ai-agent-design-spec

Estrelas8

Forks0

Atualizado24 de julho de 2026 às 17:47

Turn dissertation evidence into an AI agent design specification for supporting active learning implementation, including user scenarios, functions, interaction flow, boundaries, failure modes, and design rationale.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

JonasLee12

JonasLee12/research-agent-starter-kit

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Professores do ensino superior, todos os outrosEducação e Biblioteconomia·SOC 25-1199

SKILL.md

readonly

name	ai-agent-design-spec
description	Turn dissertation evidence into an AI agent design specification for supporting active learning implementation, including user scenarios, functions, interaction flow, boundaries, failure modes, and design rationale.

AI Agent Design Spec

Use when the user asks to design, refine, evaluate, or document the AI agent proposed in the dissertation.

Inputs

Look for:

DISSERTATION_BRIEF.md
teacher interview findings, concept-card responses, design-elicitation outputs, or confirmed co-design outputs
teacher interview/workshop findings
research-wiki/DESIGN_RATIONALE.md
research-wiki/FINDINGS_INDEX.md
chapter drafts about design implications

Workflow

Identify the teaching problem the agent supports.
Define primary users:
- university teachers
- teaching assistants or learning designers, if relevant
- students only if the dissertation explicitly includes them
Map teacher needs and concerns to agent capabilities.
Specify:
- user scenarios
- agent goals and non-goals
- core functions
- interaction flow
- inputs and outputs
- human control points
- failure modes and recovery
- evidence source for each design decision
Separate evidence-backed requirements from speculative features.
Produce a design rationale that links back to active learning and adoption conditions.

Output

Create or update:

design-specs/AI_AGENT_DESIGN_SPEC.md
design-specs/USER_SCENARIOS.md
design-specs/DESIGN_RATIONALE.md

Required Sections

Use this structure unless the user asks otherwise:

Purpose
Intended users
Teaching scenarios
Core capabilities
Boundaries and non-goals
Interaction flow
Teacher control and override points
Data and privacy assumptions
Failure modes
Evidence-to-design traceability table

Guardrails

Read ../dissertation-shared/references/privacy-and-ethics.md when participant data is involved. Do not claim the agent is effective unless evaluation evidence exists.

Mais deste repositório

mesmo repositório

active-learning-design-support

JonasLee12/research-agent-starter-kit

Design and review active learning implementation support for university teachers, including classroom activity structures, preparation workflow, student participation, assessment alignment, and AI-agent support points.

2026-07-248

codesign-output-synthesis

JonasLee12/research-agent-starter-kit

Synthesize confirmed co-design, design-elicitation, prototype-feedback, or participant-generated design outputs into requirements, design principles, prototype changes, participant contribution maps, and design decision logs.

2026-07-248

dissertation-figure-spec

JonasLee12/research-agent-starter-kit

Design specifications for dissertation figures such as conceptual frameworks, concept-card/interview process diagrams, AI-agent workflow diagrams, adoption-condition models, and findings maps.

2026-07-248

dissertation-research-wiki

JonasLee12/research-agent-starter-kit

Maintain a lightweight dissertation research wiki with project memory, literature notes, methodology decisions, supervisor feedback, design rationale, and open questions.

2026-07-248

prototype-evaluation-audit

JonasLee12/research-agent-starter-kit

Audit an AI agent prototype or design concept for usability, pedagogical fit, teacher feedback, active learning support, evidence quality, and next design iterations.

2026-07-248

teacher-adoption-modeling

JonasLee12/research-agent-starter-kit

Build and audit a teacher adoption conditions model for an AI agent supporting active learning, distinguishing perceptions, concerns, barriers, enablers, institutional conditions, and design implications.

2026-07-248

name	ai-agent-design-spec
description	Turn dissertation evidence into an AI agent design specification for supporting active learning implementation, including user scenarios, functions, interaction flow, boundaries, failure modes, and design rationale.

AI Agent Design Spec

Use when the user asks to design, refine, evaluate, or document the AI agent proposed in the dissertation.

Inputs

Look for:

DISSERTATION_BRIEF.md
teacher interview findings, concept-card responses, design-elicitation outputs, or confirmed co-design outputs
teacher interview/workshop findings
research-wiki/DESIGN_RATIONALE.md
research-wiki/FINDINGS_INDEX.md
chapter drafts about design implications

Workflow

Identify the teaching problem the agent supports.
Define primary users:
- university teachers
- teaching assistants or learning designers, if relevant
- students only if the dissertation explicitly includes them
Map teacher needs and concerns to agent capabilities.
Specify:
- user scenarios
- agent goals and non-goals
- core functions
- interaction flow
- inputs and outputs
- human control points
- failure modes and recovery
- evidence source for each design decision
Separate evidence-backed requirements from speculative features.
Produce a design rationale that links back to active learning and adoption conditions.

Output

Create or update:

design-specs/AI_AGENT_DESIGN_SPEC.md
design-specs/USER_SCENARIOS.md
design-specs/DESIGN_RATIONALE.md

Required Sections

Use this structure unless the user asks otherwise:

Purpose
Intended users
Teaching scenarios
Core capabilities
Boundaries and non-goals
Interaction flow
Teacher control and override points
Data and privacy assumptions
Failure modes
Evidence-to-design traceability table

Guardrails

Read ../dissertation-shared/references/privacy-and-ethics.md when participant data is involved. Do not claim the agent is effective unless evaluation evidence exists.