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 yutianxiao6/openreel-studio --skill character-promptgit clone --depth 1 https://github.com/yutianxiao6/openreel-studioWrote 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/yutianxiao6/openreel-studio/character-prompt)<a href="https://agentmods.dev/skills/yutianxiao6/openreel-studio/character-prompt"><img src="https://agentmods.dev/badge/skills/yutianxiao6/openreel-studio/character-prompt/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/yutianxiao6/openreel-studio/character-prompt"><img src="https://agentmods.dev/badge/skills/yutianxiao6/openreel-studio/character-prompt.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 | $0.00075 | $0.01437 |
| Opus 5 | $0.00037 | $0.00718 |
| Sonnet 5 | $0.00015 | $0.00287 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
character-prompt 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 12d 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.
What it actually says
人物图提示词 Skill
用于主要人物 image 节点。人物图服务后续分镜、首尾帧和视频一致性,是长期可复用的角色身份锚点。输出写成纯文本 image prompt 正文,使用本项目通用的官方设定集角色视觉参考表写法。
读取素材
写人物图前读取或确认:
- 详细剧本或人物所在剧情段落。
- 角色姓名/称谓、年龄感、身份、性格气质和剧情功能。
- 脸型、五官、眼神、发型、体态、姿态和关键识别点。
- 服装轮廓、材质、颜色、配饰、武器、法器、装备和剧情关键道具。
- 项目主风格、时代背景、世界观气质、光线、色调和目标质感。
- 参考图用途:脸部、服装、装备、风格或整体角色参考。
用户提供参考图时,先看图或读取图像上下文,再把可见身份、脸、发型、服装、道具和材质写成稳定锚点。参考图是角色权威来源,人物图保持参考图里的身份和关键外观。
标准设定集写法
当用户需要视频参考、角色设定集、人物模型图、三视图/四视图、服装装备拆解或长期复用角色时,prompt 写成“官方设定集角色视觉参考表”。写入节点时直接替换花括号内容,不保留模板占位符、字段说明、代码块或 JSON 包装。
官方设定集角色视觉参考表,真人摄影级质感,纯白背景图解风排版。
角色身份:
{角色姓名/称谓},{年龄感/性别气质/身份/职业/世界观位置}。{一句话说明角色在剧情中的功能和核心气质。}
脸部与体态:
{脸型、五官比例、眼神、眉眼状态、鼻梁、嘴唇、肤质、发型、发色、体态、身高感、站姿和最重要识别点}。
三视图:
正面全身、侧面全身、背面全身,保持同一脸、同一发型、同一服装、同一装备和同一身体比例。姿态中性,轮廓清楚,方便后续分镜复用。
表情特写:
毛孔级写实面部特写,包含{与剧情相关的表情组},保持同一五官和同一身份。
服装与装备拆解:
{外套/内衬/裤装/鞋靴/盔甲/腰带/纹样/材质/磨损/缝线/金属件/织物层次}。{武器/法器/工具/饰品/关键道具}作为同一角色装备展示,结构清楚,材质可辨。
配色与材质:
色彩搭配色板:{主色、辅色、点缀色、金属/皮革/布料/木质/玉石/科技材质等}。整体色调符合{项目主风格}。
世界观边注:
边缘加入少量图解式视觉注释,说明{身份、阵营、年代、职业、装备用途或角色气质},版面简洁。
画面要求:
单人角色设定集,背景干净,轮廓清晰,无遮挡,细节锐利,高级电影美术设定稿质感。人物外观保持参考素材和剧本设定。
轻量身份锚点
只需要一个可复用人物身份锚点时,使用单人半身或全身参考图格式:
{角色姓名/称谓},{年龄感/性别气质/身份},
{脸型/五官/眼神/发型/体态/关键识别点},
{服装轮廓/材质/配饰/关键道具},
{项目主风格},{光线和色调},
单人{半身/全身}人物参考图,背景简洁,轮廓清楚,姿态稳定,用于后续分镜和视频复用。
写作标准
人物图 prompt 聚焦身份稳定性。角色设定集以中性姿态、纯白或简洁背景、三视图、表情特写、服装拆解、装备拆解和配色色板锁定角色。同一角色在全流程保持同一脸、同一发型、同一服装、同一装备和同一身体比例。
服装、武器、法器、饰品和关键道具直接影响剧情理解时,和主要人物一起写入设定集;独立道具需要更高细节时,再创建单独 image 节点。
普通人物欣赏图、写真、海报、剧照或氛围图按画面目标写背景、动作、构图和光影;设定集模板服务于后续视频一致性。
Standalone 节点推荐字段
以下字段只用于直接创建或更新 image 节点。Workflow Build Mode 只把用途、阶段和引用等业务字段写进 spec;模型、画幅、分辨率、宽高、画质和 fps 由前端运行配置提供。
fields.purpose:character_referencefields.stage:visual_referencefields.aspect_ratio:16:9fields.resolution:2560x1440fields.quality:highfields.references: 剧本 text 用context,参考图片用visual_reference
检查点
- prompt 中有角色身份、外貌、服装、道具、姿态和风格。
- 角色可被后续场景、分镜和视频稳定引用。
- 同一人物只创建需要推动剧情的主要参考图。
What ships with it
1 file 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.
- 12d ago First seen · 91 lines · 75 tokens per session scan A 12f67593a9d1
character-prompt is a skill published in the GitHub repository yutianxiao6/openreel-studio (29 stars, last pushed 25d ago), licensed MIT. It adds 75 tokens to every session and 1,437 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
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.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.