+### Smart Contracts
+
+- Self-executing code on blockchain
+- Immutable after deployment (upgradeable patterns available)
+- Gas fees for execution
+- Common languages: Solidity (EVM), Rust (Solana), Move
+
+### Wallets
+
+- **Types**: Hot (MetaMask, Phantom), Cold (Ledger, Trezor)
+- **Connection**: WalletConnect, browser extensions
+- **Multi-sig**: Multiple signatures required for transactions
+
+## dApp Architecture
+
+### Frontend
+
+- React/Next.js with wallet adapters
+- Web3 libraries: ethers.js, web3.js, @solana/web3.js
+- State management for wallet connection
+
+### Backend (if needed)
+
+- Indexers for blockchain data
+- Caching layer for performance
+- Off-chain storage (IPFS, Arweave)
+
+### Smart Contract Layer
+
+- Core business logic on-chain
+- Upgradeable proxy patterns
+- Access control (roles, permissions)
+
+## Common dApp Types
+
+### DeFi (Decentralized Finance)
+
+- DEX (decentralized exchanges): AMM, order book
+- Lending/borrowing protocols
+- Yield farming, staking
+- Liquidity pools
+
+### NFT (Non-Fungible Tokens)
+
+- Minting, burning
+- Marketplaces, auctions
+- Royalties, creator fees
+- Metadata (on-chain vs. off-chain)
+
+### GameFi / Play-to-Earn
+
+- In-game assets as NFTs
+- Token rewards
+- Staking mechanics
+
+### DAO (Decentralized Autonomous Organizations)
+
+- Governance tokens
+- Proposal and voting systems
+- Treasury management
+
+## Security Considerations
+
+- Smart contract audits
+- Reentrancy attacks
+- Flash loan attacks
+- Oracle manipulation
+- Private key management
+
+## Key Metrics
+
+- TVL (Total Value Locked)
+- Daily Active Users (DAU)
+- Transaction volume
+- Gas efficiency
+- Token price, market cap

package/.agent/skills/business-analysis/references/domains/ecommerce.md

@@ -0,0 +1,77 @@
+# E-commerce Domain Reference
+
+## Core Modules
+
+### Product Management
+
+- Product catalog (name, SKU, description, images, variants)
+- Categories and collections
+- Inventory management (stock, warehouses, reorder points)
+- Pricing (base price, sale price, tiered pricing, bulk discounts)
+
+### Order Management
+
+- Shopping cart and checkout flow
+- Order lifecycle: pending → confirmed → processing → shipped → delivered
+- Order modifications, cancellations, returns
+- Multi-currency, multi-language support
+
+### Customer Management
+
+- User registration, authentication (email, social, phone)
+- Customer profiles, addresses, preferences
+- Loyalty programs, points, rewards
+- Customer segmentation
+
+### Payment Processing
+
+- Payment gateways (Stripe, PayPal, local gateways)
+- Payment methods (card, bank transfer, COD, e-wallets)
+- Refunds, partial refunds
+- Recurring payments, subscriptions
+
+### Shipping & Fulfillment
+
+- Shipping carriers integration
+- Shipping zones, rates calculation
+- Order tracking
+- Returns and exchanges
+
+## Common Features
+
+### Search & Discovery
+
+- Full-text search, filters, facets
+- Recommendations engine
+- Recently viewed, wishlists
+- Compare products
+
+### Marketing
+
+- Promotions, coupons, discount codes
+- Flash sales, limited-time offers
+- Email marketing integration
+- Abandoned cart recovery
+
+### Analytics
+
+- Sales reports, revenue tracking
+- Customer behavior analytics
+- Conversion funnel analysis
+- Inventory reports
+
+## User Roles
+
+- **Guest**: Browse, add to cart
+- **Customer**: Full checkout, order history, profile
+- **Staff**: Order management, inventory
+- **Admin**: Full access, settings, reports
+
+## Key Metrics
+
+- GMV (Gross Merchandise Value)
+- AOV (Average Order Value)
+- Conversion rate
+- Cart abandonment rate
+- Customer lifetime value (CLV)
+- Return rate

package/.agent/skills/business-analysis/references/domains/education.md

@@ -0,0 +1,42 @@
+# Domain Knowledge: Education (EdTech) / LMS
+
+## Core Entities (Ontology)
+
+- **Institution/School**: Top-level tenant.
+- **Curriculum**:
+  - **Program**: E.g., "Computer Science BS".
+  - **Course**: E.g., "CS101 - Intro to Programming".
+  - **Section/Class**: Specific instance (e.g., "Fall 2026, Section A").
+- **People**:
+  - **Student**: Consumer of content. Constraints: COPPA/FERPA compliance.
+  - **Instructor**: Creator/Grader.
+  - **Admin**: Scheduler/Manager.
+- **Assessment**:
+  - **Assignment**: Submission based (File, Text).
+  - **Quiz**: Automated grading (MCQ, True/False).
+  - **Rubric**: Criteria-based grading matrix.
+- **Gradebook**:
+  - **Weighted Categories**: (Homework 20%, Exam 80%).
+  - **Letter Grading**: (A > 90%).
+
+## Common Workflows
+
+### 1. Enrollment Flow
+
+- Student adds course -> Check prerequisites -> Check seat capacity -> Payment (if applicable) -> Active Enrollment.
+- _Edge Cases_: Waitlists, Holds (financial/academic), Time conflicts.
+
+### 2. Assignment Submission
+
+- Student uploads file -> Antivirus scan -> Timestamp log -> Status: "Submitted".
+- _Edge Cases_: Late submission (grace period?), File size limit, Unsupported format.
+
+### 3. Grading Flow
+
+- Instructor views submission -> Attaches Rubric scores -> Calculates total -> Publishes grade -> Student Notified.
+
+## Key Regulations
+
+- **FERPA (USA)**: Student records privacy.
+- **LTI (Learning Tools Interoperability)**: Standard for plugging external tools (e.g., Zoom, Turnitin) into LMS.
+- **SCORM/xAPI**: Content standards for courseware.

package/.agent/skills/business-analysis/references/domains/fintech.md

@@ -0,0 +1,44 @@
+# Domain: FinTech (Financial Technology)
+
+## 1. Core Mindset
+
+- **Precision**: Integers for money (cents), never floats.
+- **Auditability**: Every action needs a trace. Immutable logs.
+- **Security**: PCI-DSS compliance, Data encryption at rest/transit.
+
+## 2. Key Terminology (Glossary)
+
+- **KYC (Know Your Customer)**: Mandatory identity verification.
+- **AML (Anti-Money Laundering)**: Monitoring for suspicious transaction patterns.
+- **Ledger**: The source of truth. Double-entry bookkeeping (Debits = Credits).
+- **PSP (Payment Service Provider)**: Stripe, PayPal, Adyen.
+- **PCI-DSS**: Security standards for handling credit card info.
+
+## 3. Common Entities (Data Models)
+
+- **Wallet**: Holds balance. `user_id`, `currency`, `balance_cents`.
+- **Transaction**: A movement of funds. `id`, `amount`, `source_wallet`, `dest_wallet`, `type` (deposit, withdrawal, transfer).
+- **KYCprofile**: Verification status. `document_url`, `status` (pending, approved, rejected).
+
+## 4. Key Workflows
+
+### A. Deposit Funds (Mock)
+
+1.  User initiates deposit $50.
+2.  System creates `Transaction` (status: pending).
+3.  User redirected to PSP.
+4.  Webhook received -> Update `Transaction` (success).
+5.  Credit User `Wallet` (+5000 cents).
+
+### B. Peer-to-Peer Transfer
+
+1.  **Check Balance**: Ensure Sender has > Amount.
+2.  **Lock Funds**: Prevent double-spend (Database transaction).
+3.  **Debit Sender**: `Wallet A` -= Amount.
+4.  **Credit Receiver**: `Wallet B` += Amount.
+5.  **Audit Log**: Record immutable entry.
+
+## 5. Regulatory Compliance Checklist
+
+- [ ] **GDPR/CCPA**: Right to be forgotten (BUT financial records must be kept for X years).
+- [ ] **SCA (Strong Customer Authentication)**: 2FA for payments (PSD2 in Europe).