@techierathore/techieflow 1.0.2 → 1.0.4

package/.tfcore/tasks/kb-mode-interaction.md

@@ -1,75 +0,0 @@
-# KB Mode Interaction Task
-
-## Purpose
-
-Provide a user-friendly interface to the TechieFlow knowledge base without overwhelming users with information upfront.
-
-## Instructions
-
-When entering KB mode (\*kb-mode), follow these steps:
-
-### 1. Welcome and Guide
-
-Announce entering KB mode with a brief, friendly introduction.
-
-### 2. Present Topic Areas
-
-Offer a concise list of main topic areas the user might want to explore:
-
-**What would you like to know more about?**
-
-1. **Setup & Installation** - Getting started with TechieFlow
-2. **Workflows** - Choosing the right workflow for your project
-3. **Web vs IDE** - When to use each environment
-4. **Agents** - Understanding specialized agents and their roles
-5. **Documents** - PRDs, Architecture, Stories, and more
-6. **Agile Process** - How TechieFlow implements Agile methodologies
-7. **Configuration** - Customizing TechieFlow for your needs
-8. **Best Practices** - Tips for effective TechieFlow usage
-
-Or ask me about anything else related to TechieFlow!
-
-### 3. Respond Contextually
-
-- Wait for user's specific question or topic selection
-- Provide focused, relevant information from the knowledge base
-- Offer to dive deeper or explore related topics
-- Keep responses concise unless user asks for detailed explanations
-
-### 4. Interactive Exploration
-
-- After answering, suggest related topics they might find helpful
-- Maintain conversational flow rather than data dumping
-- Use examples when appropriate
-- Reference specific documentation sections when relevant
-
-### 5. Exit Gracefully
-
-When user is done or wants to exit KB mode:
-
-- Summarize key points discussed if helpful
-- Remind them they can return to KB mode anytime with \*kb-mode
-- Suggest next steps based on what was discussed
-
-## Example Interaction
-
-**User**: \*kb-mode
-
-**Assistant**: I've entered KB mode and have access to the full TechieFlow knowledge base. I can help you with detailed information about any aspect of TechieFlow.
-
-**What would you like to know more about?**
-
-1. **Setup & Installation** - Getting started with TechieFlow
-2. **Workflows** - Choosing the right workflow for your project
-3. **Web vs IDE** - When to use each environment
-4. **Agents** - Understanding specialized agents and their roles
-5. **Documents** - PRDs, Architecture, Stories, and more
-6. **Agile Process** - How TechieFlow implements Agile methodologies
-7. **Configuration** - Customizing TechieFlow for your needs
-8. **Best Practices** - Tips for effective TechieFlow usage
-
-Or ask me about anything else related to TechieFlow!
-
-**User**: Tell me about workflows
-
-**Assistant**: [Provides focused information about workflows from the KB, then offers to explore specific workflow types or related topics]

package/.tfcore/tasks/shard-doc.md

@@ -1,185 +0,0 @@
-# Document Sharding Task
-
-## Purpose
-
-- Split a large document into multiple smaller documents based on level 2 sections
-- Create a folder structure to organize the sharded documents
-- Maintain all content integrity including code blocks, diagrams, and markdown formatting
-
-## Primary Method: Automatic with markdown-tree
-
-[[LLM: First, check if markdownExploder is set to true in .tfcore/core-config.yaml. If it is, attempt to run the command: `md-tree explode {input file} {output path}`.
-
-If the command succeeds, inform the user that the document has been sharded successfully and STOP - do not proceed further.
-
-If the command fails (especially with an error indicating the command is not found or not available), inform the user: "The markdownExploder setting is enabled but the md-tree command is not available. Please either:
-
-1. Install @kayvan/markdown-tree-parser globally with: `npm install -g @kayvan/markdown-tree-parser`
-2. Or set markdownExploder to false in .tfcore/core-config.yaml
-
-**IMPORTANT: STOP HERE - do not proceed with manual sharding until one of the above actions is taken.**"
-
-If markdownExploder is set to false, inform the user: "The markdownExploder setting is currently false. For better performance and reliability, you should:
-
-1. Set markdownExploder to true in .tfcore/core-config.yaml
-2. Install @kayvan/markdown-tree-parser globally with: `npm install -g @kayvan/markdown-tree-parser`
-
-I will now proceed with the manual sharding process."
-
-Then proceed with the manual method below ONLY if markdownExploder is false.]]
-
-### Installation and Usage
-
-1. **Install globally**:
-
-   ```bash
-   npm install -g @kayvan/markdown-tree-parser
-   ```
-
-2. **Use the explode command**:
-
-   ```bash
-   # For PRD
-   md-tree explode docs/prd.md docs/prd
-
-   # For Architecture
-   md-tree explode docs/architecture.md docs/architecture
-
-   # For any document
-   md-tree explode [source-document] [destination-folder]
-   ```
-
-3. **What it does**:
-   - Automatically splits the document by level 2 sections
-   - Creates properly named files
-   - Adjusts heading levels appropriately
-   - Handles all edge cases with code blocks and special markdown
-
-If the user has @kayvan/markdown-tree-parser installed, use it and skip the manual process below.
-
----
-
-## Manual Method (if @kayvan/markdown-tree-parser is not available or user indicated manual method)
-
-### Task Instructions
-
-1. Identify Document and Target Location
-
-- Determine which document to shard (user-provided path)
-- Create a new folder under `docs/` with the same name as the document (without extension)
-- Example: `docs/prd.md` → create folder `docs/prd/`
-
-2. Parse and Extract Sections
-
-CRITICAL AEGNT SHARDING RULES:
-
-1. Read the entire document content
-2. Identify all level 2 sections (## headings)
-3. For each level 2 section:
-   - Extract the section heading and ALL content until the next level 2 section
-   - Include all subsections, code blocks, diagrams, lists, tables, etc.
-   - Be extremely careful with:
-     - Fenced code blocks (```) - ensure you capture the full block including closing backticks and account for potential misleading level 2's that are actually part of a fenced section example
-     - Mermaid diagrams - preserve the complete diagram syntax
-     - Nested markdown elements
-     - Multi-line content that might contain ## inside code blocks
-
-CRITICAL: Use proper parsing that understands markdown context. A ## inside a code block is NOT a section header.]]
-
-### 3. Create Individual Files
-
-For each extracted section:
-
-1. **Generate filename**: Convert the section heading to lowercase-dash-case
-   - Remove special characters
-   - Replace spaces with dashes
-   - Example: "## Tech Stack" → `tech-stack.md`
-
-2. **Adjust heading levels**:
-   - The level 2 heading becomes level 1 (# instead of ##) in the sharded new document
-   - All subsection levels decrease by 1:
-
-   ```txt
-     - ### → ##
-     - #### → ###
-     - ##### → ####
-     - etc.
-   ```
-
-3. **Write content**: Save the adjusted content to the new file
-
-### 4. Create Index File
-
-Create an `index.md` file in the sharded folder that:
-
-1. Contains the original level 1 heading and any content before the first level 2 section
-2. Lists all the sharded files with links:
-
-```markdown
-# Original Document Title
-
-[Original introduction content if any]
-
-## Sections
-
-- [Section Name 1](./section-name-1.md)
-- [Section Name 2](./section-name-2.md)
-- [Section Name 3](./section-name-3.md)
-  ...
-```
-
-### 5. Preserve Special Content
-
-1. **Code blocks**: Must capture complete blocks including:
-
-   ```language
-   content
-   ```
-
-2. **Mermaid diagrams**: Preserve complete syntax:
-
-   ```mermaid
-   graph TD
-   ...
-   ```
-
-3. **Tables**: Maintain proper markdown table formatting
-
-4. **Lists**: Preserve indentation and nesting
-
-5. **Inline code**: Preserve backticks
-
-6. **Links and references**: Keep all markdown links intact
-
-7. **Template markup**: If documents contain {{placeholders}} ,preserve exactly
-
-### 6. Validation
-
-After sharding:
-
-1. Verify all sections were extracted
-2. Check that no content was lost
-3. Ensure heading levels were properly adjusted
-4. Confirm all files were created successfully
-
-### 7. Report Results
-
-Provide a summary:
-
-```text
-Document sharded successfully:
-- Source: [original document path]
-- Destination: docs/[folder-name]/
-- Files created: [count]
-- Sections:
-  - section-name-1.md: "Section Title 1"
-  - section-name-2.md: "Section Title 2"
-  ...
-```
-
-## Important Notes
-
-- Never modify the actual content, only adjust heading levels
-- Preserve ALL formatting, including whitespace where significant
-- Handle edge cases like sections with code blocks containing ## symbols
-- Ensure the sharding is reversible (could reconstruct the original from shards)