agency-scaffold-generator
Agency Scaffold Generator
What This Skill Does
Generates a structured scaffold for progressively releasing decision-making to students — moving from teacher-directed to student-directed learning in specific, manageable steps across five dimensions of agency: choice of topic, choice of process, choice of product, choice of criteria, and choice of timeline. The critical principle is that agency is not binary (teacher controls vs. student controls) but a continuum that must be scaffolded — giving full agency to students who have never had it is as counterproductive as never giving agency at all. The output is a progressive release scaffold showing exactly what choices to offer at each level, how to structure those choices so they are meaningful but manageable, and what to do when students make poor choices (recover without removing agency). AI is specifically valuable here because scaffolding agency requires balancing two competing demands: enough structure that students don't flounder, and enough freedom that the choices are genuine — and this balance point is different for every class, every subject, and every task.
Evidence Foundation
Zimmerman (2002) established that self-regulation — the capacity to direct one's own learning — is developed through explicit teaching and gradual release. Students don't become self-directed by being given freedom; they become self-directed by being taught the skills of self-direction and practising them in increasingly open contexts. Deci & Ryan (2000) demonstrated that autonomy — the sense that one's actions are self-endorsed — is a basic psychological need that, when satisfied, enhances intrinsic motivation and deeper learning. However, autonomy requires SUPPORT, not just FREEDOM. Autonomy support means providing rationale, acknowledging the student's perspective, and offering meaningful choice — not removing all structure. Reeve & Tseng (2011) identified agency as a fourth dimension of student engagement (alongside behavioural, emotional, and cognitive engagement), showing that students who exercise agency — who contribute to the learning process rather than passively receiving it — show deeper engagement and better outcomes. Manyukhina & Wyse (2019) argued that learner agency must be understood within curriculum structures — agency doesn't mean "students choose everything" but that students have genuine decision-making power within a purposeful learning framework. Mercer (2011) showed that agency is not a fixed trait but a dynamic system influenced by context, confidence, prior experience, and the specific demands of the task.
Input Schema
The teacher must provide:
- Current task: The activity where agency will be scaffolded. e.g. "Year 9 history essay on the causes of WW1" / "Year 7 science investigation into plant growth" / "Year 10 English literature coursework"
- Student level: Year group. e.g. "Year 9"
- Current agency level: Where students are now. e.g. "Very dependent — they wait for the teacher to tell them exactly what to do at every step" / "Some independence — they can work through a task but don't make choices about how to approach it" / "Moderate — they can choose between options but struggle with open-ended tasks"
Optional (injected by context engine if available):
- Subject area: The curriculum subject
More from garethmanning/claude-education-skills
intelligent-tutoring-dialogue-designer
Script a multi-turn tutoring dialogue with branching responses for anticipated student difficulties. Use when designing AI tutors, chatbot interactions, or structured one-to-one support scripts.
15scaffolded-task-modifier
Modify a classroom task with language scaffolds that preserve cognitive demand for EAL learners. Use when adapting existing tasks for students at different English proficiency levels.
14experiential-learning-cycle-designer
Structure a direct experience into a full learning cycle with concrete experience, reflection, and conceptual transfer. Use when planning field trips, simulations, or practical tasks.
14gap-analysis-from-student-work
Analyse student work against criteria to identify specific gaps between current performance and learning objectives. Use when reviewing submissions, planning feedback, or diagnosing learning needs.
13backwards-design-unit-planner
Plan a unit using backwards design from desired outcomes through assessment evidence to learning activities. Use when starting a new unit or redesigning an existing one from standards.
13dual-coding-designer
Design a visual complement to verbal content using dual coding principles for stronger encoding. Use when creating slides, diagrams, posters, or visual explanations of complex concepts.
12