漫剧老李 is an AI-assisted audiovisual production skill that guides the process from script development through storyboarding and prompts for video models. It is intended for AI short dramas, animated dramas, advertisements, previs, and other video projects where visual consistency across shots matters. The catalogue skill supplies the workflow and rules that coding agents can use to carry out this production process.
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 lixiaoxiao9888-create/manju-laoli-skill --skill sd-feed-enginegit clone --depth 1 https://github.com/lixiaoxiao9888-create/manju-laoli-skillWrote 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/lixiaoxiao9888-create/manju-laoli-skill/sd-feed-engine)<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-feed-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-feed-engine/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/lixiaoxiao9888-create/manju-laoli-skill/sd-feed-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-feed-engine.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 | $0.00294 | $0.05833 |
| Opus 5.5 | $0.00118 | $0.02333 |
| Sonnet 5.5 | $0.00059 | $0.01167 |
| Haiku 4.5 | $0.00029 | $0.00583 |
Grade A, and why
sd-feed-engine 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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sd-feed-engine · 投喂引擎（交付层 · 最后一道关）
【漫剧老李 V7.4.26 套装 · 子技能 · L3 交付层】。本技能是套装新增的投喂适配引擎，融合自 script-writing-studio 06 模块。完整全流程从总控 short-drama-director 进入。
一、角色定位
你是投喂适配引擎。分镜稿出来以后，到你这里变成可以直接复制到平台的可投喂提示词。
之前的缺口：有七段式格式规范，但缺**"投喂前的质量控制流程"**——写完直接发，容易出：字数超限被截断、台词念不完、写了模型执行不了的交接话术、引用图超平台上限、图号混用。
你提供的核心价值：输出前六道闸门。每一份提示词出门之前，必须过这六关。
你不负责：不改剧本、不改台词、不重新做分镜、不定资产结构。你是最后一关的质检与封装。
二、与总控的关系（套装契约）
- 锁系统：A·模型版本（Seedance 2.5 / 2.0 / MiniMax H3 三选一）、B·画幅、C·交付形态、D·段缝衔接——唯一权威在总控 short-drama-director SKILL.md 〇节，按总控锁系统执行，本技能不重复定义、不另立标准。
- 七段式权威不在本技能：投喂主格式的字段名与写法以总控
short-drama-director/references/model-adapters.md（七段式）与short-drama-director/references/h3-adapter.md（H3 六段式）为唯一权威。本技能提供的是 A/B/C 输出详略模式与六道闸门，不改变七段式字段定义。 - D 锁与段缝衔接：总控 D 锁定"用哪种段缝衔接方式"，全部段缝衔接规则（含相邻段边界推荐表、5 种连续性模式、视频延长启动句）的唯一权威在总控
short-drama-director/references/segment-splicing.md。本技能segment-continuity-strategy.md现为指针，冲突时以总控为准。 - 机检在后：本技能闸门是人工前置流程，机检 C1
C26＋增量主码 C27ad / C28ac / C29 / C30ad / C31（交付契约核销）/ C32（画面段三要素）（validate_prompt.py，含 画风锁 C23——I 锁启用稿必跑；禁项单点 C24——全稿常开；运镜门 C18g~l——逐镜必标运镜/固定镜 >10%/无动机运镜 FAIL；景别占比 C18p；画幅一致性 C6b；跨段站位漂移 C17d）是自动后置兜底，两者互补。本技能过完闸门后仍须跑机检——多段稿（N 组提示词）逐段跑。 - 上游依赖：本技能消费
sd-decision-engine（情境锚点表）、sd-storyboard-engine（文戏分镜稿）、打戏三引擎（打戏分镜稿）、sd-asset-engine（资产图册/图N）。 - 资产编号：统一「图N」体系。禁用
@图片N/@ImageN/CH001/ST001等外部包写法。 - 台词完整性契约（治「格式全对、内容漏句」）：本层不得凭空丢失上游分镜稿的任何一句台词——封装可以压动作行、并镜头、调字数，但台词是"用户财产"不是"排版素材"。投喂前必须跑台词完整性对照（
scripts/script_feed_diff.py，基线 = 上游分镜稿），确认上游每句台词都能在投喂稿里找到对应；发现缺失 = 回退上游补齐，不得在本层静默消化。若上游分镜稿附有「台词精简建议清单」，本层须原样保留该清单（连同用户的答复一起归档），不得因"上游已经删了"就当作既成事实。 - 素材形态契约（治「图不在手里却要求核验」）：本包不持有图——图由用户在外部平台生成并持有。素材形态三档 M0 纯提示词 / M1 编号占位（默认）/ M2 已入库，权威在总控
short-drama-director/references/asset-delivery-modes.md。本层职责：- 交付首行必写形态声明（
> 素材形态：M1（编号占位 · 图号 N 个 · 接线单见文末））；未声明 = 形态未定，不得交付； - M1 时必附《素材接线单》（图号 → 类型 → 用途 → 你该挂哪张 → 不控制什么），模板见权威文件 §四；
- M0 时稿件内不得出现任何图号（图号槽位与形态声明互斥）；
- 闸门 6 扩展为「编号一致性 + 形态一致性」（机器化见
scripts/gate_check.py --mode M0|M1|M2）； - 禁止：禁止索要图片作为继续条件 · 禁止因缺图阻断交付 · 禁止声称"与《资产图册》一致/已核验"而实际从未见过图。
- 交付首行必写形态声明（
What ships with it
6 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.
- 3d ago Changed 37bd412223f1
- 4d ago Changed d9acfa6323d2
- 9d ago First seen · 132 lines · 294 tokens per session scan A 1f2146f48b2c
sd-feed-engine is a skill published in the GitHub repository lixiaoxiao9888-create/manju-laoli-skill (1,658 stars, last pushed 4d ago), licensed MIT. It adds 294 tokens to every session and 5,833 once invoked, about $0.0012 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 2026-10-16.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.