القائمة
Active recall quiz at optimal spacing intervals. The core spaced repetition technique. Use when the API recommends "quiz" or the concept has lapses > 0.
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
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 | spaced-retrieval |
| description | Active recall quiz at optimal spacing intervals. The core spaced repetition technique. Use when the API recommends "quiz" or the concept has lapses > 0. |
| user-invocable | false |
The most effective learning technique. Force the user to recall information without hints.
Use the concept label and any context from the learner state
Generate 2-3 questions per concept, varying in format:
Match difficulty to the user's ZPD band from the API:
below: easier questions, more scaffoldinginside: challenging but achievableabove: stretch questions with hints availableFor each question:
Present clearly with context:
Q1/3 — React Hooks (retrievability: 43%, last reviewed: 3 days ago)
What happens when you return a function from useEffect?
a) It runs immediately on mount b) It runs when the component unmounts or before the effect re-runs c) It prevents the effect from running again d) It caches the effect's dependencies
Wait for the user's answer
Grade:
Give feedback:
Record via reflect flow with:
question_type: multiple_choice / short_answer / true_falsedifficulty: easy / medium / hard / zpdis_correct: boolevaluation_score: 0.0-1.0latency_ms: time from question shown to answerconfidence_self_report: ask "How confident were you?" (1-5 scale, map to 0-1)The API handles spacing via the Weibull decay model. After recording results, the API updates stability and difficulty. The next review time is computed server-side. Just report results accurately.