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 wu529778790/shenzjd-skills --skill video-cover-packagergit clone --depth 1 https://github.com/wu529778790/shenzjd-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/wu529778790/shenzjd-skills/video-cover-packager)<a href="https://agentmods.dev/skills/wu529778790/shenzjd-skills/video-cover-packager"><img src="https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/video-cover-packager/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/wu529778790/shenzjd-skills/video-cover-packager"><img src="https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/video-cover-packager.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 | $0.00151 | $0.03147 |
| Opus 5.5 | $0.00060 | $0.01259 |
| Sonnet 5.5 | $0.00030 | $0.00629 |
| Haiku 4.5 | $0.00015 | $0.00315 |
Grade A, and why
video-cover-packager 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Cover Packager
把一份视频素材（脚本/大纲/字幕/逐字稿/音频/视频）包装成所选平台可直接使用的完整发布方案：封面标题、平台标题、作品描述、平台标签，确认后再生成封面创意方向与生图。
Overview
方法参考 jennie-dingding-cover-packager：先判断"这期内容真正值得点击的是什么"，再决定"画面怎样让观众一眼看懂"。一次只处理一期内容。
固定交付四部分：
- 封面包装：精简包装简报、标题推导、3 个有策略差异的封面标题、推荐分行、3-5 个创意主题方向、封面预审、平台尺寸适配。
- 平台标题：只为用户选择的平台生成。
- 作品描述：默认一套供所有所选平台共用（含 YouTube）。
- 平台标签：只为用户选择的平台生成。
流程：包装简报 → 标题策略 → 封面标题 → 平台标题 → 封面主题 → 封面预审 → 作品描述 → 平台标签 → 待用户确认 → 生图 → 标题合成出成品封面。
When to Use
- User provides a video script/transcript/audio and wants cover titles + publish copy
- User mentions 封面包装 / 视频包装 / 发布方案 / 标题 / 标签 for one episode of content
- User wants cover art direction (creative scenes) before generating the actual cover image
- User says "给这期视频做封面标题描述标签"
When NOT to Use:
- Batch packaging of multiple episodes（一次只处理一期）
- 用户只想剪辑视频或做字幕（不在范围内）
- 纯文章/图文（无视频素材）的标题创作
Core Pattern
Step 1: 素材与平台确认
最低输入：一份本期素材 + 至少一个目标平台（小红书/抖音/视频号/B站/YouTube，可多选）。
- 缺素材时请用户提供脚本、大纲、字幕、逐字稿、音频、视频或完整说明；音频/视频无法转写时明确说明限制，不假装理解。
- 素材和平台齐全时默认直接执行（A 模式），不让追问成为阻塞；用户想控制方向可最多回答 2 个问题（给谁看/看完做什么），或提供账号资料定制语气（B/C 模式）。
- 用户已提供标题/封面时先审查，给出"保留/局部修改/重做"结论；未经允许不替换已确认内容。
Step 2: 提炼包装简报
从素材事实中提炼，用最多 6 项展示：一句话主题、目标人群与场景、痛点/观看理由、结果/冲突/反转/证据、内容类型、最合适的用户动作。内容事实优先，账号资料只做校准。
Step 3: 标题推导与生成
先完成推导链：内容事实 → 独特结果 → 人群动机 → 单一点击承诺 → 主策略+备选策略 → 压缩 → 兑现检查，再生成 3 个有真实策略差异的封面标题 + 1 个推荐 + 2-3 行分行排版 + 各平台标题。
主策略从下表选 1 个、备选 1 个，从对应公式池内部生成至少 8 个候选后淘汰：
| 策略 | 适合内容 | 代表公式 |
|---|---|---|
| 判断选择型 | A vs B、怎么选、值不值 | [好的特质] VS [坏的特质] 如何区分；你到底要不要 [话题] |
| 痛点避坑型 | 踩坑、纠错、损失 | [领域] 这 [N] 件事千万别做；[不想要的结果] 的最根本原因 |
| 身份代入型 | 人群明确，"说的就是我" | 给 [一群人] 的一个忠告；没有 [资源]，也能 [结果] |
| 结果清单型 | 教程、清单、可收藏 | [结果] 的 [N] 个技巧；如何不 [讨厌的事] 就能 [结果] |
| 体验反转型 | 亲测、复盘、前后变化 | 我如何在 [时间] 内 [结果]；从 [不想要] 到 [想要] |
| 好奇缺口型 | 反常识、内幕、认知升级 | [一群人] 不会告诉你的建议；为什么 [大家都觉得好的事] 其实有害 |
| 互动测试型 | 测一测、你是哪种 | 测测你的 [属性]；[N] 秒看出你是哪种 [人群] |
| 数字锚定型 | 数据、效率、对比 | [N] 分钟完成 [原来要 N 小时的事]；靠 [方法] 拿到 [数字结果] |
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.
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.
- 4d ago First seen · 158 lines · 151 tokens per session scan A c9bde9cb8ba5
video-cover-packager is a skill published in the GitHub repository wu529778790/shenzjd-skills (4 stars, last pushed 5d ago), licensed MIT. It adds 151 tokens to every session and 3,147 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 2026-09-26.
Other skills, from other repositories
dedicated-server
Use when building dedicated servers — headless export, server architecture, lobby management, and deployment.
dialogue-manager
Use when using the Dialogue Manager addon — .dialogue files with titles, responses, conditions and mutations, runtime balloons, and C# support.
event-bus
Use when implementing decoupled communication between nodes — global EventBus autoload with typed signals.
limboai
Use when using the LimboAI addon — behavior trees and hierarchical state machines (C++ GDExtension) with a visual editor, BTTask subclassing, and a blackboard.
localization
Use when implementing localization (i18n/l10n) — TranslationServer, CSV/PO translation files, locale switching, RTL support, and pluralization in Godot 4.3+.
physics-system
Use when working with physics bodies, collision shapes, raycasting, areas, rigid bodies, ragdolls, soft bodies, Jolt physics, and physics interpolation in Godot 4.3+.