메뉴
Send screen observations to the Cognition API as learning events. Transforms Screenpipe data into API event format.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Connect a notification channel (Slack, Gmail, etc.) so Cognition can send you learning exercises throughout the day — even when your laptop is off.
Schedule learning exercises for the next 24 hours via Slack/Gmail. Runs at the end of every session so exercises arrive even when Claude Code is closed. The API decides WHEN and WHAT technique — you build the exercise and schedule delivery.
Launch the Cognition GUI app. Opens the Electron window and connects Claude Code to it via WebSocket. Use this after /cognition:start or whenever you need the GUI.
Generate and deliver a learning exercise based on what the user is forgetting. Orchestrates different learning techniques.
Test if the user's confidence matches their actual knowledge. Use when calibration ECE is high or strategy is "overconfident".
Quick surprise retention check. A 30-second mini-quiz to test if a concept is still in memory. Use for concepts with high stability that haven't been tested recently.
| name | ingest |
| description | Send screen observations to the Cognition API as learning events. Transforms Screenpipe data into API event format. |
| user-invocable | false |
Transform raw Screenpipe observations into Cognition API events and POST them.
TOKEN=$(cat ~/.cognition/token)
EVENT_ID=$(python3 -c "import uuid; print(uuid.uuid4())")
TIMESTAMP=$(python3 -c "import time; print(int(time.time()*1000))")
curl -s -X POST -H "x-api-key: $TOKEN" -H "Content-Type: application/json" \
https://cognition-api.fly.dev/v1/events \
-d '{
"event": {
"schema_version": "1.0",
"event_id": "'$EVENT_ID'",
"idempotency_key": "'$EVENT_ID'",
"timestamp_ms": '$TIMESTAMP',
"event_type": "screen_capture",
"tenant": { "tenant_id": "default", "deployment_id": "prod" },
"user": { "user_id": "USER_ID", "pseudonymous_id": "USER_ID", "locale": "en", "timezone": "America/Chicago" },
"session": {
"session_id": "session-'$EVENT_ID'",
"surface": "desktop_widget",
"app_context": "APP_CONTEXT",
"device": { "os": "Windows", "device_type": "desktop", "screen": { "width": 1920, "height": 1080 } },
"attention": { "active_time_ms": 5000, "idle_time_ms": 0, "focus_switch_count": 0, "window_focus_ratio": 0.9 }
},
"provenance": { "source": "screen" },
"privacy": { "consent_raw_text": true, "consent_embeddings_only": false, "pii_detected": false, "redaction_applied": false },
"payload": {
"text_spans": ["THE_OCR_TEXT"],
"span_hashes": [],
"viewport_coverage_ratio": 0.8,
"app_context": "APP_CONTEXT",
"concept_tagging": { "concepts": [], "edges": [], "relations": [] }
}
}
}'
Map Screenpipe app names to API AppContext:
Replace placeholders with actual values:
USER_ID: from the token (decode the JWT to get the sub field, or use a stored user ID)APP_CONTEXT: mapped from screenpipe app nameTHE_OCR_TEXT: actual text from screenpipeReport results:
Ingested 5 screen captures. API extracted 12 concepts, 4 relations.
The API handles concept extraction via Gemini and forgetting model updates automatically.