agentleFS
hailo-aihailo-ai/hailo-apps/.cursor/rules/standalone-apps.mdc

hailo-apps / rules

Cursor rule506 starsChanged 7 months agoMITView on GitHub

You are working on a standalone inference application (HailoInfer + OpenCV, no GStreamer). Read these files before making changes (paths relative to .hailo/):

We split this standalone-apps.mdc into the rules it gives an agent

7 rules. About 0 are common, 0 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read these files before making changes (paths relative to .hailo/):

    line 12
  2. Very specific:

    If camera input: memory/camera_and_display.md, skills/hl-camera.md

    line 23
  3. Very specific:

    If adding models: skills/hl-model-management.md

    line 24
  4. Very specific:

    Use HailoInfer for inference (wraps VDevice + HEF loading)

    line 28
  5. Very specific:

    Use get_standalone_parser() for CLI arguments

    line 29
  6. Very specific:

    Use SHARED_VDEVICE_GROUP_ID for VDevice creation

    line 30
  7. Very specific:

    Always resolve HEF paths with resolve_hef_path(path, app_name, arch)

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
standalone-apps.mdc
---
globs: ["**/standalone_apps/**"]
alwaysApply: false
---

# Standalone Apps — Contextual Instructions

You are working on a **standalone inference application** (HailoInfer + OpenCV, no GStreamer).

## Required Context Files

Read these files before making changes (paths relative to `.hailo/`):

- `skills/hl-build-standalone-app/SKILL.md` — Standalone app patterns
- `instructions/coding-standards.md` — Import rules, logging, HEF resolution
- `toolsets/core-framework-api.md` — HailoInfer, camera_utils, parsers
- `toolsets/hailort-api.md` — VDevice, HEF resolution, constants
- `memory/hailo_platform_api.md` — VDevice creation, HEF resolution chain
- `memory/common_pitfalls.md` — Known anti-patterns to avoid

## Additional Context (load if relevant)

- If camera input: `memory/camera_and_display.md`, `skills/hl-camera.md`
- If adding models: `skills/hl-model-management.md`

## Key Patterns for Standalone Apps

- Use `HailoInfer` for inference (wraps VDevice + HEF loading)
- Use `get_standalone_parser()` for CLI arguments
- Use `SHARED_VDEVICE_GROUP_ID` for VDevice creation
- Always resolve HEF paths with `resolve_hef_path(path, app_name, arch)`
- OpenCV for frame capture and display — check `camera_and_display.md` for BGR/RGB gotchas
- Register new apps in `hailo_apps/python/core/common/defines.py`

## Reference Implementations

- Object detection: `hailo_apps/python/standalone_apps/object_detection/`
- Pose estimation: `hailo_apps/python/standalone_apps/pose_estimation/`
- Instance segmentation: `hailo_apps/python/standalone_apps/instance_segmentation/`

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.