@jhm1909/ag-kit 0.2.1 → 0.2.2

package/.agent/skills/code-review/SKILL.md

@@ -16,9 +16,9 @@ Guide proper code review practices: technical rigor, evidence-based claims, secu
 
 ## Three Practices
 
-1. **Receiving feedback** — Technical evaluation over performative agreement
-2. **Requesting reviews** — Systematic review process
-3. **Verification gates** — Evidence before any completion claims
+1. **Receiving feedback** ??Technical evaluation over performative agreement
+2. **Requesting reviews** ??Systematic review process
+3. **Verification gates** ??Evidence before any completion claims
 
 ## Core Principle
 
@@ -28,36 +28,31 @@ Guide proper code review practices: technical rigor, evidence-based claims, secu
 
 ```
 SITUATION?
-│
-├─ Received feedback
-│  ├─ Unclear items? → STOP, ask for clarification first
-│  ├─ From human partner? → Understand, then implement
-│  └─ From external reviewer? → Verify technically before implementing
-│
-├─ Security-focused PR review?
-│  └─ Read: differential_review.md (blast radius, risk classification)
-│
-├─ Spec-to-code compliance check?
-│  └─ Read: spec_compliance.md (6-phase audit methodology)
-│
-├─ Completed work
-│  └─ Major feature/task? → Run verification, present evidence
-│
-└─ About to claim status
-   ├─ Have fresh verification? → State claim WITH evidence
-   └─ No fresh verification? → RUN verification command first
+???��? Received feedback
+?? ?��? Unclear items? ??STOP, ask for clarification first
+?? ?��? From human partner? ??Understand, then implement
+?? ?��? From external reviewer? ??Verify technically before implementing
+???��? Security-focused PR review?
+?? ?��? Read: differential-review.md (blast radius, risk classification)
+???��? Spec-to-code compliance check?
+?? ?��? Read: spec-compliance.md (6-phase audit methodology)
+???��? Completed work
+?? ?��? Major feature/task? ??Run verification, present evidence
+???��? About to claim status
+   ?��? Have fresh verification? ??State claim WITH evidence
+   ?��? No fresh verification? ??RUN verification command first
 ```
 
 ## Receiving Feedback Protocol
 
-**Pattern**: READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT
+**Pattern**: READ ??UNDERSTAND ??VERIFY ??EVALUATE ??RESPOND ??IMPLEMENT
 
 **Key Rules**:
-- ❌ No performative agreement: "You're absolutely right!", "Great point!"
-- ❌ No implementation before verification
-- ✅ Restate requirement, ask questions, push back with technical reasoning
-- ✅ If unclear: STOP and ask for clarification on ALL unclear items first
-- ✅ YAGNI check: grep for usage before implementing suggested features
+- ??No performative agreement: "You're absolutely right!", "Great point!"
+- ??No implementation before verification
+- ??Restate requirement, ask questions, push back with technical reasoning
+- ??If unclear: STOP and ask for clarification on ALL unclear items first
+- ??YAGNI check: grep for usage before implementing suggested features
 
 **Full protocol**: [code-review-reception.md](./references/code-review-reception.md)
 
@@ -72,14 +67,14 @@ SITUATION?
 | Bug fixed | Original symptom passes | "Code changed" |
 | Requirements met | Line-by-line checklist | "Tests passing" |
 
-**Red Flags — STOP**:
+**Red Flags ??STOP**:
 - Using "should", "probably", "seems to"
 - Expressing satisfaction before verification
 - Committing without verification
 
 **Full protocol**: [verification-before-completion.md](./references/verification-before-completion.md)
 
-## Security Review — Risk Classification
+## Security Review ??Risk Classification
 
 | Risk Level | Triggers |
 |------------|----------|
@@ -93,7 +88,7 @@ SITUATION?
 - Validation removed without replacement
 - High blast radius (50+ callers) + HIGH risk change
 
-**Full methodology**: [differential_review.md](./references/differential_review.md)
+**Full methodology**: [differential-review.md](./references/differential-review.md)
 
 ## References
 
@@ -102,12 +97,12 @@ SITUATION?
 | `code-review-reception.md` | Receiving feedback protocol |
 | `verification-before-completion.md` | Iron Law verification gates |
 | `requesting-code-review.md` | How to request reviews |
-| `differential_review.md` | Security PR review (Trail of Bits) |
-| `spec_compliance.md` | Spec-to-code audit (Trail of Bits) |
+| `differential-review.md` | Security PR review (Trail of Bits) |
+| `spec-compliance.md` | Spec-to-code audit (Trail of Bits) |
 
 ## Bottom Line
 
-1. Technical rigor over social performance — No performative agreement
-2. Evidence before claims — Verification gates always
-3. Security before speed — Risk-classify every PR change
+1. Technical rigor over social performance ??No performative agreement
+2. Evidence before claims ??Verification gates always
+3. Security before speed ??Risk-classify every PR change
 4. Verify. Question. Then implement. Evidence. Then claim.

package/.agent/skills/designer/SKILL.md

@@ -13,7 +13,7 @@ metadata:
   estimated_tokens: 15000
 ---
 
-# Designer — Design Intelligence
+# Designer ??Design Intelligence
 
 Expert design guidance powered by a **searchable design database** with BM25 ranking.
 
@@ -73,10 +73,10 @@ python3 skills/designer/scripts/ui-search/search.py "<keyword>" --domain <domain
 ### Workflow
 
 ```
-1. ANALYZE requirements → product type, audience, style keywords
-2. SEARCH --design-system → get full recommendation
-3. DEEP-DIVE --domain → supplement specific needs
-4. IMPLEMENT → using verified, data-driven choices
+1. ANALYZE requirements ??product type, audience, style keywords
+2. SEARCH --design-system ??get full recommendation
+3. DEEP-DIVE --domain ??supplement specific needs
+4. IMPLEMENT ??using verified, data-driven choices
 ```
 
 ---
@@ -93,7 +93,7 @@ python3 skills/designer/scripts/ui-search/search.py "<keyword>" --domain <domain
 | 6 | Typography & Color | MEDIUM | Base 16px, line-height 1.5, semantic tokens |
 | 7 | Animation | MEDIUM | 150-300ms, transform/opacity only, reduced-motion |
 | 8 | Forms & Feedback | MEDIUM | Visible labels, error near field, progressive disclosure |
-| 9 | Navigation | HIGH | Bottom nav ≤5, predictable back, deep linking |
+| 9 | Navigation | HIGH | Bottom nav ??, predictable back, deep linking |
 | 10 | Charts & Data | LOW | Legends, tooltips, accessible colors |
 
 ---
@@ -101,14 +101,14 @@ python3 skills/designer/scripts/ui-search/search.py "<keyword>" --domain <domain
 ## Core Principles
 
 ### Intentionality Over Trends
-- **Why this color?** — Brand meaning, accessibility, contrast
-- **Why this font?** — Readability, personality, performance
-- **Why this animation?** — User feedback, spatial understanding
+- **Why this color?** ??Brand meaning, accessibility, contrast
+- **Why this font?** ??Readability, personality, performance
+- **Why this animation?** ??User feedback, spatial understanding
 
 ### Distinctive Over Generic (Anti-AI-Slop)
-- ❌ Default gradients, Inter everywhere, card templates
-- ✅ Committed aesthetic, unique typography, contextual layouts
-- 📖 Load [Frontend Design Aesthetics](./references/frontend_design_aesthetics.md) for Anthropic's anti-AI-slop guide
+- ??Default gradients, Inter everywhere, card templates
+- ??Committed aesthetic, unique typography, contextual layouts
+- ?�� Load [Frontend Design Aesthetics](./references/frontend-design-aesthetics.md) for Anthropic's anti-AI-slop guide
 
 ### Technical Excellence
 - Semantic HTML first
@@ -127,12 +127,12 @@ python3 skills/designer/scripts/ui-search/search.py "<keyword>" --domain <domain
 
 ### Interaction
 - [ ] All tappable elements have press feedback
-- [ ] Touch targets ≥44×44pt
+- [ ] Touch targets ??4×44pt
 - [ ] Micro-interactions 150-300ms
 - [ ] Disabled states visually clear
 
 ### Light/Dark Mode
-- [ ] Primary text contrast ≥4.5:1 in both modes
+- [ ] Primary text contrast ??.5:1 in both modes
 - [ ] Dividers/borders visible in both modes
 - [ ] Both themes tested before delivery
 

package/.agent/skills/frontend-developer/SKILL.md

@@ -109,8 +109,8 @@ User: "Add a 3D model viewer to my React app"
 
 | Reference | Purpose |
 |:----------|:--------|
-| `react_performance_rules.md` | 65 Vercel React/Next.js perf rules (8 categories) |
-| `composition_patterns.md` | React composition patterns (Vercel) |
+| `react-performance-rules.md` | 65 Vercel React/Next.js perf rules (8 categories) |
+| `composition-patterns.md` | React composition patterns (Vercel) |
 
 ## Related Skills
 

package/.agent/skills/mcp-builder/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: mcp-builder
-description: Guide for creating production-grade MCP (Model Context Protocol) servers. Use when building MCP servers to integrate external APIs, databases, or services — whether in TypeScript (MCP SDK) or Python (FastMCP). Covers architecture, tool design, security, evaluation, and best practices.
+description: Guide for creating production-grade MCP (Model Context Protocol) servers. Use when building MCP servers to integrate external APIs, databases, or services ??whether in TypeScript (MCP SDK) or Python (FastMCP). Covers architecture, tool design, security, evaluation, and best practices.
 ---
 
 # MCP Server Development Guide
@@ -11,7 +11,7 @@ description: Guide for creating production-grade MCP (Model Context Protocol) se
 
 Create MCP servers that enable LLMs to interact with external services through well-designed tools. Quality is measured by how well it enables LLMs to accomplish real-world tasks.
 
-## 🚀 High-Level Workflow
+## ?? High-Level Workflow
 
 ### Phase 1: Deep Research and Planning
 
@@ -24,9 +24,9 @@ Create MCP servers that enable LLMs to interact with external services through w
 2. **Study Framework Documentation**
    - **Recommended stack**: TypeScript (best SDK support + AI compatibility)
    - **Transport**: Streamable HTTP for remote, stdio for local
-   - Load: [📋 MCP Best Practices](./references/mcp_best_practices.md)
-   - Load: [⚡ TypeScript Guide](./references/node_mcp_server.md)
-   - Load: [🐍 Python Guide](./references/python_mcp_server.md)
+   - Load: [?�� MCP Best Practices](./references/mcp_best-practices.md)
+   - Load: [??TypeScript Guide](./references/node-mcp-server.md)
+   - Load: [?�� Python Guide](./references/python-mcp-server.md)
 
 3. **Plan Implementation**
    - Review the service's API documentation
@@ -35,8 +35,8 @@ Create MCP servers that enable LLMs to interact with external services through w
 
 ### Phase 2: Implementation
 
-1. **Project Structure** — see language-specific guides
-2. **Core Infrastructure** — API client, error handling, pagination, response formatting
+1. **Project Structure** ??see language-specific guides
+2. **Core Infrastructure** ??API client, error handling, pagination, response formatting
 3. **Tool Implementation**:
    - Input Schema: Zod (TS) or Pydantic (Python) with constraints
    - Output Schema: Define `outputSchema` where possible
@@ -51,24 +51,24 @@ Create MCP servers that enable LLMs to interact with external services through w
 
 ### Phase 4: Create Evaluations
 
-Load [✅ Evaluation Guide](./references/evaluation.md) for complete guidelines.
+Load [??Evaluation Guide](./references/evaluation.md) for complete guidelines.
 
 Create 10 evaluation questions that are:
-- **Independent** — not dependent on other questions
-- **Read-only** — non-destructive operations only
-- **Complex** — requiring multiple tool calls
-- **Realistic** — based on real use cases
-- **Verifiable** — single, clear answer
-- **Stable** — answer won't change over time
+- **Independent** ??not dependent on other questions
+- **Read-only** ??non-destructive operations only
+- **Complex** ??requiring multiple tool calls
+- **Realistic** ??based on real use cases
+- **Verifiable** ??single, clear answer
+- **Stable** ??answer won't change over time
 
 ## Reference Files
 
 | File | When to Load |
 |------|-------------|
-| [mcp_best_practices.md](./references/mcp_best_practices.md) | Always — naming, security, pagination, transport |
-| [node_mcp_server.md](./references/node_mcp_server.md) | TypeScript/Node implementation |
-| [python_mcp_server.md](./references/python_mcp_server.md) | Python/FastMCP implementation |
-| [evaluation.md](./references/evaluation.md) | Phase 4 — creating quality evaluations |
+| [mcp_best-practices.md](./references/mcp_best-practices.md) | Always ??naming, security, pagination, transport |
+| [node-mcp-server.md](./references/node-mcp-server.md) | TypeScript/Node implementation |
+| [python-mcp-server.md](./references/python-mcp-server.md) | Python/FastMCP implementation |
+| [evaluation.md](./references/evaluation.md) | Phase 4 ??creating quality evaluations |
 
 ## Knowledge Graph
 

package/.agent/skills/mcp-builder/references/evaluation.md

@@ -511,7 +511,7 @@ The evaluation script generates a detailed report including:
 - **Per-Task Results**:
   - Prompt and expected response
   - Actual response from the agent
-  - Whether the answer was correct (✅/❌)
+  - Whether the answer was correct (????
   - Duration and tool call details
   - Agent's summary of its approach
   - Agent's feedback on the tools

package/.agent/skills/project-manager/SKILL.md

@@ -30,30 +30,25 @@ Deliver value through efficient systems and clear processes.
 
 ## Core Philosophy
 
-1. **Outcome & Efficiency** — Value (Product) through efficient systems (Process)
-2. **Voice of User & Team** — Represent user in requirements, team in process
-3. **Ruthless Prioritization** — "No" protects focus
-4. **Automated Governance** — Automate rules, don't just follow them
+1. **Outcome & Efficiency** ??Value (Product) through efficient systems (Process)
+2. **Voice of User & Team** ??Represent user in requirements, team in process
+3. **Ruthless Prioritization** ??"No" protects focus
+4. **Automated Governance** ??Automate rules, don't just follow them
 
 ## Decision Tree
 
 ```
 What PM activity is needed?
-│
-├─ Discovery / Research?
-│  └─ Read: discovery_process.md (6-phase workflow)
-│
-├─ PRD / Requirements?
-│  └─ Read: prd_development.md (10-section template)
-│
-├─ Understanding customer needs?
-│  └─ Read: jobs_to_be_done.md (JTBD framework)
-│
-├─ Strategic planning?
-│  └─ Use: strategic-frameworks (Roadmap, OKRs)
-│
-└─ Process / Governance?
-   └─ Use: rules-guide, workflows-guide
+???��? Discovery / Research?
+?? ?��? Read: discovery-process.md (6-phase workflow)
+???��? PRD / Requirements?
+?? ?��? Read: prd-development.md (10-section template)
+???��? Understanding customer needs?
+?? ?��? Read: jobs-to-be-done.md (JTBD framework)
+???��? Strategic planning?
+?? ?��? Use: strategic-frameworks (Roadmap, OKRs)
+???��? Process / Governance?
+   ?��? Use: rules-guide, workflows-guide
 ```
 
 ## Capabilities
@@ -69,9 +64,9 @@ What PM activity is needed?
 
 ## Quick Rules
 
-- **Repeated 3x?** → Make a **Workflow** (`.agent/workflows/`)
-- **Mistake 2x?** → Make a **Rule** (`.agent/rules/`)
-- **Domain-specific?** → Consult **[[business-analysis]]**
+- **Repeated 3x?** ??Make a **Workflow** (`.agent/workflows/`)
+- **Mistake 2x?** ??Make a **Rule** (`.agent/rules/`)
+- **Domain-specific?** ??Consult **[[business-analysis]]**
 
 ## Skill Detection Matrix
 
@@ -95,15 +90,15 @@ What PM activity is needed?
 | `templates/rfc.md` | Request for Comments |
 | `templates/prd-template.md` | Product Requirements |
 | `templates/user-story-template.md` | User stories |
-| `discovery_process.md` | Product discovery 6-phase workflow (Dean Peters) |
-| `prd_development.md` | Structured PRD creation guide (Dean Peters) |
-| `jobs_to_be_done.md` | JTBD framework (Dean Peters) |
+| `discovery-process.md` | Product discovery 6-phase workflow (Dean Peters) |
+| `prd-development.md` | Structured PRD creation guide (Dean Peters) |
+| `jobs-to-be-done.md` | JTBD framework (Dean Peters) |
 
 ## Related Skills
 
-- [[business-analysis]] — Deep requirements analysis
-- [[qa-tester]] — Quality and testing
-- [[lead-architect]] — High-level technical decisions
+- [[business-analysis]] ??Deep requirements analysis
+- [[qa-tester]] ??Quality and testing
+- [[lead-architect]] ??High-level technical decisions
 
 ---
 

package/.agent/skills/qa-tester/SKILL.md

@@ -30,31 +30,27 @@ Comprehensive testing + security auditing for high-quality software delivery.
 
 ## Core Philosophy
 
-1. **Docs First** — Base all testing on `docs/` folder requirements
-2. **No Assumptions** — Missing docs? STOP and CONFIRM with user
-3. **Verify Everything** — Happy path, negative path, boundaries, edges
-4. **Trust No Input** — Every input is a potential attack vector
-5. **Pit of Success** — Secure usage should be the path of least resistance
+1. **Docs First** ??Base all testing on `docs/` folder requirements
+2. **No Assumptions** ??Missing docs? STOP and CONFIRM with user
+3. **Verify Everything** ??Happy path, negative path, boundaries, edges
+4. **Trust No Input** ??Every input is a potential attack vector
+5. **Pit of Success** ??Secure usage should be the path of least resistance
 
 ## Decision Tree
 
 ```
 What testing is needed?
-│
-├─ Functional testing?
-│  └─ Read: test_case_standards.md, unit_testing.md, e2e_testing.md
-│
-├─ Security audit?
-│  ├─ Insecure defaults/hardcoded secrets? → Read: security_audit.md
-│  ├─ API footgun analysis? → Read: sharp_edges.md
-│  ├─ Dependency risk? → Read: supply_chain_audit.md
-│  └─ Static analysis scan? → Read: static_analysis.md
-│
-├─ Property-based testing?
-│  └─ Read: property_based_testing.md
-│
-└─ Performance testing?
-   └─ Read: performance_testing.md
+???��? Functional testing?
+?? ?��? Read: test-case-standards.md, unit-testing.md, e2e-testing.md
+???��? Security audit?
+?? ?��? Insecure defaults/hardcoded secrets? ??Read: security-audit.md
+?? ?��? API footgun analysis? ??Read: sharp-edges.md
+?? ?��? Dependency risk? ??Read: supply-chain-audit.md
+?? ?��? Static analysis scan? ??Read: static-analysis.md
+???��? Property-based testing?
+?? ?��? Read: property-based-testing.md
+???��? Performance testing?
+   ?��? Read: performance-testing.md
 ```
 
 ## Test Types
@@ -75,15 +71,15 @@ What testing is needed?
 
 ### Noun-Verb Extraction
 Scan docs for **Nouns** (User, Order) and **Verbs** (Register, Checkout)
-→ Each Action = At least 1 Test Case
+??Each Action = At least 1 Test Case
 
 ### Keyword Permutations
 Look for "MUST", "CANNOT", "ONLY IF"
-→ Test constraint met AND violated
+??Test constraint met AND violated
 
 ### State Transition Mapping
-Entity states (Pending → Paid → Shipped)
-→ Test valid AND invalid transitions
+Entity states (Pending ??Paid ??Shipped)
+??Test valid AND invalid transitions
 
 ### Property Detection (PBT)
 | Pattern | Property | Priority |
@@ -97,7 +93,7 @@ Entity states (Pending → Paid → Shipped)
 
 When auditing code security, check:
 
-- [ ] **Insecure defaults**: `env.get(X) or 'fallback'` — fail-open patterns
+- [ ] **Insecure defaults**: `env.get(X) or 'fallback'` ??fail-open patterns
 - [ ] **Hardcoded secrets**: `password = "..."`, `API_KEY = "..."`
 - [ ] **Weak crypto**: MD5, SHA1, DES, RC4, ECB in security contexts
 - [ ] **Permissive CORS**: `Access-Control-Allow-Origin: *`
@@ -107,35 +103,35 @@ When auditing code security, check:
 
 ## Coverage Requirements
 
-- ✅ **Happy Path** — Golden flow
-- ✅ **Negative Path** — Error handling
-- ✅ **Boundary** — Off-by-one (0, 1, Max)
-- ✅ **Edge Cases** — Timeouts, failures, concurrency
-- ✅ **Integration** — Cross-module flows
-- ✅ **Security** — Injection, auth bypass, data leaks
+- ??**Happy Path** ??Golden flow
+- ??**Negative Path** ??Error handling
+- ??**Boundary** ??Off-by-one (0, 1, Max)
+- ??**Edge Cases** ??Timeouts, failures, concurrency
+- ??**Integration** ??Cross-module flows
+- ??**Security** ??Injection, auth bypass, data leaks
 
 ## References
 
 | Reference | Purpose |
 |:----------|:--------|
-| `test_case_standards.md` | "No Ambiguity" philosophy |
-| `unit_testing.md` | "Test Behavior, Not Implementation" |
-| `integration_testing.md` | "Verify the Handshake" |
-| `e2e_testing.md` | "Simulate the Real User" |
-| `security_testing.md` | "Trust No Input" |
-| `performance_testing.md` | "Performance is a Feature" |
-| `security_audit.md` | Insecure defaults detection (Trail of Bits) |
-| `sharp_edges.md` | API footgun analysis (Trail of Bits) |
-| `property_based_testing.md` | PBT methodology (Trail of Bits) |
-| `supply_chain_audit.md` | Dependency risk scoring (Trail of Bits) |
-| `static_analysis.md` | Semgrep scanning workflow (Trail of Bits) |
+| `test-case-standards.md` | "No Ambiguity" philosophy |
+| `unit-testing.md` | "Test Behavior, Not Implementation" |
+| `integration-testing.md` | "Verify the Handshake" |
+| `e2e-testing.md` | "Simulate the Real User" |
+| `security-testing.md` | "Trust No Input" |
+| `performance-testing.md` | "Performance is a Feature" |
+| `security-audit.md` | Insecure defaults detection (Trail of Bits) |
+| `sharp-edges.md` | API footgun analysis (Trail of Bits) |
+| `property-based-testing.md` | PBT methodology (Trail of Bits) |
+| `supply-chain-audit.md` | Dependency risk scoring (Trail of Bits) |
+| `static-analysis.md` | Semgrep scanning workflow (Trail of Bits) |
 
 ## Related Skills
 
-- [[frontend-developer]] — Component testing
-- [[backend-developer]] — API testing
-- [[code-review]] — Security-focused PR review
-- [[project-manager]] — Quality metrics, UAT
+- [[frontend-developer]] ??Component testing
+- [[backend-developer]] ??API testing
+- [[code-review]] ??Security-focused PR review
+- [[project-manager]] ??Quality metrics, UAT
 
 ---
 

package/cli/index.js

@@ -14,7 +14,7 @@ const fs = require('fs');
 const path = require('path');
 
 // ─── Constants ───────────────────────────────────────────────────────
-const VERSION = '0.2.1';
+const VERSION = '0.2.2';
 const KIT_NAME = '@jhm1909/ag-kit';
 const AGENT_DIR = '.agent';
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jhm1909/ag-kit",
-  "version": "0.2.1",
+  "version": "0.2.2",
   "description": "AI Agent Kit — 21 skills, 15 workflows, manifest-driven routing for AI-powered coding",
   "main": "cli/index.js",
   "bin": {