菜单
Record learning exercise results back to the Cognition API. Updates the forgetting model.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
Send screen observations to the Cognition API as learning events. Transforms Screenpipe data into API event format.
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".
| name | reflect |
| description | Record learning exercise results back to the Cognition API. Updates the forgetting model. |
| user-invocable | false |
After any learning exercise, record the results back to the Cognition API so the forgetting model updates.
For each question the user answered, POST a quiz_answer event:
TOKEN=$(cat ~/.cognition/token)
curl -s -X POST -H "x-api-key: $TOKEN" -H "Content-Type: application/json" \
https://cognition-api.fly.dev/v1/events \
-d '{
"event": {
"schema_version": "1.0",
"event_id": "'$(python3 -c "import uuid; print(uuid.uuid4())")'",
"idempotency_key": "'$(python3 -c "import uuid; print(uuid.uuid4())")'",
"timestamp_ms": '$(python3 -c "import time; print(int(time.time()*1000))")',
"event_type": "quiz_answer",
"tenant": { "tenant_id": "TENANT_ID", "deployment_id": "prod" },
"user": { "user_id": "USER_ID", "pseudonymous_id": "USER_ID", "locale": "en", "timezone": "America/Chicago" },
"session": {
"session_id": "SESSION_ID",
"surface": "desktop_widget",
"app_context": "Other",
"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": 1.0 }
},
"provenance": { "source": "quiz" },
"privacy": { "consent_raw_text": true, "consent_embeddings_only": false, "pii_detected": false, "redaction_applied": false },
"payload": {
"quiz_session_id": "QUIZ_SESSION",
"quiz_id": "QUIZ_ID",
"quiz_version": "1.0",
"question_id": "Q1",
"question_type": "multiple_choice",
"difficulty": "medium",
"is_correct": true,
"evaluation_score": 1.0,
"latency_ms": 5000,
"hints_used": 0,
"solution_viewed": false,
"kc_node_id": "CONCEPT_ID",
"mastery_change": 0.0,
"concept_tagging": { "concepts": ["CONCEPT_ID"] }
}
}
}'
Replace placeholder values (TENANT_ID, USER_ID, etc.) with actual values from the current session context.
POST a delayed_probe event with the probe result:
curl -s -X POST -H "x-api-key: $TOKEN" -H "Content-Type: application/json" \
https://cognition-api.fly.dev/v1/probes/outcome \
-d '{
"probe_id": "PROBE_ID",
"concept_id": "CONCEPT_ID",
"horizon_days": 3,
"predicted_recall": 0.65,
"result_correct": true,
"result_score": 0.9,
"result_confidence": 0.8
}'
Confirm to the user what was updated: