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/implement/SKILL.md

@@ -32,15 +32,18 @@ The `implementer` agent is the specialist that writes all the code — it receiv
 
 ## Context Resolution
 
-- TASKS_DIR: `_docs/02_tasks/`
+- TASKS_DIR: `_docs/02_tasks/todo/`
+- DONE_DIR: `_docs/02_tasks/done/`
+- BACKLOG_DIR: `_docs/02_tasks/backlog/`
+- TASKS_ROOT: `_docs/02_tasks/`
 - Task files: all `*.md` files in TASKS_DIR (excluding files starting with `_`)
-- Dependency table: `TASKS_DIR/_dependencies_table.md`
+- Dependency table: `TASKS_ROOT/_dependencies_table.md`
 
 ## Prerequisite Checks (BLOCKING)
 
-1. TASKS_DIR exists and contains at least one task file — **STOP if missing**
-2. `_dependencies_table.md` exists — **STOP if missing**
-3. At least one task is not yet completed — **STOP if all done**
+1. TASKS_DIR (`todo/`) exists and contains at least one task file — **STOP if missing**
+2. `TASKS_ROOT/_dependencies_table.md` exists — **STOP if missing**
+3. At least one task in TASKS_DIR is not yet completed — **STOP if all done** (already-completed tasks live in DONE_DIR)
 
 ## Algorithm
 
@@ -52,7 +55,8 @@ The `implementer` agent is the specialist that writes all the code — it receiv
 
 ### 2. Detect Progress
 
-- Scan the codebase to determine which tasks are already completed
+- Scan DONE_DIR to identify tasks that were already completed in previous runs
+- Scan the codebase to determine which TASKS_DIR tasks are already completed
 - Match implemented code against task acceptance criteria
 - Mark completed tasks as done in the DAG
 - Report progress to user: "X of Y tasks completed"
@@ -130,13 +134,18 @@ Track `auto_fix_attempts` count in the batch report for retrospective analysis.
   - `git commit` with a message that includes ALL task IDs (Jira IDs, ADO IDs, or numeric prefixes) of tasks implemented in the batch, followed by a summary of what was implemented. Format: `[TASK-ID-1] [TASK-ID-2] ... Summary of changes`
   - `git push` to the remote branch
 
+### 11b. Move Completed Tasks to Done
+
+- For each task in the batch that completed successfully, move its task spec file from TASKS_DIR (`todo/`) to DONE_DIR (`done/`)
+- `git add` the moved files and amend the batch commit, or create a follow-up commit
+
 ### 12. Update Tracker Status → In Testing
 
 After the batch is committed and pushed, transition the ticket status of each task in the batch to **In Testing** via the configured work item tracker. If `tracker: local`, skip this step.
 
 ### 13. Loop
 
-- Go back to step 2 until all tasks are done
+- Go back to step 2 until TASKS_DIR (`todo/`) is empty (all tasks moved to DONE_DIR)
 - When all tasks are complete, report final summary
 
 ## Batch Report Persistence