Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add WiseWong6/wise-skills --skill build-landmark-model-lightinggit clone --depth 1 https://github.com/WiseWong6/wise-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wisewong6/wise-skills/build-landmark-model-lighting)<a href="https://agentmods.dev/skills/wisewong6/wise-skills/build-landmark-model-lighting"><img src="https://agentmods.dev/badge/skills/wisewong6/wise-skills/build-landmark-model-lighting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wisewong6/wise-skills/build-landmark-model-lighting"><img src="https://agentmods.dev/badge/skills/wisewong6/wise-skills/build-landmark-model-lighting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00149 | $0.03042 |
| Opus 5 | $0.00075 | $0.01521 |
| Sonnet 5 | $0.00030 | $0.00608 |
| Haiku 4.5 | $0.00015 | $0.00304 |
Grade A, and why
build-landmark-model-lighting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
地标建模与光效
核心原则
- 严格按“调研素材 → 冻结简报 → 内置生图 → 白模建模 → 白模校对 → 材质与光效 → 机器候选 → 按需双源终验”推进。
- 让真实资料决定身份、尺度、轮廓、结构和隐藏面；只让生成图决定构图、材质气质和光效语言。
- 先修主体，再修展示。不得用材质、发光、镜头或控制壳掩盖比例和结构错误。
- 每个模型至少实现一种合适光效；内置三类能力不等于每个主体强制交付三类。
- 把交付分为
candidate-ready与visual-approved：前者证明当前字节、结构和运行时可复现，后者才证明视觉身份已由用户或明确授权的 Reviewer 接受。不得把前者写成后者。 - 默认
review_mode=user-self-check：运行必要的自动化检查，交付绝对路径、URL 和人工验收动作；除非用户明确要求截图/视觉验收，不主动生成成套截图或做耗时主观复核。 - 任何
passed都必须绑定可解析的真实 GLB/图片、当前源码/运行时哈希、本轮报告和 HTTP 返回字节；自报布尔值、HTTP 200、单张截图或旧报告都不是证据。 - 把时间连续性当作独立门禁：
0 / mid / 1单帧正确不等于动效正确；暂停、回放、模式切换、后台恢复和画廊交换都必须通过连续帧验收。
项目规则优先级
- 进入工作区后先读取当前目录及其父级适用的
AGENTS.md；它是项目交付契约，优先级高于本 Skill 的通用默认值。 - 在
form-atlas中，根目录AGENTS.md对展示壳、模型、材质、光效和验收拥有最终解释权。本 Skill 的引用文件必须与其保持一致；发现冲突时先按AGENTS.md执行并修正文档，不得自行选择较宽松的规则。 form-atlas的硬约束包括：loading 位于当前 3D 视口正中心且同一视口最多一个可见实例；loading 只在资产指纹/结构校验和真实首帧完成后隐藏，错误态先隐藏 loading；播放条固定底部居中；静态页与 React 页使用data-landmark-loading、.landmark-loading-ring和data-landmark-playback；静态页优先复用public/white-models/shared/presentation-shell.css，React 页复用app/globals.css；桌面1440×900与移动390×844都要验收。- 集成画廊不得重复注入 loading，也不得留下旧 iframe/WebGL 残影。平安金融中心按项目契约交付
color / build / edge-color三种模式，build主体动画为 4.8 秒。 - 保护已有未提交工作，只修改当前地标或共用展示壳；不得用一个地标的修复覆盖另一个地标的模型、材料或动效实现。
开始前
- 检查目标工作区的
AGENTS.md、Git 状态、已有 3D 入口、依赖和等效运行进程。 - 记录任务开始时间、目标版本、允许范围、禁止事项、验证方式、视觉复核模式和停止条件。默认视觉复核模式为
user-self-check。 - 保护用户未提交改动。只修改任务相关目录；没有现有 3D 栈时才创建独立 Node ESM + Three.js 工程。
- 使用下面的命令初始化交付合同。不得用
--force或覆盖已有合同：
python3 <skill-dir>/scripts/init_case.py \
--root <case-root> \
--subject "<建筑名称>" \
--slug <subject-slug> \
--effect auto \
--review-mode user-self-check
完整阶段门禁和数据合同见 workflow.md。
在 form-atlas 中，--effect auto 只用于初始化；平安金融中心进入严格交付前必须将 selected_effects 冻结为 color / build / edge-color，不得以 auto 作为最终交付值。
1. 调研并冻结参考
- 先登记用户提供的图片、视频、图纸、网页、GLB 或尺寸。
- 对真实建筑补齐
front / back / left / right / roof / ground-contact / three-quarter；优先业主、建筑师、工程团队、政府和权威档案。 - 为每个来源记录 ID、机构、日期、定位信息、用途、视角、可信度、使用边界、本地路径和 SHA-256（如有本地文件）。不要把第三方图片打包进交付，除非授权明确。
- 冻结
ReferenceBundle和ModelBrief。尺寸、主体版本、地标特征或关键结构证据不足时停止，不得用生图补造事实。
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 395 B
- assets/case-template/brief/model-brief.json 1.5 KB
- assets/case-template/case-manifest.json 699 B
- assets/case-template/direction/direction-set.json 268 B
- assets/case-template/qa/comparison-report.json 330 B
- assets/case-template/references/reference-bundle.json 205 B
- assets/case-template/reports/delivery-manifest.json 1.2 KB
- assets/case-template/runtime/acceptance-contract.js 2.4 KB runs code
- LICENSE 1.0 KB
- README.md 1.9 KB
- references/acceptance.md 12 KB
- references/evidence-integrity.md 4.1 KB
- references/motion-stability.md 9.5 KB
- references/presentation-shell.md 2.5 KB
- references/visual-system.md 8.9 KB
- references/workflow.md 9.5 KB
- scripts/init_case.py 7.5 KB runs code
- scripts/seal_evidence.py 14 KB runs code
- scripts/validate_case.py 57 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 114 lines · 149 tokens per session scan A 3d3168510ab2
build-landmark-model-lighting is a skill published in the GitHub repository WiseWong6/wise-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 149 tokens to every session and 3,042 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…