Construction Video Prompt Engineering
Generate copy-ready English and Chinese positive/negative prompts for engineering video clips after identifying the clip type and requested output frame size. First/last frame files are optional and are normally supplied later to the video model; use this skill for construction actions, viewpoint transitions, static showcases, stage boundaries, object continuity, camera stability, action direction, and repair of observed failures. Do not use for generic cinematic prompts, frame creation, video generation, or full video editing.
Install
npx skills add XuJinghao221/construction-video-prompt-skill --skill construction-video-prompt-engineeringgit clone --depth 1 https://github.com/XuJinghao221/construction-video-prompt-skill.git /tmp/construction-video-prompt-skill
mkdir -p ~/.claude/skills
cp -r /tmp/construction-video-prompt-skill/. ~/.claude/skills/construction-video-prompt-engineeringPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Construction Video Prompt Engineering ## Purpose Turn a user's description of one engineering video clip into copy-ready prompt text. The normal input is text only: the user identifies the clip type, gives the requested output frame size, describes the construction stage or subject, and explains the action or viewing effect they want. By default, write the prompt so the user can later upload corresponding first and last frames to the target video model. Missing frame files are never a prerequisite for ordinary prompt generation. For ordinary prompt generation, `clip_type` and `frame_size` are required inputs. The supported clip types are: - `construction_action`: the construction state changes because of one visible construction operation. - `viewpoint_transition`: the camera or viewpoint changes while the construction state remains unchanged. - `static_showcase`: the subject is presented from a stable view without a construction-state change or deliberate camera move. This v0.1 release covers description-first prompt authoring and focused failure repair. Frame-aware refinement, historical case reconstruction, and QA are optional modes used only when the relevant materials are supplied or explicitly requested. The skill writes instructions; it does not create frames, generate video, execute a paid cloud job, inspect an unattached media file, certify engineering compliance, or guarantee a model result. ## Use This Skill When
Details
- Skill name
construction-video-prompt-engineering- Repository
- XuJinghao221/construction-video-prompt-skill
- License
- MIT
- Repo updated
- 15 September 2026
FAQ
What does the Construction Video Prompt Engineering skill do?
Generate copy-ready English and Chinese positive/negative prompts for engineering video clips after identifying the clip type and requested output frame size. First/last frame files are optional and are normally supplied later to the video model; use this skill for construction actions, viewpoint transitions, static showcases, stage boundaries, object continuity, camera stability, action direction, and repair of observed failures. Do not use for generic cinematic prompts, frame creation, video generation, or full video editing.
How do I install the Construction Video Prompt Engineering skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add XuJinghao221/construction-video-prompt-skill --skill construction-video-prompt-engineering. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Construction Video Prompt Engineering popular?
It lives in XuJinghao221/construction-video-prompt-skill, which has 5 GitHub stars and 0 forks.
Related skills
Demo Video
5surajshetty3416/demo-video-skill
Produce a polished, ScreenStudio-style 60fps product demo video of a web app with a tiny, dependency-light pipeline — Playwright frame capture + a multiprocess Pillow compositor streaming into ffmpeg (no Node/Remotion). Drives the app one step per frame so playback is true 60fps regardless of capture speed, then renders a gradient background, a rounded window with a soft shadow, a crisp vector cursor, click pulses, keyboard-shortcut keycaps, and a cinematic push-in that scales the whole window and eases out at the end; HD=1 re-renders the same capture at retina resolution. Also ingests hand-dr
Cherina Pod
5realchendahuang/cherina-pod
Turn any podcast episode into a listening-practice lesson for language learners — an offline player page (line-by-line playback, loop, blind listening, word-by-word highlight), a printable bilingual handout, and key-phrase notes. Default is English audio with Chinese translation; Chinese audio with English translation also works. Use when the user wants to practise listening with a podcast, e.g. "把这期播客做成精听课", "用播客练听力", "做一份听力讲义", "播客精听", "make a listening lesson from this podcast".
Drawing Review Cn
5Wonggeff/drawing-review-cn
中国建筑工程施工图图纸会审（图纸自审）专家技能。用于对一整套施工图（建筑/结构/给排水/电气/ 暖通/智能化/室内装修/景观园林/海绵/基坑支护/亮化等专业）开展系统性自审，产出可直接上会签认的 图纸会审问题清单与记录表。 适用场景： (1) 用户说“帮我做图纸会审”“图纸自审”“审图”“挑图纸问题”“出问题清单”“会审记录” (2) 一次性给出一个装满施工图的文件夹（PDF/DWG），要求找出各专业图纸问题 (3) 要求列出“哪个专业、哪张图纸、哪个部位、什么问题、怎么解决”并做跨专业比较 (4) 需要生成图纸会审记录表（Word/Excel，含设计回复/处理结果/闭环状态列） (5) 需要核查图纸集完整性：图纸目录、图号体系、版本冲突、签章有效性 (6) 仿古建筑 / 木结构 / 文旅 / 文物遗址类项目的专项会审
Bulkcut Coach
5Juggernaut0825/bulkcut-coach
Fitness and diet tracking tool. Use when the user wants to analyze food photos for calories, log workouts, calculate metabolism (BMR/TDEE), get daily calorie summaries, or generate training/diet plans. Invoked with /bulkcut-coach.
Grok Video Editing
5AlizayAyesha/grok-video-editing-skill
Record a product demo on a Linux desktop, cut it into feature clips, and render an on-brand 1080p motion-graphics promo video entirely with code (ffmpeg + HTML Canvas + headless Chromium via Playwright + a procedural audio mix). Use when asked to make a product demo, launch video, or social promo themed to a website's colors and fonts.
AI Image to Vector Redesign
5hxr223/ai-image-to-vector-redesign
Finish flattened GPT Image 2 design outputs by rebuilding text and layout into sharp, editable SVG/PDF/high-resolution PNG deliverables. Use for AI-generated posters, long images, infographics, flyers, social cards, and marketing graphics when upscaling or tracing would not fix blurry text or layout artifacts.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.