원클릭으로
predict
Check what knowledge is decaying and what needs review. Shows recommendations from the Cognition API.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Check what knowledge is decaying and what needs review. Shows recommendations from the Cognition API.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
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".
SOC 직업 분류 기준
| name | predict |
| description | Check what knowledge is decaying and what needs review. Shows recommendations from the Cognition API. |
TOKEN=$(cat ~/.cognition/token)
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/recommendations?user_id=USER_ID&limit=10"
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/learner-state?user_id=USER_ID"
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/strategy/signature?user_id=USER_ID"
curl -s -H "x-api-key: $TOKEN" \
"https://cognition-api.fly.dev/v1/calibration/snapshot?user_id=USER_ID"
Show the user a clear summary:
🧠 Knowledge State
📉 Decaying (needs review soon):
• React useEffect cleanup — 43% recall, critical in 1.5 days
• SQL JOIN types — 52% recall, critical in 3 days
• Git rebase workflow — 61% recall, critical in 5 days
📊 Strong (no action needed):
• Python list comprehensions — 92% recall
• HTTP status codes — 87% recall
🎯 Your learning style: stable_retriever
📐 Calibration: well-calibrated (ECE: 0.08)
Recommended: Quiz on useEffect cleanup (highest priority)
If there are urgent recommendations, offer to start a learning exercise immediately by invoking the learn skill.