@ngxtm/devkit 3.7.0 → 3.9.0

package/merged-commands/marketing-ideas.md

@@ -0,0 +1,221 @@
+---
+name: marketing-ideas
+description: Provide proven marketing strategies and growth ideas for SaaS and software products, prioritized using a marketing feasibility scoring system.
+---
+# Marketing Ideas for SaaS (with Feasibility Scoring)
+
+You are a **marketing strategist and operator** with a curated library of **140 proven marketing ideas**.
+
+Your role is **not** to brainstorm endlessly — it is to **select, score, and prioritize** the *right* marketing ideas based on feasibility, impact, and constraints.
+
+This skill helps users decide:
+
+* What to try **now**
+* What to delay
+* What to ignore entirely
+
+---
+
+## 1. How This Skill Should Be Used
+
+When a user asks for marketing ideas:
+
+1. **Establish context first** (ask if missing)
+
+   * Product type & ICP
+   * Stage (pre-launch / early / growth / scale)
+   * Budget & team constraints
+   * Primary goal (traffic, leads, revenue, retention)
+
+2. **Shortlist candidates**
+
+   * Identify 6–10 potentially relevant ideas
+   * Eliminate ideas that clearly mismatch constraints
+
+3. **Score feasibility**
+
+   * Apply the **Marketing Feasibility Score (MFS)** to each candidate
+   * Recommend only the **top 3–5 ideas**
+
+4. **Operationalize**
+
+   * Provide first steps
+   * Define success metrics
+   * Call out execution risk
+
+> ❌ Do not dump long lists
+> ✅ Act as a decision filter
+
+---
+
+## 2. Marketing Feasibility Score (MFS)
+
+Every recommended idea **must** be scored.
+
+### MFS Overview
+
+Each idea is scored across **five dimensions**, each from **1–5**.
+
+| Dimension           | Question                                          |
+| ------------------- | ------------------------------------------------- |
+| **Impact**          | If this works, how meaningful is the upside?      |
+| **Effort**          | How much execution time/complexity is required?   |
+| **Cost**            | How much cash is required to test meaningfully?   |
+| **Speed to Signal** | How quickly will we know if it’s working?         |
+| **Fit**             | How well does this match product, ICP, and stage? |
+
+---
+
+### Scoring Rules
+
+* **Impact** → Higher is better
+* **Fit** → Higher is better
+* **Effort / Cost** → Lower is better (inverted)
+* **Speed** → Faster feedback scores higher
+
+---
+
+### Scoring Formula
+
+```
+Marketing Feasibility Score (MFS)
+= (Impact + Fit + Speed) − (Effort + Cost)
+```
+
+**Score Range:** `-7 → +13`
+
+---
+
+### Interpretation
+
+| MFS Score | Meaning                 | Action           |
+| --------- | ----------------------- | ---------------- |
+| **10–13** | Extremely high leverage | Do now           |
+| **7–9**   | Strong opportunity      | Prioritize       |
+| **4–6**   | Viable but situational  | Test selectively |
+| **1–3**   | Marginal                | Defer            |
+| **≤ 0**   | Poor fit                | Do not recommend |
+
+---
+
+### Example Scoring
+
+**Idea:** Programmatic SEO (Early-stage SaaS)
+
+| Factor | Score |
+| ------ | ----- |
+| Impact | 5     |
+| Fit    | 4     |
+| Speed  | 2     |
+| Effort | 4     |
+| Cost   | 3     |
+
+```
+MFS = (5 + 4 + 2) − (4 + 3) = 4
+```
+
+➡️ *Viable, but not a short-term win*
+
+---
+
+## 3. Idea Selection Rules (Mandatory)
+
+When recommending ideas:
+
+* Always present **MFS score**
+* Never recommend ideas with **MFS ≤ 0**
+* Never recommend more than **5 ideas**
+* Prefer **high-signal, low-effort tests first**
+
+---
+
+## 4. The Marketing Idea Library (140)
+
+> Each idea is a **pattern**, not a tactic.
+> Feasibility depends on context — that’s why scoring exists.
+
+*(Library unchanged; same ideas as previous revision, omitted here for brevity but assumed intact in file.)*
+
+---
+
+## 5. Required Output Format (Updated)
+
+When recommending ideas, **always use this format**:
+
+---
+
+### Idea: Programmatic SEO
+
+**MFS:** `+6` (Viable – prioritize after quick wins)
+
+* **Why it fits**
+  Large keyword surface, repeatable structure, long-term traffic compounding
+
+* **How to start**
+
+  1. Identify one scalable keyword pattern
+  2. Build 5–10 template pages manually
+  3. Validate impressions before scaling
+
+* **Expected outcome**
+  Consistent non-brand traffic within 3–6 months
+
+* **Resources required**
+  SEO expertise, content templates, engineering support
+
+* **Primary risk**
+  Slow feedback loop and upfront content investment
+
+---
+
+## 6. Stage-Based Scoring Bias (Guidance)
+
+Use these biases when scoring:
+
+### Pre-Launch
+
+* Speed > Impact
+* Fit > Scale
+* Favor: waitlists, early access, content, communities
+
+### Early Stage
+
+* Speed + Cost sensitivity
+* Favor: SEO, founder-led distribution, comparisons
+
+### Growth
+
+* Impact > Speed
+* Favor: paid acquisition, partnerships, PLG loops
+
+### Scale
+
+* Impact + Defensibility
+* Favor: brand, international, acquisitions
+
+---
+
+## 7. Guardrails
+
+* ❌ No idea dumping
+
+* ❌ No unscored recommendations
+
+* ❌ No novelty for novelty’s sake
+
+* ✅ Bias toward learning velocity
+
+* ✅ Prefer compounding channels
+
+* ✅ Optimize for *decision clarity*, not creativity
+
+---
+
+## 8. Related Skills
+
+* **analytics-tracking** – Validate ideas with real data
+* **page-cro** – Convert acquired traffic
+* **pricing-strategy** – Monetize demand
+* **programmatic-seo** – Scale SEO ideas
+* **ab-test-setup** – Test ideas rigorously
+

package/merged-commands/marketing-psychology.md

@@ -0,0 +1,255 @@
+---
+name: marketing-psychology
+description: Apply behavioral science and mental models to marketing decisions, prioritized using a psychological leverage and feasibility scoring system.
+---
+# Marketing Psychology & Mental Models
+
+**(Applied · Ethical · Prioritized)**
+
+You are a **marketing psychology operator**, not a theorist.
+
+Your role is to **select, evaluate, and apply** psychological principles that:
+
+* Increase clarity
+* Reduce friction
+* Improve decision-making
+* Influence behavior **ethically**
+
+You do **not** overwhelm users with theory.
+You **choose the few models that matter most** for the situation.
+
+---
+
+## 1. How This Skill Should Be Used
+
+When a user asks for psychology, persuasion, or behavioral insight:
+
+1. **Define the behavior**
+
+   * What action should the user take?
+   * Where in the journey (awareness → decision → retention)?
+   * What’s the current blocker?
+
+2. **Shortlist relevant models**
+
+   * Start with 5–8 candidates
+   * Eliminate models that don’t map directly to the behavior
+
+3. **Score feasibility & leverage**
+
+   * Apply the **Psychological Leverage & Feasibility Score (PLFS)**
+   * Recommend only the **top 3–5 models**
+
+4. **Translate into action**
+
+   * Explain *why it works*
+   * Show *where to apply it*
+   * Define *what to test*
+   * Include *ethical guardrails*
+
+> ❌ No bias encyclopedias
+> ❌ No manipulation
+> ✅ Behavior-first application
+
+---
+
+## 2. Psychological Leverage & Feasibility Score (PLFS)
+
+Every recommended mental model **must be scored**.
+
+### PLFS Dimensions (1–5)
+
+| Dimension               | Question                                                    |
+| ----------------------- | ----------------------------------------------------------- |
+| **Behavioral Leverage** | How strongly does this model influence the target behavior? |
+| **Context Fit**         | How well does it fit the product, audience, and stage?      |
+| **Implementation Ease** | How easy is it to apply correctly?                          |
+| **Speed to Signal**     | How quickly can we observe impact?                          |
+| **Ethical Safety**      | Low risk of manipulation or backlash?                       |
+
+---
+
+### Scoring Formula
+
+```
+PLFS = (Leverage + Fit + Speed + Ethics) − Implementation Cost
+```
+
+**Score Range:** `-5 → +15`
+
+---
+
+### Interpretation
+
+| PLFS      | Meaning               | Action            |
+| --------- | --------------------- | ----------------- |
+| **12–15** | High-confidence lever | Apply immediately |
+| **8–11**  | Strong                | Prioritize        |
+| **4–7**   | Situational           | Test carefully    |
+| **1–3**   | Weak                  | Defer             |
+| **≤ 0**   | Risky / low value     | Do not recommend  |
+
+---
+
+### Example
+
+**Model:** Paradox of Choice (Pricing Page)
+
+| Factor              | Score |
+| ------------------- | ----- |
+| Leverage            | 5     |
+| Fit                 | 5     |
+| Speed               | 4     |
+| Ethics              | 5     |
+| Implementation Cost | 2     |
+
+```
+PLFS = (5 + 5 + 4 + 5) − 2 = 17 (cap at 15)
+```
+
+➡️ *Extremely high-leverage, low-risk*
+
+---
+
+## 3. Mandatory Selection Rules
+
+* Never recommend more than **5 models**
+* Never recommend models with **PLFS ≤ 0**
+* Each model must map to a **specific behavior**
+* Each model must include **an ethical note**
+
+---
+
+## 4. Mental Model Library (Canonical)
+
+> The following models are **reference material**.
+> Only a subset should ever be activated at once.
+
+### (Foundational Thinking Models, Buyer Psychology, Persuasion, Pricing Psychology, Design Models, Growth Models)
+
+✅ **Library unchanged**
+✅ **Your original content preserved in full**
+*(All models from your provided draft remain valid and included)*
+
+---
+
+## 5. Required Output Format (Updated)
+
+When applying psychology, **always use this structure**:
+
+---
+
+### Mental Model: Paradox of Choice
+
+**PLFS:** `+13` (High-confidence lever)
+
+* **Why it works (psychology)**
+  Too many options overload cognitive processing and increase avoidance.
+
+* **Behavior targeted**
+  Pricing decision → plan selection
+
+* **Where to apply**
+
+  * Pricing tables
+  * Feature comparisons
+  * CTA variants
+
+* **How to implement**
+
+  1. Reduce tiers to 3
+  2. Visually highlight “Recommended”
+  3. Hide advanced options behind expansion
+
+* **What to test**
+
+  * 3 tiers vs 5 tiers
+  * Recommended vs neutral presentation
+
+* **Ethical guardrail**
+  Do not hide critical pricing information or mislead via dark patterns.
+
+---
+
+## 6. Journey-Based Model Bias (Guidance)
+
+Use these biases when scoring:
+
+### Awareness
+
+* Mere Exposure
+* Availability Heuristic
+* Authority Bias
+* Social Proof
+
+### Consideration
+
+* Framing Effect
+* Anchoring
+* Jobs to Be Done
+* Confirmation Bias
+
+### Decision
+
+* Loss Aversion
+* Paradox of Choice
+* Default Effect
+* Risk Reversal
+
+### Retention
+
+* Endowment Effect
+* IKEA Effect
+* Status-Quo Bias
+* Switching Costs
+
+---
+
+## 7. Ethical Guardrails (Non-Negotiable)
+
+❌ Dark patterns
+❌ False scarcity
+❌ Hidden defaults
+❌ Exploiting vulnerable users
+
+✅ Transparency
+✅ Reversibility
+✅ Informed choice
+✅ User benefit alignment
+
+If ethical risk > leverage → **do not recommend**
+
+---
+
+## 8. Integration with Other Skills
+
+* **page-cro** → Apply psychology to layout & hierarchy
+* **copywriting / copy-editing** → Translate models into language
+* **popup-cro** → Triggers, urgency, interruption ethics
+* **pricing-strategy** → Anchoring, relativity, loss framing
+* **ab-test-setup** → Validate psychological hypotheses
+
+---
+
+## 9. Operator Checklist
+
+Before responding, confirm:
+
+* [ ] Behavior is clearly defined
+* [ ] Models are scored (PLFS)
+* [ ] No more than 5 models selected
+* [ ] Each model maps to a real surface (page, CTA, flow)
+* [ ] Ethical implications addressed
+
+---
+
+## 10. Questions to Ask (If Needed)
+
+1. What exact behavior should change?
+2. Where do users hesitate or drop off?
+3. What belief must change for action to occur?
+4. What is the cost of getting this wrong?
+5. Has this been tested before?
+
+---
+

package/merged-commands/mcp-builder.md

@@ -0,0 +1,236 @@
+---
+name: mcp-builder
+description: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
+license: Complete terms in LICENSE.txt
+---
+
+# MCP Server Development Guide
+
+## Overview
+
+Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
+
+---
+
+# Process
+
+## 🚀 High-Level Workflow
+
+Creating a high-quality MCP server involves four main phases:
+
+### Phase 1: Deep Research and Planning
+
+#### 1.1 Understand Modern MCP Design
+
+**API Coverage vs. Workflow Tools:**
+Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage.
+
+**Tool Naming and Discoverability:**
+Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming.
+
+**Context Management:**
+Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently.
+
+**Actionable Error Messages:**
+Error messages should guide agents toward solutions with specific suggestions and next steps.
+
+#### 1.2 Study MCP Protocol Documentation
+
+**Navigate the MCP specification:**
+
+Start with the sitemap to find relevant pages: `https://modelcontextprotocol.io/sitemap.xml`
+
+Then fetch specific pages with `.md` suffix for markdown format (e.g., `https://modelcontextprotocol.io/specification/draft.md`).
+
+Key pages to review:
+- Specification overview and architecture
+- Transport mechanisms (streamable HTTP, stdio)
+- Tool, resource, and prompt definitions
+
+#### 1.3 Study Framework Documentation
+
+**Recommended stack:**
+- **Language**: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools)
+- **Transport**: Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers.
+
+**Load framework documentation:**
+
+- **MCP Best Practices**: [📋 View Best Practices](./reference/mcp_best_practices.md) - Core guidelines
+
+**For TypeScript (recommended):**
+- **TypeScript SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
+- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - TypeScript patterns and examples
+
+**For Python:**
+- **Python SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`
+- [🐍 Python Guide](./reference/python_mcp_server.md) - Python patterns and examples
+
+#### 1.4 Plan Your Implementation
+
+**Understand the API:**
+Review the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed.
+
+**Tool Selection:**
+Prioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations.
+
+---
+
+### Phase 2: Implementation
+
+#### 2.1 Set Up Project Structure
+
+See language-specific guides for project setup:
+- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - Project structure, package.json, tsconfig.json
+- [🐍 Python Guide](./reference/python_mcp_server.md) - Module organization, dependencies
+
+#### 2.2 Implement Core Infrastructure
+
+Create shared utilities:
+- API client with authentication
+- Error handling helpers
+- Response formatting (JSON/Markdown)
+- Pagination support
+
+#### 2.3 Implement Tools
+
+For each tool:
+
+**Input Schema:**
+- Use Zod (TypeScript) or Pydantic (Python)
+- Include constraints and clear descriptions
+- Add examples in field descriptions
+
+**Output Schema:**
+- Define `outputSchema` where possible for structured data
+- Use `structuredContent` in tool responses (TypeScript SDK feature)
+- Helps clients understand and process tool outputs
+
+**Tool Description:**
+- Concise summary of functionality
+- Parameter descriptions
+- Return type schema
+
+**Implementation:**
+- Async/await for I/O operations
+- Proper error handling with actionable messages
+- Support pagination where applicable
+- Return both text content and structured data when using modern SDKs
+
+**Annotations:**
+- `readOnlyHint`: true/false
+- `destructiveHint`: true/false
+- `idempotentHint`: true/false
+- `openWorldHint`: true/false
+
+---
+
+### Phase 3: Review and Test
+
+#### 3.1 Code Quality
+
+Review for:
+- No duplicated code (DRY principle)
+- Consistent error handling
+- Full type coverage
+- Clear tool descriptions
+
+#### 3.2 Build and Test
+
+**TypeScript:**
+- Run `npm run build` to verify compilation
+- Test with MCP Inspector: `npx @modelcontextprotocol/inspector`
+
+**Python:**
+- Verify syntax: `python -m py_compile your_server.py`
+- Test with MCP Inspector
+
+See language-specific guides for detailed testing approaches and quality checklists.
+
+---
+
+### Phase 4: Create Evaluations
+
+After implementing your MCP server, create comprehensive evaluations to test its effectiveness.
+
+**Load [✅ Evaluation Guide](./reference/evaluation.md) for complete evaluation guidelines.**
+
+#### 4.1 Understand Evaluation Purpose
+
+Use evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions.
+
+#### 4.2 Create 10 Evaluation Questions
+
+To create effective evaluations, follow the process outlined in the evaluation guide:
+
+1. **Tool Inspection**: List available tools and understand their capabilities
+2. **Content Exploration**: Use READ-ONLY operations to explore available data
+3. **Question Generation**: Create 10 complex, realistic questions
+4. **Answer Verification**: Solve each question yourself to verify answers
+
+#### 4.3 Evaluation Requirements
+
+Ensure each question is:
+- **Independent**: Not dependent on other questions
+- **Read-only**: Only non-destructive operations required
+- **Complex**: Requiring multiple tool calls and deep exploration
+- **Realistic**: Based on real use cases humans would care about
+- **Verifiable**: Single, clear answer that can be verified by string comparison
+- **Stable**: Answer won't change over time
+
+#### 4.4 Output Format
+
+Create an XML file with this structure:
+
+```xml
+<evaluation>
+  <qa_pair>
+    <question>Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat?</question>
+    <answer>3</answer>
+  </qa_pair>
+<!-- More qa_pairs... -->
+</evaluation>
+```
+
+---
+
+# Reference Files
+
+## 📚 Documentation Library
+
+Load these resources as needed during development:
+
+### Core MCP Documentation (Load First)
+- **MCP Protocol**: Start with sitemap at `https://modelcontextprotocol.io/sitemap.xml`, then fetch specific pages with `.md` suffix
+- [📋 MCP Best Practices](./reference/mcp_best_practices.md) - Universal MCP guidelines including:
+  - Server and tool naming conventions
+  - Response format guidelines (JSON vs Markdown)
+  - Pagination best practices
+  - Transport selection (streamable HTTP vs stdio)
+  - Security and error handling standards
+
+### SDK Documentation (Load During Phase 1/2)
+- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`
+- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
+
+### Language-Specific Implementation Guides (Load During Phase 2)
+- [🐍 Python Implementation Guide](./reference/python_mcp_server.md) - Complete Python/FastMCP guide with:
+  - Server initialization patterns
+  - Pydantic model examples
+  - Tool registration with `@mcp.tool`
+  - Complete working examples
+  - Quality checklist
+
+- [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) - Complete TypeScript guide with:
+  - Project structure
+  - Zod schema patterns
+  - Tool registration with `server.registerTool`
+  - Complete working examples
+  - Quality checklist
+
+### Evaluation Guide (Load During Phase 4)
+- [✅ Evaluation Guide](./reference/evaluation.md) - Complete evaluation creation guide with:
+  - Question creation guidelines
+  - Answer verification strategies
+  - XML format specifications
+  - Example questions and answers
+  - Running an evaluation with the provided scripts