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 62656456/ai-film-skills --skill prop-assetgit clone --depth 1 https://github.com/62656456/ai-film-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/62656456/ai-film-skills/prop-asset)<a href="https://agentmods.dev/skills/62656456/ai-film-skills/prop-asset"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/prop-asset/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/62656456/ai-film-skills/prop-asset"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/prop-asset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00109 | $0.05353 |
| Opus 5.5 | $0.00044 | $0.02141 |
| Sonnet 5.5 | $0.00022 | $0.01071 |
| Haiku 4.5 | $0.00011 | $0.00535 |
Grade A, and why
prop-asset 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 18d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
道具资产参考图生成预设
当前包已经包含全部运行规则、参数依据和质量门;不使用未经用户确认的人脸或生物特征。
0. 加载规则与映射表
先确定本次媒介与改动范围。首次建立或重设计资产按下方剧本依据、描述、状态、材质/光影/几何和适用模板完成;局部修改只执行受影响部分,编号/文件查询直接回答。同一上下文已完整读取且未变的材料复用,不为改一处重新跑全流程。资产编号:P01–P99,已确认编号不得复用。
| 节 | 独立输出 | 用途 |
|---|---|---|
| 1–5 | 资产描述、锁定规则 | 确定外观与状态 |
| 6–7 | 平台任务与提示词字段 | 直接生成参考图 |
| 8–9 | 验收和防崩 | 独立质量检查 |
| 10 | JSON 合同 | 供后续制作直接读取 |
| 11 | 类型适配字段 | 注入成片提示词的对应段落 |
剧本先行与设计依据
首次建立或重新设定资产且用户提供剧本时,通读所提供的完整正文,理解世界规则、身份关系、剧情因果和时间线,再回到资产出现的场次设计。长剧本可分段读完并留简短连续性记录。局部修订复用本轮已读且未变的依据,只补读受影响原文、当前场次与必要前后状态;跨上下文或源文本变化时核对实际来源。不能只搜名称或读摘要就声称通读;只有片段时说明覆盖范围,未给剧本时依据当前描述设计。
内部保留简短设计依据:正文来源与阅读范围、相关场次、故事风格与成像方式、已确认事实、设计推定、关键未知。设计要能解释“为什么这个资产在此时此地是这个样子”;后文信息可帮助理解时代、身份与伏笔,但不能把后续损坏、受伤、天气或揭示结果提前带入当前场次。
用户与当前项目已经明确的画风优先;未指定成像方式时默认摄影写实,以可信结构、材质和光影呈现。悬疑、喜剧、奇幻等故事类型不自动等于某种画风。未提供细节或参考图时,从剧本与用途主动提出合理设计;影响剧情、身份、既有锁定事实的关键未知才需确认。一般颜色、材料、陈设、维护与使用细节可作有依据的设计推定,不一律退回待确认;推定不能冒充原文或用户已确认事实。
交付与成像模式
按用户点名的结果选择,不自动扩展为整套图:
- 提示词/设计说明:交付当前请求的完整提示词、必要锁定信息与资产合同;尚未生成的参考图用空列表并标为计划,不填写虚构图片路径或声称图片通过。
- 实际参考图:用户要求出图且有可用能力时生成所需图片;单图先交单图,整套资产请求或明确跨视角验收需求才扩展角度。实际看图后记录检查结果,用户批准前保持 pending_review。
- 诊断/局部修改:围绕给定图或提示词指出可见问题、原因假设和对应修正;保留未点名的身份、风格与状态,不默认重做整套资产。
依第0节确定成像方式(无指定时默认摄影写实),再按本包 电影画面关系判断 设计画面关系与负向。新设计、整体改写或整体诊断读取此参考;局部修订仅补读相关判断,已读且未变时复用;编号/文件查询不必加载。模板中的多格、人物尺度、标准布光和材质纹理均按用途选取,不因模板固定成套、写实或宏大。
新设计、整体重设计或完整设定板任务读取 道具造型与设定表达:先完成形制与设计意图,再选解释它所需的视图。已有明确外观只做局部派生时直接继承基准,补读对应方法,不重开造型。
道具资产的重点是整体设定与能解释设计的细节。整套设定任务按需要组织整体外形、区别正反/侧面的视图,以及关键结构和材质的局部图;避免只有一张漂亮摆拍,也避免每个物件都机械套相同多视图。用户只要一张时,可按用途交整体图或一张设定板;用户指定单视角、单个局部或不拼图时严格遵从。视图数量由需要回答的设计问题决定,不固定格数,不自动扩成多张。
设定板的每个局部都对应同一件道具上的明确位置与当前状态,整体/视角图用于定位,局部用于解释构造。完整设定图可按表达需要使用简短部位名、引线、材料说明与有依据的比例/尺寸,不必等用户逐项点名;用户明确无字时不添加。纯外观参考和剧情画面不自动叠加说明。精确尺寸无依据时标为设计推定或留空,工程性能与可制造性不因生成图存在而成立。
1. 描述维度表
设计依据按用途覆盖:类型、用途、时代、使用者、形体比例、尺寸、结构/操作关系、材质、颜色、重量感、状态/磨损、必要视面、文字、持有人与朝向;不逐字段堆进提示词。先决定与使用方式和世界美术一致的轮廓、体块及辨识特征,再细化接口与新旧程度。磨损有使用位置与原因,不给所有道具统一做旧,不加入尚未发生的损坏或泄露后续线索。
规则:按第0节区分剧本事实、设计推定与关键未知;只把用户或剧本已确认的维度写入 locked_features,待审设计不冒充已锁定。描述按从整体到局部、从外观到材质、从静态到状态组织,并对应当前剧情节点。
What ships with it
4 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.
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.
- 18d ago Changed · +33 lines · +22 tokens per session 86647c6045aa
- 28d ago Changed 8fc378d17822
- 1mo ago Changed · +13 lines 598730d035a9
- 1mo ago Changed · +10 lines 470bd06279ee
- 1mo ago Changed · +10 tokens per session 3dd4bce13548
- 1mo ago First seen · 164 lines · 77 tokens per session scan A 0fd050392c65
prop-asset is a skill published in the GitHub repository 62656456/ai-film-skills (92 stars, last pushed 9d ago), licensed Apache-2.0. It adds 109 tokens to every session and 5,353 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML…
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
miora-video-studio
A video-generation workflow for the Miora and WorkBuddy tools. It checks whether a video was really created by inspecting the saved file, rather than trusting a task response.
travel-skill
A production guide for realistic travel-promotion videos that combine authorised real footage with AI-generated shots.
action-fight-prompt
A guide for writing prompts for AI-generated action and fight videos. It breaks a scene into short timed sections and describes connected movements, camera work, visual continuity, and sound effects.
travel-photo-to-video
A workflow for turning real travel photographs into a storyboard and prompts for short AI-generated video shots. It keeps the photographs' subjects and locations consistent while suggesting restrained camera movement.