影策 is an open-source workspace for AI film and short-video production, using a freeform canvas and structured workflows to organize scripts, characters, scenes, storyboards, media assets, and generated text, images, video, and audio. It is for creators who manage audiovisual projects through local or trusted deployments, with features for task tracking, asset management, timelines, and AI-agent workflows.
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 ddcat-ai/open-ai-canvas --skill mechanicsgit clone --depth 1 https://github.com/ddcat-ai/open-ai-canvasWrote 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/ddcat-ai/open-ai-canvas/mechanics)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/mechanics"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/mechanics/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/ddcat-ai/open-ai-canvas/mechanics"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/mechanics.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 | $0.00065 | $0.03730 |
| Opus 5.5 | $0.00026 | $0.01492 |
| Sonnet 5.5 | $0.00013 | $0.00746 |
| Haiku 4.5 | $0.00006 | $0.00373 |
Grade A, and why
喜剧 Mechanics 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 28d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
喜剧机制：前提/反差/反转/包袱与幽默生成
本包由 67 张方法论重铸卡汇编重铸（卡片明细与出处见各卡 frontmatter 的 source_card / source_book）。
何时调用
当写喜剧内容或表演喜剧时调用（本包由 67 张方法论卡汇编而成，整理自《超棒喜剧这样写》、《Step by Step to Stand-Up Comedy》、《The NEW Comedy Bible (Judy Carter, 2020)》、《崔凯文集·喜剧小品卷》、《王朔作品精选（套装共6册）》）。核心能力三层：① 创作——前提/反差/反转/包袱/三叠/配方齐不齐；② 表演——act-out 把「说」变「演」、timing 与停顿、排练与临场、砸场应对、脑内自我批评；③ 职业化——整场排序、段子串联、写作纪律、喜剧人设与冒犯边界。关键触发：“这段为什么不好笑”、“写不出梗 / 素材攒了一堆没成文”、“停顿把握不好 / 观众笑时我该不该说话”、“上台就僵 / 背稿就忘”、“整场怎么排序”、“这段能不能这么写（冒犯边界）”。工位边界：本包负责喜剧创作与表演方法论；提示词语法与模型参数走影策官方市场技能，两者接力不抢戏。
本包交付什么
用户提出需求时，本包最终交付：
- 笑点结构拆解（铺垫/升级/梗）
- 桥段排序与节奏图
- 角色笑点配置
内容保真优先级
冲突时按此顺序裁决，禁止圆场：
- 用户明确指定（时长/风格/禁项/参考职责）；
- 笑点有铺垫有兑现；
- 升级沿同一逻辑递进，不跳频道；
- 风格与质感装饰。
默认决策
用户未指定时采用，并在交付前用一句话说明选了什么：
- 笑点密度：未说则三段一梗
- 角色：默认一主笑一冷面
- 禁忌：默认不用贬低型笑点
质量门槛
交付前逐项自检，任一项不过就改完再交：
- 每个梗是否有铺垫
- 升级是否沿同一逻辑
- 是否避免解释笑点（ Kill the joke ）
- 节奏是否有呼吸不连炸
包内卡片名录
cards/act-out.md— 用于把"说"的笑话变成"演"的笑话——当你写的是陈述、观众没画面、或想让笑点更立体有戏cards/act-outs-pov.md— 当用户"讲段子像念稿、观众不投入""想把讲述改成表演""不懂 scene work / 走位 / 三视角"时调用cards/act-outs-povs.md— 当用户"讲段子像念稿、观众不投入""想把讲述改成表演""不懂 scene work / 走位"时调用cards/bca-show-order.md— 当用户"整场演出怎么排序""演完不知道怎么改""想建立持续进步的闭环"时调用cards/chunwan-wuduan.md— 春晚小品五段式结构cards/comedy-buddy-seinfeld.md— 用于建立写作纪律、对抗"断更/拖延/不敢拿出去"——当你素材攒了一堆却没成文、或写好了不敢演cards/comedy-persona.md— 用于打造一个可辨识、可记住的"台上的我"——当你要立喜剧人设、或觉得自己"台上台下一个样"没特点cards/comic-timing.md— 当用户"把握不好停顿""观众笑时我该不该说话""想理解什么是好 timing""麦克风举多高、站哪最合适"时调用cards/critic-performer-space.md— 当用户"排练时不断自我否定""上台后发挥不出、脑中持续自我批评""想分开'创造'与'打磨'"时调用cards/ctb-comic-character.md— 当用户说"怎么造一个好笑的角色"、"我的角色为什么不好笑"、"喜剧人设怎么立"时调用cards/ctb-comic-premise.md— 当用户说"喜剧前提怎么设"、"这个世界设定为什么不好笑"、"喜剧冲突有几种"时调用cards/ctb-local-tactics.md— 当用户说"三叠怎么写"、"先写个不好笑的占位再改"、"怎么 callback 收尾"时调用cards/ctb-raise-stakes.md— 当用户说"怎么让这段更紧张更好笑"、"这段为什么平淡"、"怎么设计紧张感"时调用cards/ctb-tension-release.md— 当用户说"怎么让包袱更响"、"笑点节奏怎么控"、"关键笑词放哪"时调用cards/ctb-throughline.md— 当用户说"怎么把点子长成完整喜剧故事"、"故事骨架怎么搭"、"喜剧主线九步"时调用cards/ctb-tools-context.md— 当用户说"怎么把不搭的东西凑一起"、"写个离谱回应"、"设计一对欢喜冤家"时调用cards/ctb-truth-and-pain.md— 当用户说"幽默到底是什么"、"为什么这个梗只有我懂别人不懂"、"怎么让笑话有共鸣"时调用cards/cuowei-wuhui.md— 误会与错位层层加码cards/cws-brainstorm-edit.md— 当用户说"创作流/破冰"、"成品成分诊断"、"写不出"时调用cards/cws-exaggeration-shock.md— 当用户说"夸张"时调用cards/cws-mapp-targeting.md— 当用户说"对谁讲才笑"、"受众定位"、"表演者人设"时调用cards/cws-pow-wordplay.md— 当用户说"字音/文字"、"意义/预期"、"形式/结构"时调用cards/cws-reverse.md— 当用户说"意义/预期"、"字音/文字"、"反转"时调用cards/cws-simple-truth-takeoff.md— 当用户说"简单真相"、"人人都懂的铺垫"、"借形改编"时调用cards/cws-threes-formula.md— 当用户说"我写的段子没人笑/不对劲，帮我看看"、"配方齐不齐"、"幽默到底由哪些成分构成"时调用cards/cws-triple.md— 当用户说"三单位节奏"、"误导+翻转"、"三叠"时调用cards/fangaochao-liubai.md— 冷幽默留白 / 反高潮结尾cards/fearless-bombing.md— 当用户"上台怯场""忘词/砸场/被起哄""不敢找机会演""担心喜剧越过伤痛线"时调用cards/huangdan-jiangjie.md— 荒诞降格解构cards/jingwei-yugan.md— 京味口语语感训练cards/joke-binary-structure.md— 当用户在写笑话/段子、或分析"为什么这个梗不好笑"时调用cards/joke-economy.md— 当用户"铺垫太长观众冷场""想让 punch 更响""改词时想让笑果更强"时调用cards/joke-prospector-map.md— 当用户"不知道写什么""素材想不出梗""选题太宽泛写不出来"时调用cards/joke-prospector-mine.md— 当用户"已经有一个 setup / 话题句，但挖不出包袱""punch 想不出来"时调用cards/kom-active-emotion.md— 动态情绪cards/kom-archetype.md— 原型cards/kom-comedy-equation.md— 喜剧方程式cards/kom-comic-premise.md— 喜剧前提cards/kom-expectation-gap.md— 期待与现实落差cards/kom-funny-vs-comedy.md— 好笑 vs 喜剧 辨析cards/kom-joke-four-requirements.md— 叙事笑话四要件cards/kom-non-hero.md— 非英雄cards/kom-not-knowing.md— 不知道cards/kom-perspective-lens.md— 隐喻关系 + 世界观 + 框架cards/kom-positive-action.md— 正向行为cards/kom-rewriting.md— 喜剧重写cards/kom-sitcom-family.md— 迷人的失能家庭cards/kom-straight-wavy-line.md— 直线 / 波浪型曲线cards/kom-tools-for-repair.md— 工具只在"坏掉时"用于维修cards/kom-winning.md— 获胜cards/mixes.md— 用于给任何笑话"追加"一个低成本高产的扩展笑点——当你素材不够、或想把一个梗撑大cards/piwei-kaichang.md— 痞味第一人称开场cards/premise-opposition.md— 当用户"写不出 punch-premise""punch 与 setup 像同调重述不好笑""分不清 punch-precards/rehearsal-process.md— 当用户"背稿上台就僵""排练时总忘词""想让表演自然不机械"时调用cards/reveal-at-end.md— 当用户"抖包袱时观众先笑了我还没说完""punch 的笑点被自己提前泄了""想知道为什么包袱要放最后"时调用cards/routine-builder.md— 当用户"有一堆零散笑话但串不成段子""段子之间衔接生硬""不知道怎么排序和存档"时调用cards/rule-of-three.md— 当用户"写列表/排比想埋笑点""段子里有'一、二、三'但不好笑""想用节奏制造 punch"时调用cards/self-mocking-formula.md— 用于把"弱点/尴尬/惨"变成素材和安全讨喜的人设——当你想自嘲、立亲和力人设、或避免嘲他踩雷cards/shijing-duizui.md— 市井对白节奏与斗嘴cards/stand-up-structure.md— 用于从零搭一个笑话/段子结构，或诊断"为什么不好笑""这到底算不算笑话""铺垫写不出来"cards/tag-jokes.md— 当用户"一个 setup 只拿到一次笑，想多拿""笑话讲完还能再追一句吗""想提高每分钟笑声 LPM"时调用cards/ten-commandments.md— 用于把握喜剧行业的职业立场与冒犯边界——当你写冒犯/敏感/政治正确相关内容，想既犀利又不翻车cards/turn-list-of-three.md— 用于给笑话"转向"制造惊喜落点——当你写的 punch 太平、或想学 List of Three 的节奏型笑点cards/waici-baofu.md— 方言谐音与"歪词"包袱库cards/zhoujin-renshe.md— 乡土"轴劲"人物塑造cards/zichao-fanzhao.md— 反讽自嘲人设cards/zichao-redian.md— 荒诞自嘲人设 × 时代热点嫁接
What ships with it
60 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.
- cards/act-out.md 3.1 KB
- cards/act-outs-pov.md 5.5 KB
- cards/act-outs-povs.md 4.8 KB
- cards/bca-show-order.md 5.3 KB
- cards/chunwan-wuduan.md 6.4 KB
- cards/comedy-buddy-seinfeld.md 2.8 KB
- cards/comedy-persona.md 3.2 KB
- cards/comic-timing.md 5.3 KB
- cards/critic-performer-space.md 5.5 KB
- cards/ctb-comic-character.md 3.1 KB
- cards/ctb-comic-premise.md 3.0 KB
- cards/ctb-local-tactics.md 3.1 KB
- cards/ctb-raise-stakes.md 3.0 KB
- cards/ctb-tension-release.md 2.8 KB
- cards/ctb-throughline.md 3.2 KB
- cards/ctb-tools-context.md 3.2 KB
- cards/ctb-truth-and-pain.md 2.8 KB
- cards/cuowei-wuhui.md 6.5 KB
- cards/cws-brainstorm-edit.md 2.4 KB
- cards/cws-exaggeration-shock.md 2.5 KB
- cards/cws-mapp-targeting.md 2.8 KB
- cards/cws-pow-wordplay.md 2.5 KB
- cards/cws-reverse.md 2.6 KB
- cards/cws-simple-truth-takeoff.md 2.6 KB
- cards/cws-threes-formula.md 3.5 KB
- cards/cws-triple.md 2.4 KB
- cards/fangaochao-liubai.md 6.5 KB
- cards/fearless-bombing.md 6.1 KB
- cards/huangdan-jiangjie.md 6.6 KB
- cards/jingwei-yugan.md 6.4 KB
- cards/joke-binary-structure.md 6.3 KB
- cards/joke-economy.md 5.2 KB
- cards/joke-prospector-map.md 5.9 KB
- cards/joke-prospector-mine.md 5.8 KB
- cards/kom-active-emotion.md 6.3 KB
- cards/kom-archetype.md 6.1 KB
- cards/kom-comedy-equation.md 7.2 KB
- cards/kom-comic-premise.md 6.3 KB
- cards/kom-expectation-gap.md 7.4 KB
- cards/kom-funny-vs-comedy.md 6.9 KB
- cards/kom-joke-four-requirements.md 6.4 KB
- cards/kom-non-hero.md 7.4 KB
- cards/kom-not-knowing.md 7.0 KB
- cards/kom-perspective-lens.md 7.5 KB
- cards/kom-positive-action.md 7.4 KB
- cards/kom-rewriting.md 6.4 KB
- cards/kom-sitcom-family.md 6.0 KB
- cards/kom-straight-wavy-line.md 6.5 KB
- cards/kom-tools-for-repair.md 6.5 KB
- cards/kom-winning.md 7.1 KB
- cards/mixes.md 2.8 KB
- cards/piwei-kaichang.md 7.1 KB
- cards/premise-opposition.md 5.4 KB
- cards/rehearsal-process.md 5.5 KB
- cards/reveal-at-end.md 5.2 KB
- cards/routine-builder.md 5.5 KB
- cards/rule-of-three.md 5.0 KB
- cards/self-mocking-formula.md 2.9 KB
- cards/shijing-duizui.md 7.1 KB
- cards/stand-up-structure.md 3.4 KB
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.
- 28d ago First seen · 157 lines · 65 tokens per session scan A a1bc99f0fd7a
喜剧 Mechanics is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 3,730 once invoked, about $0.0003 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 2026-09-27.
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.