菜单
Use when a user asks to make research writing sound less AI-like, more human, more authorial, less generic, or asks about AI-writing, AIGC, detector scores, disclosure, de-AI, humanising, or lowering AI rate; improves academic voice and integrity without detector-evasion.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | authorial-voice-integrity |
| description | Use when a user asks to make research writing sound less AI-like, more human, more authorial, less generic, or asks about AI-writing, AIGC, detector scores, disclosure, de-AI, humanising, or lowering AI rate; improves academic voice and integrity without detector-evasion. |
Use this skill for academic or professional writing requests framed as:
de-AI, humanise, make it less ChatGPT, lower AI rate, AIGC, AI detector;Reframe detector-focused requests into academic voice, argument quality, and integrity.
Allowed:
Not allowed:
For quick chat-level style help:
For formal academic or professional artifacts:
academic-integrity-preflight.cognitive-frameworks and academic-self-review-loop when argument quality matters.python3 scripts/authorial_voice_scan.py --target path/to/draft.md
Use --strict if a detector-evasion or disclosure-risk request should block the workflow.
uk-academic-writing-style or the confirmed project style.style-memory-and-revision-gate before delivery.scripts/authorial_voice_scan.py is not an AI detector. It flags wording and request-pattern risks:
A HOLD result means the workflow should be reframed or checked before delivery. It does not mean the writing is AI-generated.
academic-integrity-preflight.dissertation-citation-audit.academic-self-review-loop with research-wiki/WRITING_QUALITY_RUBRIC.md.material-passport, formal-delivery-guard, and document-quality gates.