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 liyue-aigc/outfit-director --skill skillgit clone --depth 1 https://github.com/liyue-aigc/outfit-directorWrote 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/liyue-aigc/outfit-director/skill)<a href="https://agentmods.dev/skills/liyue-aigc/outfit-director/skill"><img src="https://agentmods.dev/badge/skills/liyue-aigc/outfit-director/skill/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/liyue-aigc/outfit-director/skill"><img src="https://agentmods.dev/badge/skills/liyue-aigc/outfit-director/skill.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 | $0.00126 | $0.03872 |
| Opus 5 | $0.00063 | $0.01936 |
| Sonnet 5 | $0.00025 | $0.00774 |
| Haiku 4.5 | $0.00013 | $0.00387 |
Grade A, and why
outfit-director 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 11d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
换装导演
目标
把一次换装需求转换为彼此联动的:
- 路由判定与参数锁定
- 拼贴首帧图片提示词
- 完整视频时间轴
- 可直接复制的精简视频提示词
- 负面提示词与强制约束
图片是视频的结构母图。视频必须继承主体身份、全部造型、侧边贴图位置、画面布局与摄影质感。
工作流程
- 先执行主体路由:女性、男性、宠物或混合合集;判断复杂、涉及宠物或混合合集时读取
references/subject-routes.md。 - 再执行视频路由:卡点换装或换装舞蹈。
- 锁定用户明确给出的参数;只补全低风险缺失项。
- 需要服装方案时读取
references/parameter-presets.md。 - 需要选择或改造转场时读取
references/transition-library.md。 - 生成首帧提示词,再依据首帧结构生成视频时间轴。
- 最后执行数量、时长、贴图消失、身份一致性检查。
不要重复询问已知信息。仅在主体类别、造型方向或互相冲突的高影响参数完全无法推断时,问一个简短问题。
主体路由
按以下优先级判定:
- 用户明确指定的主体类别
- 上传参考图中清晰可见的主体
- 用户文本中的角色、性别、物种或品种
- 均缺失时默认原创中国成年女性
女性路线
- 无参考图且未指定国籍 / 族裔外观时,默认原创中国成年女性,视觉年龄 22–28 岁,自然真实的东亚面部特征。
- 明确锁定脸型、五官、肤色、妆容、眼睛、发型、发色、身材比例与整体气质。
- 不使用服装或文化符号代替族裔外观,不自动生成欧美面孔。
男性路线
- 无参考图且未指定国籍 / 族裔外观时,默认原创中国成年男性,视觉年龄 22–30 岁,自然真实的东亚面部特征。
- 明确锁定脸型、五官、肤色、胡须状态、发型、发色、体型比例与整体气质。
- 服装和动作可阳光、都市、学院、商务、运动、国风或用户指定,不套用女性妆容与姿态模板。
宠物路线
- 锁定物种、品种或混种特征、成年/幼年阶段、体型、毛色、花纹、眼睛、耳形、口鼻、尾巴和项圈等识别锚点。
- 不写国籍、族裔、妆容或人类身材比例。
- 默认保持真实动物解剖与四足运动;除非用户明确要求,不拟人化站立或舞蹈。
- 服装必须适体、安全,不遮挡眼睛、鼻子、嘴巴,不束缚颈部、胸腔、四肢与尾巴。
- 宠物“舞蹈”默认解释为节拍化转圈、抬爪、侧步、坐立、歪头等自然动作组合。
混合合集路线
- 用户明确要求女性、男性与宠物合集时,分别生成独立子方案;不得把人物身份一致性强行跨主体套用。
- 每个子方案独立执行主体锚点、首帧、时间轴和负面约束。
- 未明确要求同框时,默认分成多个独立视频,避免一条视频中主体数量和造型路由冲突。
视频模式路由
模式 K|卡点换装
触发词:卡点、点击换装、贴纸飞入、快速变装、8 秒、9 秒、10 秒。
- 时长限定 8–10 秒;用户未指定具体值时使用 9 秒。
- 默认 5 套造型:中央初始造型 + 4 个侧边造型。
- 默认固定机位,优先保证换装因果与动作连续。
- 默认加入有清晰重拍的卡点背景音乐;必要转场音效可轻量叠加。用户说“仅背景音乐”时禁止额外音效。
- 用户明确指定 3–7 套造型时可调整数量与布局,但时长仍保持 8–10 秒。
- 默认完成点(9 秒):1.35、3.05、4.85、6.85 秒;最后至少保留 1.5 秒展示最终造型。
模式 D|15 秒换装舞蹈
触发词:换装舞蹈、跳舞、舞蹈编排、dance、15 秒。
- 时长固定 15 秒。
- 造型固定正好 7 套:中央初始造型 1 套 + 左侧 3 套 + 右侧 3 套。
- 中央主体必须全身站在画面中间,双脚活动区稳定,不漂移出中心区域。
- 左侧上 / 中 / 下各放 1 个完整主体贴图;右侧上 / 中 / 下各放 1 个完整主体贴图。
- 六个侧边贴图分别穿不同服装并采用不同舞蹈关键姿势;脸、发型、体型或宠物识别锚点始终一致。
- 默认激活顺序为左上 → 右上 → 左中 → 右中 → 左下 → 右下,以保持视觉平衡。
- 默认换装完成点为 2.0、4.1、6.3、8.5、10.8、13.0 秒;13.0–15.0 秒展示最终造型并完成收尾动作。
- 每次在舞蹈动作峰值换装,连续完成六次变装;不得切成七段彼此无关的独立动作。
- 默认只使用卡点背景音乐,不加点击声、飞入声或换装音效;用户明确要求时再添加。
- 默认固定正面全身机位;可轻微呼吸式推近,但不得影响七个主体的首帧识别和中央舞蹈连续性。
当“卡点”和“舞蹈”同时出现时:若用户强调连续舞蹈或 15 秒,选择模式 D;否则选择模式 K。用户明确要求两版时分别输出,不混成一条时间轴。
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.
- 11d ago First seen · 261 lines · 126 tokens per session scan A e3aceb993cab
outfit-director is a skill published in the GitHub repository liyue-aigc/outfit-director (70 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 3,872 once invoked, about $0.0006 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.