菜单
Use before claiming a GitHub, public template, or release-page update is complete, especially after version bumps, tags, GitHub Releases, README badges, About/sidebar text, topics, links, or public onboarding changes.
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
| name | release-surface-verification |
| description | Use before claiming a GitHub, public template, or release-page update is complete, especially after version bumps, tags, GitHub Releases, README badges, About/sidebar text, topics, links, or public onboarding changes. |
Use this skill whenever the task affects what another person sees on GitHub or another public project surface.
Prevent false completion where the source layer changed but the user-visible surface was not verified.
The source layer includes local files, commits, pushed branches, tags, and release notes in the working tree.
The visible surface includes the GitHub repository page, About sidebar, topics, latest-release panel, release page, rendered README, badges, documentation links, and any browser-rendered setup instructions.
Before saying the public update is complete, verify both layers:
Latest release points to the expected versionTO VERIFY with the exact surfaceUse the GitHub connector, GitHub CLI, or browser verification when available. If no live GitHub check is available, report the limitation clearly and provide the exact manual checks for the user.
Release surface verification:
- Source layer:
- GitHub release page:
- Sidebar latest release:
- About/topics:
- Rendered README/docs:
- Links:
- Privacy/public boundary:
- Verdict: PASS / PARTIAL / BLOCKED
- Remaining manual checks:
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.