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 ZJU-REAL/Easel --skill asset-managergit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/zju-real/easel/asset-manager)<a href="https://agentmods.dev/skills/zju-real/easel/asset-manager"><img src="https://agentmods.dev/badge/skills/zju-real/easel/asset-manager/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/zju-real/easel/asset-manager"><img src="https://agentmods.dev/badge/skills/zju-real/easel/asset-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.01807 |
| Opus 5 | $0.00057 | $0.00903 |
| Sonnet 5 | $0.00023 | $0.00361 |
| Haiku 4.5 | $0.00011 | $0.00181 |
Grade A, and why
asset-manager 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 11d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
素材管理器
outputs/ 产物的归档、标签、检索 — 让历史内容随时可查可复用
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| action | 是 | 操作类型：scan / search / archive / tag / list / report |
| query | 否 | 搜索关键词（search 操作时使用） |
| path | 否 | 指定操作的文件或目录（默认 outputs/） |
| tags | 否 | 要添加的标签列表，逗号分隔（tag 操作时使用） |
| filter_platform | 否 | 按平台筛选：xiaohongshu / weibo / douyin / zhihu / wechat / x |
| filter_type | 否 | 按类型筛选：image / video / text / card / poster / script |
| filter_date | 否 | 按日期筛选：today / this-week / this-month / 2026-07 / 2026-07-15 |
| profile_name | 否 | 按画像筛选（有 Profile 上下文时自动填入） |
输出
list 操作
## 素材清单
**目录**: outputs/
**统计**: 共 {n} 个文件，{size} MB
| 文件名 | 类型 | 来源 SKILL | 创建日期 | 标签 |
|--------|------|-----------|----------|------|
| hero-poster-科技新品-20260715.png | 海报 | poster-hero | 2026-07-15 | #科技 #新品发布 |
| xhs-card-护肤-01.png | 卡片 | card-xiaohongshu | 2026-07-14 | #护肤 #小红书 |
| ... | ... | ... | ... | ... |
search 操作
## 搜索结果："{query}"
找到 {n} 个匹配项：
| 文件 | 匹配位置 | 相关度 | 创建日期 |
|------|----------|--------|----------|
| outputs/主题名/科技-对比评测.md | 文件名+内容 | ★★★ | 2026-07-12 |
| outputs/主题名/科技产品-开箱.md | 内容 | ★★☆ | 2026-07-10 |
report 操作
## 素材统计
### 按类型分布
| 类型 | 数量 | 占比 |
|------|------|------|
| 图片 | 45 | 38% |
| 文案 | 32 | 27% |
| 视频脚本 | 20 | 17% |
| 卡片 | 15 | 13% |
| 海报 | 6 | 5% |
### 按平台分布
| 平台 | 数量 | 最近产出 |
|------|------|----------|
| 小红书 | 30 | 2026-07-15 |
| 微博 | 25 | 2026-07-14 |
| 抖音 | 20 | 2026-07-13 |
### 产出趋势（近 30 天）
| 周 | 产出数量 | 日均 |
|----|----------|------|
| 本周 | 12 | 1.7 |
| 上周 | 18 | 2.6 |
| 上上周 | 8 | 1.1 |
执行步骤
所有有副作用、需状态一致的文件操作（扫描索引、移动归档、维护 tags.json）已固化为
scripts/assets.py（纯 stdlib，argparse 子命令）。LLM 只做意图路由和结果呈现，不手动 find/grep/mv 或手写 JSON。 索引与 tags 用原子写入（临时文件 + rename）。
操作路由
- 解析用户意图，映射到脚本子命令：
- "整理素材" / "归档" / "outputs 整理" →
archive - "打标签" / "标记" →
tag - "找之前的" / "搜索历史" / "之前做的" →
search - "素材列表" / "看看有什么" →
list - "素材统计" / "产出报告" →
report - （检索前若索引可能过期，先跑一次
scan；search/list 在索引缺失时会自动扫描）
- "整理素材" / "归档" / "outputs 整理" →
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.
- 11d ago First seen · 143 lines · 114 tokens per session scan A 48978ff5c6f5
asset-manager is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 1,807 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…