Skill-Details

spaced-practice-scheduler

Plans evidence-based learning and revision schedules.

ÜbereinstimmungDirektGeprüft für bildung
Quellegarethmanning/education-agent-skillsExterne Quelle
Gemeldete Installationen75Nur Popularitätssignal

Vor Nutzung prüfen

Die automatische Prüfung bewertet Relevanz, nicht Sicherheit oder Empfehlung. Lies vor der Nutzung die Quellanweisungen.

Gespeicherte Quellvorschau

SKILL.md

Dieser Auszug wurde bei der Prüfung gespeichert. Die externe Quelle enthält die vollständige und aktuelle Version.

---
# AGENT SKILLS STANDARD FIELDS (v2)
name: spaced-practice-scheduler
description: "Design a spaced retrieval schedule for any topic list and timeline. Use when planning units, term sequences, or revision programmes."
disable-model-invocation: false
user-invocable: true
effort: medium

# EXISTING FIELDS

skill_id: "memory-learning-science/spaced-practice-scheduler"
skill_name: "Spaced Practice Schedule Builder"
domain: "memory-learning-science"
version: "1.0"
evidence_strength: "strong"
evidence_sources:
  - "Ebbinghaus (1885/1913) — The forgetting curve: exponential decay of memory without review"
  - "Cepeda et al. (2006) — Meta-analysis of 254 studies on distributed practice: optimal spacing depends on retention interval"
  - "Kornell & Bjork (2008) — Spacing and interleaving effects on learning"
  - "Carpenter et al. (2012) — Using spacing to enhance diverse forms of learning"
  - "Dunlosky et al. (2013) — Distributed practice rated high-utility learning strategy"
input_schema:
  required:
    - field: "topics"
      type: "array"
      description: "List of topics or concepts to be spaced across the schedule"
    - field: "timeline"
      type: "string"
      description: "Available teaching period (e.g. '6-week half-term' or 'Term 2: Jan 15 – Mar 28')"
    - field: "lessons_per_week"
      type: "integer"
      description: "Number of lessons per week for this subject"
  optional:
    - field: "assessment_date"
      type: "string"
      description: "Date of summative assessment, if known — affects final spacing intervals"
    - field: "topic_difficulty"
      type: "array"
      description: "Teacher's estimate of relative difficulty for each topic (high/medium/low)"
    - field: "curriculum_sequence"
      type: "array"
      description: "From context engine: mandated teaching order or prerequisite dependencies"
    - field: "student_profiles"
      type: "array"
      description: "From context engine: class-level retention data from prior assessments"
output_schema:
  type: "object"
  fields:
    - field: "schedule"
      type: "array"
      description: "Week-by-week schedule showing new teaching and spaced review slots"
    - field: "spacing_rationale"
      type: "string"
      description: "Explanation of why topics are spaced at these intervals"
    - field: "review_activity_suggestions"
      type: "array"
      description: "Brief retrieval activities for each review slot"
    - field: "teacher_guidance"
      type: "string"
      description: "How to implement the schedule and adjust based on student response"
chains_well_with:
  - "retrieval-practice-generator"
  - "interleaving-unit-planner"
  - "formative-assessment-technique-selector"
  - "lesson-opening-designer"
teacher_time: "5 minutes"
tags: ["spacing", "memory", "planning", "forgetting-curve", "distributed-practice"]
---

# Spaced Practice Schedule Builder

## What This Skill Does

Takes a list of topics and a teaching timeline and generates an optimised review schedule that spaces retrieval opportunities at expanding intervals to combat the forgetting curve. The output is a week-by-week plan showing when to introduce new content and when to revisit previous topics, with specific activity suggestions for each review slot. AI is specifically valuable here because calculating optimal spacing intervals across multiple topics while respecting prerequisite dependencies and timetable constraints is genuinely complex — most teachers default to blocked practice (finish topic A, move to topic B, never return) because the cognitive load of planning spaced schedules manually is too high.

## Evidence Foundation

Ebbinghaus (1885/1913) first demonstrated that memory follows an exponential decay curve — without review, approximately 70% of new learning is lost within 24 hours. Cepeda et al. (2006) conducted a meta-analysis of 254 studies and established that the optimal gap between study sessions depends on the desired retention interval: roughly 10–20% of th
Vollständige Quelle auf GitHub lesen (öffnet externe Seite)
Kontext

Verwandte Arbeit