Refactor inference engine and task management: Remove obsolete inference engine and ONNX engine files, update inference processing to utilize batch handling, and enhance task management structure in documentation. Adjust paths for task specifications to align with new directory organization.

.cursor/skills/decompose/SKILL.md

@@ -22,7 +22,7 @@ Decompose planned components into atomic, implementable task specs with a bootst
 
 - **Atomic tasks**: each task does one thing; if it exceeds 5 complexity points, split it
 - **Behavioral specs, not implementation plans**: describe what the system should do, not how to build it
-- **Flat structure**: all tasks are Jira-ID-prefixed files in TASKS_DIR — no component subdirectories
+- **Flat structure**: all tasks are Jira-ID-prefixed files in TASKS_DIR (`todo/`) — no component subdirectories within workflow folders
 - **Save immediately**: write artifacts to disk after each task; never accumulate unsaved work
 - **Jira inline**: create Jira ticket immediately after writing each task file
 - **Ask, don't assume**: when requirements are ambiguous, ask the user before proceeding
@@ -34,20 +34,26 @@ Determine the operating mode based on invocation before any other logic runs.
 
 **Default** (no explicit input file provided):
 - DOCUMENT_DIR: `_docs/02_document/`
-- TASKS_DIR: `_docs/02_tasks/`
+- TASKS_DIR: `_docs/02_tasks/todo/`
+- TASKS_ROOT: `_docs/02_tasks/`
+- DEPS_TABLE: `_docs/02_tasks/_dependencies_table.md`
 - Reads from: `_docs/00_problem/`, `_docs/01_solution/`, DOCUMENT_DIR
 - Runs Step 1 (bootstrap) + Step 2 (all components) + Step 3 (blackbox tests) + Step 4 (cross-verification)
 
 **Single component mode** (provided file is within `_docs/02_document/` and inside a `components/` subdirectory):
 - DOCUMENT_DIR: `_docs/02_document/`
-- TASKS_DIR: `_docs/02_tasks/`
+- TASKS_DIR: `_docs/02_tasks/todo/`
+- TASKS_ROOT: `_docs/02_tasks/`
+- DEPS_TABLE: `_docs/02_tasks/_dependencies_table.md`
 - Derive component number and component name from the file path
 - Ask user for the parent Epic ID
 - Runs Step 2 (that component only, appending to existing task numbering)
 
 **Tests-only mode** (provided file/directory is within `tests/`, or `DOCUMENT_DIR/tests/` exists and input explicitly requests test decomposition):
 - DOCUMENT_DIR: `_docs/02_document/`
-- TASKS_DIR: `_docs/02_tasks/`
+- TASKS_DIR: `_docs/02_tasks/todo/`
+- TASKS_ROOT: `_docs/02_tasks/`
+- DEPS_TABLE: `_docs/02_tasks/_dependencies_table.md`
 - TESTS_DIR: `DOCUMENT_DIR/tests/`
 - Reads from: `_docs/00_problem/`, `_docs/01_solution/`, TESTS_DIR
 - Runs Step 1t (test infrastructure bootstrap) + Step 3 (blackbox test decomposition) + Step 4 (cross-verification against test coverage)
@@ -99,8 +105,8 @@ Announce the detected mode and resolved paths to the user before proceeding.
 
 **Default:**
 1. DOCUMENT_DIR contains `architecture.md` and `components/` — **STOP if missing**
-2. Create TASKS_DIR if it does not exist
-3. If TASKS_DIR already contains task files, ask user: **resume from last checkpoint or start fresh?**
+2. Create TASKS_ROOT subfolders (`todo/`, `backlog/`, `done/`) if they do not exist
+3. If TASKS_DIR (`todo/`) already contains task files, ask user: **resume from last checkpoint or start fresh?**
 
 **Single component mode:**
 1. The provided component file exists and is non-empty — **STOP if missing**
@@ -108,22 +114,26 @@ Announce the detected mode and resolved paths to the user before proceeding.
 **Tests-only mode:**
 1. `TESTS_DIR/blackbox-tests.md` exists and is non-empty — **STOP if missing**
 2. `TESTS_DIR/environment.md` exists — **STOP if missing**
-3. Create TASKS_DIR if it does not exist
-4. If TASKS_DIR already contains task files, ask user: **resume from last checkpoint or start fresh?**
+3. Create TASKS_ROOT subfolders (`todo/`, `backlog/`, `done/`) if they do not exist
+4. If TASKS_DIR (`todo/`) already contains task files, ask user: **resume from last checkpoint or start fresh?**
 
 ## Artifact Management
 
 ### Directory Structure
 
 ```
-TASKS_DIR/
-├── [JIRA-ID]_initial_structure.md
-├── [JIRA-ID]_[short_name].md
-├── [JIRA-ID]_[short_name].md
-├── ...
-└── _dependencies_table.md
+_docs/02_tasks/
+├── _dependencies_table.md
+├── backlog/
+├── todo/
+│   ├── [JIRA-ID]_initial_structure.md
+│   ├── [JIRA-ID]_[short_name].md
+│   └── ...
+└── done/
 ```
 
+New task files are written to `todo/`. The `/implement` skill moves them to `done/` after successful implementation. Users can move tasks to `backlog/` to defer them.
+
 **Naming convention**: Each task file is initially saved with a temporary numeric prefix (`[##]_[short_name].md`). After creating the Jira ticket, rename the file to use the Jira ticket ID as prefix (`[JIRA-ID]_[short_name].md`). For example: `01_initial_structure.md` → `AZ-42_initial_structure.md`.
 
 ### Save Timing
@@ -138,9 +148,9 @@ TASKS_DIR/
 
 ### Resumability
 
-If TASKS_DIR already contains task files:
+If task files already exist (in `todo/`, `backlog/`, or `done/`):
 
-1. List existing `*_*.md` files (excluding `_dependencies_table.md`) and count them
+1. List existing `*_*.md` files across all three subfolders (excluding `_dependencies_table.md`) and count them
 2. Resume numbering from the next number (for temporary numeric prefix before Jira rename)
 3. Inform the user which tasks already exist and are being skipped
 
@@ -342,7 +352,7 @@ Tests-only mode:
 - **Cross-component tasks**: each task belongs to exactly one component
 - **Skipping BLOCKING gates**: never proceed past a BLOCKING marker without user confirmation
 - **Creating git branches**: branch creation is an implementation concern, not a decomposition one
-- **Creating component subdirectories**: all tasks go flat in TASKS_DIR
+- **Creating component subdirectories**: all tasks go flat in TASKS_DIR (`todo/`)
 - **Forgetting Jira**: every task must have a Jira ticket created inline — do not defer to a separate step
 - **Forgetting to rename**: after Jira ticket creation, always rename the file from numeric prefix to Jira ID prefix