Closed
Conversation
Add the skill system foundation for DeepCamera's evolution into an AI skill platform for SharpAI Aegis. New files: - skills.json: Registry manifest listing available skills - skills/detection/yolo-detection-2026/SKILL.md: First skill spec with parameters, capabilities, setup instructions, and JSON-lines protocol - skills/detection/yolo-detection-2026/requirements.txt: Python dependencies - skills/detection/yolo-detection-2026/scripts/detect.py: Working reference implementation using ultralytics YOLO with stdin/stdout JSON-lines protocol Updated: - README.md: Check 'Skill architecture' roadmap item The skill architecture uses a pluggable SKILL.md interface where each skill declares parameters (rendered as config UI in Aegis) and capabilities (what the skill can do). Skills communicate via JSON lines over stdin/stdout.
- .gitignore: modernize with Python, ML models, Docker, IDE sections - CONTRIBUTING.md: add skill-focused contributing guide - CODE_OF_CONDUCT.md: update to Contributor Covenant 2.1 - Contributions.md: refresh third-party acknowledgments for 2026 - FUNDING.yml: move to .github/ (GitHub convention) - docs/skill-development.md: add comprehensive skill development guide covering SKILL.md format, parameter types, JSON-lines protocol, and skill categories
Add README.md inside src/ so visitors immediately understand the 19 modules, their purpose, and status (Production/Experimental/Legacy). Includes ASCII architecture diagram and evolution table mapping legacy modules to their new skill equivalents.
Add SKILL.md manifests for the complete DeepCamera skill platform: Detection (3): - yolo-detection-2026: YOLOv11/v10 real-time detection - dinov3-grounding: open-vocabulary detection - person-recognition: cross-camera ReID Analysis (2): - vlm-scene-analysis: offline VLM clip understanding - sam2-segmentation: click-to-segment (Segment Anything 2) Transformation (1): - depth-estimation: Depth Anything v2 depth maps Annotation (1): - dataset-annotation: AI-assisted COCO annotation + export Camera Providers (5): - blink, eufy, reolink, tapo, ring Streaming (1): - go2rtc-cameras: multi-camera RTSP to WebRTC Channels (3): - matrix, line, signal messaging channels Automation (3): - mqtt, webhook, ha-trigger Integrations (1): - homeassistant-bridge: bidirectional HA integration Also updates skills.json registry manifest with all 20 skills.
- Remove camera-providers/blink and camera-providers/ring (built into Aegis) - Remove blink/ring from skills.json registry - Add requirements.txt and working Python scripts for all 18 skills: Detection: dinov3-grounding/ground.py, person-recognition/detect.py Analysis: vlm-scene-analysis/analyze.py, sam2-segmentation/segment.py Transformation: depth-estimation/transform.py Annotation: dataset-annotation/annotate.py (CocoDatasetManager) Camera Providers: eufy/feed.py, reolink/feed.py, tapo/feed.py Streaming: go2rtc-cameras/stream.py Channels: matrix/channel.py, line/channel.py, signal/channel.py Automation: mqtt/mqtt_publish.py, webhook/webhook.py, ha-trigger/ha_trigger.py Integrations: homeassistant-bridge/bridge.py All scripts follow the JSON-lines stdin/stdout protocol defined in SKILL.md.
… feature/consolidate-unmerged # Conflicts: # README.md # skills.json
… feature/consolidate-unmerged # Conflicts: # skills.json
…ure/consolidate-unmerged # Conflicts: # README.md
…/consolidate-unmerged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.