azaion/detections
1
0
Fork 0
mirror of https://github.com/azaion/detections.git synced 2026-04-22 23:46:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enhance autopilot documentation and workflows: Add assumptions regarding single project per workspace, update notification sound references, and introduce context budget heuristics for managing session limits. Revise various skill documents to reflect changes in task management, including ticketing and testing processes, ensuring clarity and consistency across the system.

Browse Source
This commit is contained in:
Oleksandr Bezdieniezhnykh
2026-03-24 05:56:12 +02:00
parent 749217bbb6
commit a5fc4fe073
14 changed files with 341 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.cursor/skills/code-review/SKILL.md
+39
View File
@@ -152,3 +152,42 @@ The `/implement` skill invokes this skill after each batch completes:
2. Passes task spec paths + changed files to this skill
3. If verdict is FAIL — presents findings to user (BLOCKING), user fixes or confirms
4. If verdict is PASS or PASS_WITH_WARNINGS — proceeds automatically (findings shown as info)
## Integration Contract
### Inputs (provided by the implement skill)
| Input | Type | Source | Required |
|-------|------|--------|----------|
| `task_specs` | list of file paths | Task `.md` files from `_docs/02_tasks/` for the current batch | Yes |
| `changed_files` | list of file paths | Files modified by implementer agents (from `git diff` or agent reports) | Yes |
| `batch_number` | integer | Current batch number (for report naming) | Yes |
| `project_restrictions` | file path | `_docs/00_problem/restrictions.md` | If exists |
| `solution_overview` | file path | `_docs/01_solution/solution.md` | If exists |
### Invocation Pattern
The implement skill invokes code-review by:
1. Reading `.cursor/skills/code-review/SKILL.md`
2. Providing the inputs above as context (read the files, pass content to the review phases)
3. Executing all 6 phases sequentially
4. Consuming the verdict from the output
### Outputs (returned to the implement skill)
| Output | Type | Description |
|--------|------|-------------|
| `verdict` | `PASS` / `PASS_WITH_WARNINGS` / `FAIL` | Drives the implement skill's auto-fix gate |
| `findings` | structured list | Each finding has: severity, category, file:line, title, description, suggestion, task reference |
| `critical_count` | integer | Number of Critical findings |
| `high_count` | integer | Number of High findings |
| `report_path` | file path | `_docs/03_implementation/reviews/batch_[NN]_review.md` |
### Report Persistence
Save the review report to `_docs/03_implementation/reviews/batch_[NN]_review.md` (create the `reviews/` directory if it does not exist). The report uses the Output Format defined above.
The implement skill uses `verdict` to decide:
- `PASS` / `PASS_WITH_WARNINGS` → proceed to commit
- `FAIL` → enter auto-fix loop (up to 2 attempts), then escalate to user