Release Media Pack Agent Skill

Generates story-driven bilingual launch films, promotional graphics, and release copy packaged into a verifiable release media bundle.

Context cost
5.8k tokensestimated from the bundle, loaded when it triggers
Bundle
5 of 6 fileshanded out here; the rest is at its source
Licence
AGPL-3.0-onlythe author’s own terms
Last change
—v1.0.0
Servers it uses
Noneruns standalone

What it does

为 Nomi 桌面端发版制作故事先行的双语宣传片、更新图文与发布文案,并把版本事实、TikHub 样片研究、Nomi 生成和本地后期串成可回溯的素材包。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

content

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md13.0 kB · preview
--- name: release-media-pack metadata: nomi: selectable-in-workbench: true version: 1.0.0 label: 发版素材包 author: "@nomi" tools: - read_script - look_at_canvas - draft_shots - arrange_canvas - generate required-providers: - text - image - video stages: - id: evidence goal: 先冻结当前/上版身份、安装包证据、用户可见变化、限制与官方网址;未验证内容不得写成公开事实。 tools: - read_script pause: true skill-refs: - writer-review model-prefs: - kind: text - id: research goal: 读取已提供的 TikHub 公开样片研究包,提炼钩子、节奏、转场、声音和 CTA 机制;Nomi 当前无 TikHub 工具时必须输出外部研究交接,不得假装已检索。 tools: - read_script depends-on: - evidence pause: true skill-refs: - writer-review - director-transitions - director-sound model-prefs: - kind: text - id: story goal: 让故事先成立,再把核心版本变化作为剧情转折写入 3–4 段、60 秒内的分镜与声音/转场方案,交用户审阅。 tools: - look_at_canvas - draft_shots depends-on: - research pause: true skill-refs: - writer-screenwriter - writer-structure - writer-review - director-shot-translation - director-cinematography - director-consistency - director-transitions - director-sound model-prefs: - kind: text - id: build goal: 把获批分镜落成画布节点,连接角色、道具和风格锚,写入可直接生成且包含连续性出入点的提示词。 tools: - look_at_canvas - draft_shots - arrange_canvas depends-on: - story pause: true skill-refs: - director-staging - director-consistency - director-cinematography model-prefs: - kind: image - kind: video - id: generate goal: 用户确认花费后按波次生成:先验证锚点和代表镜头,再扩到关键帧与全部视频;失败只重跑受影响镜头。 tools: - look_at_canvas - generate depends-on: - build pause: true skill-refs: - director-keyframe-review - director-consistency model-prefs: - kind: image - kind: video - id: assemble goal: 把已生成镜头按故事顺序排入时间轴,保留中央安全区、语义转场和声音提示,分别准备中文与英文后期版本。 tools: - look_at_canvas depends-on: - generate pause: true skill-refs: - director-transitions - director-sound - director-keyframe-review model-prefs: - kind: video - id: handoff goal: 输出版本化素材包清单与真实状态;把 TikHub、音乐/音效、HyperFrames/FFmpeg、成片 QA 和发布列为外部后期动作,未完成就降级而非假报。 tools: [] depends-on: - assemble pause: true model-prefs: - kind: text library: kind: skill title: zh-CN: 发版素材包 en: Release media pack summary: zh-CN: 为 Nomi 桌面端发版制作故事先行的双语宣传片、更新图文与发布文案,并把版本事实、TikHub 样片研究、Nomi 生成和本地后期串成可回溯的素材包。 en: Prepare bilingual launch films, graphics and release copy. appliesTo: - text group: zh-CN: 创作流程 en: Workflow slots: [] source: url: https://github.com/aqm857886159/Nomi/blob/7a072f12d4e35d1bf341403d942e5c0c702e6c7b/skills/release-media-pack/SKILL.md revision: 7a072f12d4e35d1bf341403d942e5c0c702e6c7b author: Nomi contributors changes: Nomi adds library presentation metadata; the skill body is unchanged. evidence: - https://github.com/aqm857886159/Nomi/blob/7a072f12d4e35d1bf341403d942e5c0c702e6c7b/skills/release-media-pack/SKILL.md preview: path: assets/cover.png type: image provenance: illustration license: AGPL-3.0-only ---
141# Nomi 发版素材包
142
143你是 Nomi 的发版内容导演,不是功能播报员。每次桌面端准备发新版时,把版本证据、故事宣传片、更新图文和发布文案收进同一个可回溯素材包。
144
145## 硬规则
146
1471. **先事实,后表达**:PR 标题不是发布事实。未核到准确版本/提交/安装包/上版基线的内容只能标 unverified,不能进公开文案。
1482. **先故事,后功能**:前五秒先让人物、冲突或荒诞事件成立;更新只作为世界变化的原因出现,不能把宣传片剪成功能 PPT。
1493. **中文、英文分成两支**:同一故事和镜头可复用,但 ZH 与 EN 的标题、断行、图文和文案必须独立校对;禁止中英翻译同屏混排。品牌/模型官方名不算混排。
1504. **不假装工具存在**:Nomi 当前能拆分镜、建节点、连参考、生成、排时间轴;不能由本 Skill 直接做 TikHub 联网、音乐/音效、HyperFrames/FFmpeg、本地打包、成片 QA 或上传。缺口进入 handoff,状态降级。
1515. **按波次推进**:证据、研究、故事和分镜先审,再调 generate;先跑锚点和代表镜头,然后才扩批。
1526. **不照抄样片**:只学习钩子、节奏、转场、标题、声音、证明方式和 CTA;不复刻完整故事、镜头顺序、台词、人物、音乐、Logo、画面或品牌视觉。
153
154## 流程规划
155
156### 1. evidence — 冻结发布事实
157
158先产出事实表,每条公开变化都要有:
159
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md560 words
Files5
LicenceAGPL-3.0-only
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈970
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,880
on trigger
The instruction body and 4 supporting files, read only when the skill fires.
2.9%
of a 200k window
Ten skills this size would take about 29% of the window before you open a file.
050k100k150k200k context window

5.8k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

The download carries 5 of the 6 files in its source folder; the list here names 5 files, 23.4 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in. The other one is not in the download — listed after these, with why.

  • SKILL.md13.0 kB
  • README.md5.3 kB
  • evals/evals.json2.2 kB
  • examples/material-pack-manifest.template.json1.7 kB
  • examples/release-evidence.template.md1.2 kB

Not in the download

Not carried is a type a skill download does not hold. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take it from its source.

  • assets/cover.pngread · not carried
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the download is 5 files — not the whole of its source: 1 file is left out, and the skill reads it. It is listed under the files, with why. The AGPL-3.0-only licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Release Media Pack · 5.8k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/release-media-pack/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/release-media-pack" ] && { [ ! -e .claude/skills/release-media-pack ] || { mv .claude/skills/release-media-pack "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/release-media-pack" .claude/skills/ && echo "Installed .claude/skills/release-media-pack"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add aqm857886159/release-media-pack

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/release-media-pack/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/release-media-pack/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/release-media-pack" ] && { [ ! -e ~/.claude/skills/release-media-pack ] || { mv ~/.claude/skills/release-media-pack "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/release-media-pack" ~/.claude/skills/ && echo "Installed ~/.claude/skills/release-media-pack" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/release-media-pack/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: 1 file of its source, which its SKILL.md or scripts read (which one, and why). Take it from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0.0
Publishedno release date on file
PriceFree
Referenceaqm857886159/release-media-pack

Versions

v1.0.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

AQ
aqm857886159

Publishes on mcprush.

0 servers listed2 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill