메뉴
Use before substantive formal research drafting and again before delivery to check concrete integrity risks such as prompt residue, placeholders, fake or unverified references, unsupported claims, unresolved compliance requirements, and AI-use disclosure boundaries.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
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.
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.
Design specifications for dissertation figures such as conceptual frameworks, concept-card/interview process diagrams, AI-agent workflow diagrams, adoption-condition models, and findings maps.
Maintain a lightweight dissertation research wiki with project memory, literature notes, methodology decisions, supervisor feedback, design rationale, and open questions.
Audit an AI agent prototype or design concept for usability, pedagogical fit, teacher feedback, active learning support, evidence quality, and next design iterations.
| name | academic-integrity-preflight |
| description | Use before substantive formal research drafting and again before delivery to check concrete integrity risks such as prompt residue, placeholders, fake or unverified references, unsupported claims, unresolved compliance requirements, and AI-use disclosure boundaries. |
Use this skill for proposal, manuscript, report, methodology, ethics/IRB/compliance-facing, supervisor/PI/client/reviewer-facing, submission-facing, or citation-heavy research artifacts.
Catch concrete integrity and submission-readiness risks before style polishing or final delivery.
This is not an AI detector and must not be used to judge whether text was written by AI from style alone.
Run twice for formal-writing pipelines:
Look for:
TO CONFIRM, SOURCE TO ADD, NEEDS VERIFICATION, xxx, TODO, bracketed missing fields, or template instructions left in user-facing text;Use when checking a Markdown or text artifact:
python3 scripts/academic_integrity_preflight.py --target <path> --stage early
python3 scripts/academic_integrity_preflight.py --target <path> --stage final --strict
Use --requires-ethics, --requires-rubric, or --citation-heavy when the task type requires those gates.
HOLD: prompt residue, user-facing placeholders, fake or unverified reference markers, unresolved compliance blockers, unverified official requirements, or unsupported major claims.WARN: low-risk wording concern, non-blocking reminder, or missing optional evidence.PASS: no concrete integrity issue found by this preflight.If the preflight returns HOLD, do not describe the artifact as usable, approved, submission-ready, publication-ready, or client-ready. Fix the issue, downgrade the claim, mark TO CONFIRM, or record an explicit user risk override where the workflow allows it.
authorial-voice-integrity.