القائمة
Choose assay-specific features and measurable objectives for behavior analysis, including distances, zones, speed, contact, orientation, and object interaction.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Label video behavior segments from frame-grid images with a defined behavior list, model-ready JSON, resumable outputs, and no_behavior handling for sparse labels.
Use Annolid GUI tools for robust automation across web, PDF, video, and chat controls.
Infer the assay or paradigm from video context, task text, tracked entities, and experimental cues such as social interaction, open field, courtship, resident-intruder, and novel object recognition.
Segment behavior timelines from tracks, pose, contact, speed, and proximity signals into typed intervals with stable labels and rationales.
Keep behavior analysis aligned with assay objectives, controls, reproducibility, and measurable outputs instead of ad hoc summaries.
Derive assay metrics from typed artifacts and segments, including bout counts, durations, rates, occupancy, proximity, and investigation time.
| name | behavior-feature-selection |
| description | Choose assay-specific features and measurable objectives for behavior analysis, including distances, zones, speed, contact, orientation, and object interaction. |
| metadata | {"annolid":{"always":false}} |
Use this skill to convert assay context into a concrete measurement plan.
Pick the smallest feature set that supports the requested assay outcome.
aggression: inter-animal distance, approach velocity, retreat, contact,
attack initiation, escape trajectories.social_interaction: body distance, nose-to-nose, following, orientation,
proximity dwell time.open_field: centroid, speed, immobility, center/periphery occupancy.novel_object_recognition: nose/object distance, investigation dwell time,
transitions between objects.courtship: pursuit, display posture, contact sequences, proximity dynamics.Return:
Do not request generic features "just in case". Select features that are tied to the assay and the requested report.