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 Supreme-Ultimate/novel-to-script-team --skill art-direction-review-skillgit clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamWrote 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/supreme-ultimate/novel-to-script-team/art-direction-review-skill)<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/art-direction-review-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/art-direction-review-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/supreme-ultimate/novel-to-script-team/art-direction-review-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/art-direction-review-skill.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 | $0.00062 | $0.02395 |
| Opus 5 | $0.00031 | $0.01197 |
| Sonnet 5 | $0.00012 | $0.00479 |
| Haiku 4.5 | $0.00006 | $0.00239 |
Grade A, and why
art-direction-review-skill 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
服化道设计审核技能
必读
../../references/00-first-principles.md../../references/04-review-gates.md../../references/05-compliance-boundaries.md
技能说明
审核服化道在阶段二的设计产出,包括人物设定提示词和场景环境提示词。导演需要以批判性视角审视服化道的产出,通过逐项比对导演清单、脑内预演文生图效果、逐项评分的方式,确保提示词质量真正达标,能让用户通过文生图工具生成准确的参考图。
审核对象
outputs/{剧本名}/assets/character-prompts.md 和 outputs/{剧本名}/assets/scene-prompts.md 中本集新增内容
审核流程
第一步:建立整体理解
- 读取导演分析产出(
01-director-analysis.md)中的人物清单和场景清单 - 读取待审核的服化道设计产出
- 如有已有素材,读取了解上下文
- 明确审核立场:你的任务是找出问题,而非确认通过
第二步:逐项比对
- 对每个人物:逐个对照导演人物清单中的外观关键词,找出服化道提示词中遗漏、偏离或矛盾的地方
- 对每个场景:逐个对照导演场景清单中的光线/色调/氛围描述,找出服化道提示词中遗漏、偏离或矛盾的地方
- 同时检查讲戏本中对同一人物/场景的具体描述,确保服化道提示词没有与讲戏本冲突
第三步:脑内预演
- 对每个人物提示词:想象把这段文字丢进文生图工具(如即梦、Nano Banana Pro),生成出来的图会是什么样?
- 生成的人物形象是否与导演心中的角色一致?
- 是否有描述歧义可能导致生成结果偏离预期(如"清秀"可能被理解为女性化)?
- 参考图的布局(特写+三视图)是否能清晰展示角色全貌?
- 对每个场景提示词:想象把这段文字丢进文生图工具,生成出来的场景图是什么样?
- 生成的场景氛围是否与导演讲戏本中该场景的情绪匹配?
- 是否有关键视觉元素可能在生成中丢失(如"牌匾上的文字"在AI生成中经常出错)?
- 空间布局是否清晰,不会生成混乱的构图?
第四步:逐项评分
按照下方验收清单,对每个人物和每个场景单独评分(1-10)
第五步:输出结果
- 计算所有人物评分和场景评分的总平均分
- 平均分 ≥ 8 且无单项低于 6 → PASS
- 平均分 < 8 或任一单项低于 6 → FAIL + 问题清单
验收清单
人物造型提示词(每个人物单独评分 1-10)
评分维度:
- □ 与导演一致性:逐个对照导演人物清单中的外观关键词,提示词是否完整覆盖?有无遗漏或偏离?具体列出不一致的地方。
- □ 辨识度(脑内预演):想象生成出来的图,这个角色能否一眼与其他角色区分开?如果是配角/路人,是否有足够的视觉差异化?
- □ 描述精确性(脑内预演):提示词中是否有歧义表达,可能导致文生图工具生成偏离预期的结果?具体指出哪句话可能有歧义。
- □ 细节完整性:面部、发型、体型、服装(款式/颜色/材质)、配饰、鞋子是否都有具体描述?缺哪个列出来。
- □ 风格匹配:提示词是否明确匹配项目的视觉风格(如 3D CG)?生成结果是否会偏向其他风格?
- □ 格式可执行:布局指令(特写+三视图+白色背景)是否清晰?能否直接复制到文生图工具使用?
评分标准:
- 9-10:提示词精准,脑内预演生成效果完全符合导演预期,无需修改
- 7-8:基本到位,但有 1-2 处可能导致生成偏差的地方
- 5-6:有明显的遗漏、偏离或歧义,需要修改
- 1-4:提示词严重不足或与导演意图冲突
场景环境提示词——宫格整体评分(1-10)
说明:场景提示词采用宫格格式(≤9场景用3×3,10-12用3×4,13-16用4×4),每格一个场景。审核时先逐格检查,再整体评分。
逐格检查维度(每个格子/场景逐一检查):
- □ 与导演一致性:该格场景是否对应导演场景清单中的某个场景?光线/色调/氛围描述是否完整覆盖?有无遗漏或偏离?
- □ 氛围传达(脑内预演):想象生成出来的该格画面,氛围是否与导演讲戏本中该场景的情绪匹配?
- □ 空间清晰度(脑内预演):该格描述的空间布局是否清晰?在宫格的小尺寸内是否能看清主要元素?
- □ 关键元素完整:导演讲戏本中提到的重要视觉元素是否在该格中有体现?
宫格整体检查维度:
- □ 场景覆盖完整性:导演场景清单中的所有场景是否都在宫格中有对应格子?有无遗漏?
- □ 宫格规格正确性:场景数量与宫格规格是否匹配(≤9用3×3,10-12用3×4,13-16用4×4)?空格处理是否正确?
- □ 格间风格一致性(脑内预演):想象生成出来的整张宫格图,所有格子的视觉风格是否统一?色彩体系是否协调?会不会出现某一格风格突兀?
- □ 风格匹配:整体是否明确匹配项目的视觉风格?
- □ 格式可执行:整段提示词能否直接复制到文生图工具生成一张完整的宫格图?
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 · 156 lines · 62 tokens per session scan A 20ddca3d9817
art-direction-review-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (165 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 2,395 once invoked, about $0.0003 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.