Make prompts more stuctured.

Separate tutorial.md for developers from commands for AI
WIP

.cursor/commands/2.planning/2.1_gen_components.md

@@ -0,0 +1,46 @@
+# decompose
+
+## The problem description
+ `@docs/00_problem/problem_description.md`.
+
+## Data samples
+  Located here: `@docs/00_problem/input_data`. They are for reference only, yet it is examples from the real data.
+
+## Restrictions for the input data
+   `@docs/00_problem/restrictions.md.md`.
+
+## Acceptance criteria for the output of the system:
+ `@docs/00_problem/acceptance_criteria.md`.  
+
+## Existing solution:
+ `@docs/01_solution/solution_draft.md`
+
+## Role
+  You are a professional software architect
+
+## Task
+ - Decompose a complex system solution to the components with proper communications between them, so that system would solve the problem. 
+ - Think about components and its interaction
+ - Think about possible requirements needed for complete full interaction flow.
+ - When you've got full understanding of how exactly each component will interact with each other
+
+## Output
+ - When all the uncertainties would be cleared by user, store description of each component to the file `docs/02_components/[##]_[component_name]/[component_name]_spec.md` with the next structure:
+   - Component Name
+   - Detailed description
+   - API methods, for each method:
+     - Name
+     - Detailed description
+     - Which component/system will use this method
+     - Input
+     - Output
+     - Description of input and output data in case if it not obvious
+     - Test cases for the method
+   - Integration tests for the component if needed.
+   - Non-functional tests for the component if needed.
+ - Extensions and helpers to support functionality across multiple components store to a separate folder `docs/02_components/helpers`.
+ - Generate draw.io components diagram shows relations between components. 
+
+## Notes
+ Do not put any code yet, only names, input and output.
+ Ask as many questions as possible to clarify all uncertainties.