chengfeng-videocut-skills is a Codex plugin that coordinates Chinese voiceover video editing through the chengfeng-videocut runtime, whose command-line tools and APIs perform the actual processing. It is for agents that need to edit and export narrated videos, while its catalogue skills handle decisions and workflow coordination around that runtime.
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 Agentchengfeng/chengfeng-videocut-skills --skill chengfeng-videocut-workbenchgit clone --depth 1 https://github.com/Agentchengfeng/chengfeng-videocut-skillsWrote 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/agentchengfeng/chengfeng-videocut-skills/chengfeng-videocut-workbench)<a href="https://agentmods.dev/skills/agentchengfeng/chengfeng-videocut-skills/chengfeng-videocut-workbench"><img src="https://agentmods.dev/badge/skills/agentchengfeng/chengfeng-videocut-skills/chengfeng-videocut-workbench/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/agentchengfeng/chengfeng-videocut-skills/chengfeng-videocut-workbench"><img src="https://agentmods.dev/badge/skills/agentchengfeng/chengfeng-videocut-skills/chengfeng-videocut-workbench.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 | $0.00145 | $0.01357 |
| Opus 5.5 | $0.00058 | $0.00543 |
| Sonnet 5.5 | $0.00029 | $0.00271 |
| Haiku 4.5 | $0.00015 | $0.00136 |
Grade A, and why
chengfeng-videocut-workbench 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 27d 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.
What it actually says
工作台操作
把明确的编辑要求变成现有 CLI 操作，始终在同一工程回读结果。不是另一套编辑引擎，也不是每次使用其他 Skill 前的必读入口。
先辨认动作
| 用户要做什么 | 本 Skill 的路径 |
|---|---|
| 看当前工程、找一句话、看已有片段和画面 | 只读定位，见 操作方法 |
| 在一句话上放动画或视频，保留原口播 | 画面覆盖；时间线不加长，见 操作方法 |
| 删除画面、词句或片段 | 区分对象与声音影响，见 删除方法 |
| 分成两段、缩短一段、调换已有片段顺序 | EDL 修改，见 操作方法 |
| 改横竖比例、画面铺满或完整显示 | 分清工程画布和媒体 fit，见 操作方法 |
| 在主时间线任意位置插新素材并顺延 | 先查当前能力；没有通用插入命令就明确缺口，不把覆盖或移位冒充插入 |
用户说“插入”时，先判断是盖画面且口播继续，还是添加新时长、让后面顺延；说“删除”时，先判断是移除画面还是剪掉声音与时间。意图已明确就执行，不重复追问；重复句、重用素材或目标不唯一时，列出位置供确认，不凭文本猜实例。
需要自动判断口误、重复和保留哪一版，交给剪口播 Skill；字幕内容与排版交给字幕 Skill；镜头/动画创作交给相应设计 Skill；成片输出交给导出 Skill；连接故障和升级交给维护与排障。不自动启动额外 Agent，也不自动安装缺失 Skill。
一次操作的固定流程
- 连接：首次或身份变化时完整读 连接与提交。保留已确认的 Runtime 参数数组、显式 origin、服务器 projectId 和能力，不每个动作重新发现环境。
- 读取：仅读相关文档；保存文档自己的 revision、目标 ID、原值和预期结果。词句定位必要时分页完整读取，确认源身份和实例；不能拿字幕 cue ID 当 word ID。
- 计划：简短说明会改哪个对象、是否缩短时间/影响声音。用户已明确授权的范围不反复确认；新影响（额外移除关联层等）须先取得授权。
- 提交：按实际
workbench commands --json的字段和模式调用。写操作的--confirmed表示已有授权，不是授予 Agent 权限的开关。编辑正式工程只通过 Runtime，不直接改工程 JSON。 - 核验：读取受影响资源，核对 ID、差异和时长，必要时检查词锚点、字幕状态及画面时序。连做多个 patch 时前一步成功回读后才构造下一步；这不是原子批量事务。
- 交付：分别说明数据已写入、画面/声音是否实际复核、未支持或未验证项。提交成功不等于预览/成片通过，页面没刷新也不等于没写入，先回读，不能再次提交来“刷新”。
失败就收住写入
- 冲突：重新读当前差异，旧批准不能通过替换成新 revision 自动重放；确认新的目标和影响后才另作计划。
- 超时、断连或 readback 失败：结果可能已写入，保存原请求和身份。按对应资源、资产哈希或原 operationId 精确查询；找不到也不证明未提交。不换 ID 盲重试。
- 资源不足、歧义目标、缺 capability：报告具体卡点，保留现有工程。不自动升级、重启、重转录、改 registry 或切到其他工具。
- 不提供通用撤销/重做、音量混音、播放控制或任意位置新媒体顺延插入的虚构命令。
playback是读取播放词流，operation-recover是受限事务恢复，不是任意 undo。 - 删除仅指工程中的指定对象；不清理原视频、录音、已导入资产、模块文件或缓存。
典型请求
- “在第二句上盖这段 MP4，声音不动。” → 定位真实词 ID、导入媒体、保留旧层新增覆盖、回读。
- “把刚加的小黑动画移除。” → 定位唯一 layer，只移除该层；不剪口播，不删动画源文件。
- “把第三次说的这句删掉，后面接上。” → 核实第三个实例，走已支持的词/片段删除流程并核验新时长。
- “把第一段分两半，再把后半放到结尾。” → 使用片段局部剪后秒数拆分，回读新 ID，再按磁性时间线规则移动。
What ships with it
7 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.
- 27d ago First seen · 48 lines · 145 tokens per session scan A c542728283c7
chengfeng-videocut-workbench is a skill published in the GitHub repository Agentchengfeng/chengfeng-videocut-skills (3,089 stars, last pushed 7d ago), licensed Apache-2.0. It adds 145 tokens to every session and 1,357 once invoked, about $0.0006 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.
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…
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…