tapcanvas-video-workflow

tapcanvas-video-workflow is a skill for Claude Code, Codex from anymouschina/TapCanvas. It costs 104 tokens per session (8,290 once invoked), scanned A, original, MIT.

A workflow for turning source material, such as a novel chapter, into a finished video through saved, resumable production steps. It coordinates planning, assets, writing, voice work, generation, editing, and delivery checks.

In plain words
What is it for?
Use it for one-off video tests, complete chapter adaptations, segmented validation, interrupted or resumed jobs, and videos with action-heavy or dialogue-led scenes.
Why use it?
It prevents separate video-making paths from getting out of sync and allows work to be split, paused, resumed, or checked at defined stages. It also keeps characters, scenes, dialogue, and actions consistent across clips.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for one-off video tests, complete chapter adaptations, segmented validation, interrupted or resumed jobs, and videos with action-heavy or dialogue-led scenes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anymouschina/tapcanvas/tapcanvas-video-workflow
Install

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.

Any agent
npx skills add anymouschina/TapCanvas --skill tapcanvas-video-workflow
Clone the repo
git clone --depth 1 https://github.com/anymouschina/TapCanvas

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tapcanvas-video-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-video-workflow/github.svg)](https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-video-workflow)
Your own site
<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-video-workflow"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-video-workflow/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.

agentmods 80×15 button for tapcanvas-video-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-video-workflow"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-video-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.08290
Opus 5.5 $0.00042 $0.03316
Sonnet 5.5 $0.00021 $0.01658
Haiku 4.5 $0.00010 $0.00829

Measured 20d ago against content hash 34bf2aeac2ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tapcanvas-video-workflow 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 20d 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.

apps/agents-cli/skills/tapcanvas-video-workflow/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

当前已装配紧凑一键成片图以冻结来源分段、章级共享资产注册表、全章连续性/对白规划、逐 Clip packet 作者、节点投影和媒体执行为主线。每个 Clip 对应一个视频节点,章内重复资产按精确注册身份共用;跨章节历史资产由通用图片节点执行时依据稳定身份在项目记忆中查询并验证真实 URL,不向章级作者一次性注入历史目录。触发视频时先验真其上游图片 URL。作者从 Skill 与同媒体知识候选按需获取创作证据,模型沿用户本轮配置继承。旧版多节点 BeatSheet 与独立站位图生产合同只在当前 Workflow IR 实际包含对应 artifact/执行器时适用,不能从历史描述补出额外节点或声称紧凑版已经上传站位图。

只有冻结 Workflow IR 实际声明 tapcanvas.source-unit-ledger/v1、tapcanvas.chapter-beat-plan/v3、tapcanvas.chapter-asset-plan/v3、tapcanvas.clip-design/v2 的执行,才按这些旧分阶段 artifact 分别交付并由组装器生成 BeatSheet。它们不是当前紧凑图的前置步骤;当前图由单个章作者交 tapcanvas.chapter-sequence/v3,作者自主选择准备工作,再交共享资产与逐 Clip 生产。首 Clip 路径同样以其实际冻结 IR 和 artifact 为准。

当前完整 full_video 图以 canvas-source 的 canonical 来源进入 delivery-contract 与全章作者,再投影同一章序列、准备共享资产并执行逐 Clip 生产。对话发起生产时,来源准备由主代理在启动前按 screenwriter 的 source-readiness 判断:完整章节可直接保留;仅有简报或存在具体因果缺口时,先完成必要创作、自审修订与定稿持久化,再显式绑定交接稿。手动直接启动仍按真实输入执行,不因缺定稿标签增加拦截,也不固定插入 source-ledger 或 text-expansion。历史快照若显式连线 expanded-source,它才作为对应节点的草稿输入,不能从本文描述补出不存在的阶段,也不减少来源、声音和资产合同。

TapCanvas 视频 Workflow IR

使命

把用户的视频目标交给一条可观察、可拆分、可中断、可恢复的持久 Workflow IR。根代理负责冻结用户范围、读取真实项目事实、完成必要的前置编剧与导演定稿并绑定真实来源后启动工作流;BeatSheet、逐 Clip writer、资产验真与补齐、配音清单、生产交接、视频生成、合成和交付验证都由已保存 DAG 的明确节点承担。

工作流受理不等于剧本已定稿。对话主代理先按 tapcanvas-screenwriter/references/source-readiness.md 判断:来源足够时保留原稿,存在缺口时在当前作者链完成必要创作、导演设计、回读与实际修订,再交生产。无需固定经过大纲、初稿、审稿等全部步骤,也不额外要求用户批准一次。导演选择写入同一份可拍正文,服务人物行动、观众认知和情绪变化,不另造与剧本冲突的设计稿。章序列作者依据该交接稿落实有序事件、完整对白、连续性与动态 Clip 窗口,不分配单镜和发声秒数,不因物理切段另编故事或重置状态;发现自身改编造成的偏差,在当前作者链直接修正。authoringRecord 只记录实际工作,不能冒充独立审核回执。主代理以真实正文、保存及回读回执报告定稿,不能用视觉圣经、计划或工作流受理冒充完成。

系统只有这一条一键成片路径:

真实项目/章节/素材事实
-> Agent 判断必要准备,完成可拍交接稿并绑定其真实来源
-> 当前已装配 Workflow IR
-> typed ports 与逐节点持久状态
-> 真实媒体任务与资产 URL
-> workflow output 交付证据

高能超自然动作扩展(同一 Workflow IR 内)

动漫/超能力都市、校园战斗或其它高动力片段仍走上述唯一路径。BeatSheet 先冻结角色卡、场景卡、能力主形、动作结果和真实时长;逐 Clip writer 再按结构化创作判断加载通用战斗标准,并可追加 tapcanvas-high-energy-action 领域扩展。该扩展只增加动作因果、快切信息功能、环绕/复合运镜、造型—能力视觉耦合与低熵交接的表达方法,不新增 route、模型、镜头配额、字数门槛或质量闸门。用户指定 15 秒时,15 秒进入当前 Clip 的 generationContract;镜头数量与切点仍由真实事件完成、对白可读度、连续性和交接状态决定。具体依赖与交付证据见 references/high-energy-action-workflow.md。

Read the full file on GitHub · 284 lines

Files

What ships with it

2 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.

Changes

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.

  1. 20d ago Changed · +27 lines 34bf2aeac2ce
  2. 1mo ago Changed · +4 lines f0bee398d941
  3. 1mo ago First seen · 253 lines · 104 tokens per session scan A 7ed6aafafa87

Subscribe to this mod's changes

tapcanvas-video-workflow is a skill published in the GitHub repository anymouschina/TapCanvas (686 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 8,290 once invoked, about $0.0004 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 2026-09-21.

Related

Other skills, from other repositories

md-hive-sync

Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…

chaitanyagiri/munder-difflin · 109 tokens

issue

Create a GitHub issue in the tldraw repository from a user description, then mature it through follow-up questions. Use when the user invokes issue, asks to create an issue, report a bug, file a feature request, or answers follow-up questions for an issue created by this skill.

tldraw/tldraw · 61 tokens

write-issue

Reference standards for writing and maintaining GitHub issues in the tldraw repository. Use as supporting guidance when another skill or workflow needs issue title, body, type, label, or triage standards.

tldraw/tldraw · 44 tokens

take

Find a GitHub issue in tldraw/tldraw, assign it, implement it, verify it, and open a pull request. Use when the user invokes take, asks to take an issue, implement an issue, work on an issue number or URL, or pick up an issue from a description.

tldraw/tldraw · 64 tokens

outlook-calendar

A skill for managing Microsoft Outlook and Microsoft 365 calendar events through a connected account.

marswaveai/skills · 70 tokens

ai-aftersales-ticket-agent

An AI workflow for sorting after-sales tickets, summarizing them, drafting replies, and routing them to the right team for e-commerce support.

wubin1836/ai-hive-agent-skills · 144 tokens