Agent skill

Asset Manager

by ZJU-REAL in ZJU-REAL/Easel

outputs/ 目录下的产物管理:按日期/平台/类型归档、打标签、搜索历史内容、生成素材清单. An agent skill from ZJU-REAL/Easel.

Apache-2.0Auto-check passed

Install Asset Manager

skills CLI
$ npx skills add ZJU-REAL/Easel --skill asset-manager -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZJU-REAL/Easel asset-manager --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/asset-manager .claude/skills/asset-manager && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
asset-manager
GitHub stars
3.4k
Token cost
~964 tokens
SKILL.md length
173 words
Files
3 (incl. scripts)
Skills in repo
114
Repo updated
First seen
Licence
Apache-2.0

At a glance

outputs/ 目录下的产物管理:按日期/平台/类型归档、打标签、搜索历史内容、生成素材清单. An agent skill from ZJU-REAL/Easel.

  • Works in 4 steps: 统一入口(默认 --root outputs) → 归档规则:文件被移动到… → 安全保证(脚本内置,无需 LLM 判断) → …
  • SKILL.md covers 输入, 输出, 执行步骤 and Profile 感知
  • Runs Python scripts from its folder; calls python3

What it does

Asset Manager is an agent skill from ZJU-REAL/Easel. outputs/ 目录下的产物管理:按日期/平台/类型归档、打标签、搜索历史内容、生成素材清单。 当用户说"整理素材"、"归档"、"找之前的内容"、"搜索历史"、"素材管理"、 "outputs 整理"、"之前做的"时使用。 与其他 produce 层 SKILL 的区别:produce 层负责生成内容, asset-manager 负责生成后的产物管理(归档、检索、标签)。

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `EASEL-META.md` and `scripts/assets.py`).

The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.

Example prompts

  • “找之前的内容”
  • “outputs 整理”
  • “/asset-manager”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 统一入口(默认 --root outputs)
  2. 归档规则:文件被移动到 outputs/{日期}/{平台}/{类型}/。日期取自文件名中的
  3. 安全保证(脚本内置,无需 LLM 判断)
  4. 结果呈现:把脚本输出整理成"输出"章节的 Markdown 表格返回给用户。

What it can do on your machine

Read from SKILL.md and the folder at commit 278f420. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Asset Manager loads about 964 tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 173 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~964

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 278f420, republished under its Apache-2.0 licence (© ZJU-REAL). 173 words, ~964 tokens.

Download SKILL.mdSave it as .claude/skills/asset-manager/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
asset-manager
description
outputs/ 目录下的产物管理:按日期/平台/类型归档、打标签、搜索历史内容、生成素材清单。 当用户说"整理素材"、"归档"、"找之前的内容"、"搜索历史"、"素材管理"、 "outputs 整理"、"之前做的"时使用。 与其他 produce 层 SKILL 的区别:produce 层负责生成内容, asset-manager 负责生成后的产物管理(归档、检索、标签)。
layer
general

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
markdown
## 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
markdown
## 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
markdown
## 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
  1. 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)
调用脚本
  1. 统一入口(默认 --root outputs):

    bash
    S=skills/openclaw/asset-manager/scripts/assets.py
    python3 $S scan                                    # 生成/更新 INDEX.json
    python3 $S search "关键词" --platform xiaohongshu --type card --date this-week
    python3 $S search --tag 护肤,种草                   # 标签需全部命中
    python3 $S list --platform weibo                    # 素材清单
    python3 $S report                                   # 类型/平台/日期分布
    python3 $S tag "招人贴/card_1.png" --add 护肤,小红书 --remove 草稿
    python3 $S archive                                  # 预览归档计划(dry-run)
    python3 $S archive --apply                          # 确认后真正移动
    python3 $S archive 招人贴 --apply                    # 只归档某目录/文件
  2. 归档规则:文件被移动到 outputs/{日期}/{平台}/{类型}/。日期取自文件名中的 YYYYMMDD/YYYY-MM-DD,无则取 mtime;平台/类型由文件名与扩展名推断。

  3. 安全保证(脚本内置,无需 LLM 判断):

    • archive 默认 dry-run,只打印 MOVE/CONFLICT/skip 计划;加 --apply 才移动
    • 幂等:source==target 跳过;目标已存在且内容一致跳过;已在 日期/平台/... 结构下的不再归档
    • 目标已存在但内容不同 → 标 CONFLICT 跳过,绝不覆盖
    • 移动时 tags.json 的 key 自动跟随新路径
  4. 结果呈现:把脚本输出整理成"输出"章节的 Markdown 表格返回给用户。 归档前务必先展示 dry-run 计划、得到确认后再 --apply。

Profile 感知

  • 有 Profile 上下文时:
    • 读取 identity.md / platforms.md 获取账号名与平台,作为 --tag(画像名)或 --platform 传给脚本,缩小 search/list 范围
    • 素材若按画像分目录存放,archive <画像目录> --apply 只归档该画像的产物
  • 无 Profile 上下文时:
    • 显示 outputs/ 下所有素材,不做画像筛选
    • 附注:"如提供账号 Profile(含 identity.md / platforms.md),可按账号和平台维度管理素材"

自研溯源与参考项目见同目录 EASEL-META.md。

© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/openclaw/asset-manager of ZJU-REAL/Easel.

  • SKILL.md
  • EASEL-META.md
  • scripts/assets.py

Open the folder on GitHubat commit 278f420

Compare with similar skills

Asset Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Asset Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Asset Manager this skillZJU-REAL/Easel3.4k—~964Automated safety check: PassApache-2.0
AssetsBuilderIO/agent-native7.1k—~1.2kAutomated safety check: PassNone
Game Asset AuditDonchitos/Claude-Code-Game-Studios26k—~2kAutomated safety check: PassMIT
3D Asset Generationcalesthio/OpenMontage66k—~1.2kAutomated safety check: PassAGPL-3.0
Game Asset Spec WriterDonchitos/Claude-Code-Game-Studios26k—~5kAutomated safety check: PassMIT
Asset Inventorysickn33/agentic-awesome-skills47k2 repos~3.4kAutomated safety check: PassMIT

Similar skills

  • Assets

    BuilderIO/agent-native

    Use Agent-Native Assets for image and video generation requests, brand-safe asset search/export, and human-in-the-loop asset selection through the hosted Assets MCP app.

    7.1k GitHub stars~1.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Game Asset Audit

    Donchitos/Claude-Code-Game-Studios

    Audits game assets against naming conventions, file size budgets and format standards, and finds orphaned assets and missing references.

    26k GitHub stars~2k tokensUpdated 3 days ago
    Game DevelopmentAuto-check passed
  • 3D Asset Generation

    calesthio/OpenMontage

    Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.

    66k GitHub stars~1.2k tokensUpdated 7 days ago
    Game DevelopmentAuto-check passed
  • Game Asset Spec Writer

    Donchitos/Claude-Code-Game-Studios

    Writes per-asset visual specs and AI image-generation prompts for a game's characters, enemies and screens, driven by the GDD, art bible and an entity inventory.

    26k GitHub stars~5k tokensUpdated 3 days ago
    Game DevelopmentAuto-check passed
  • Asset Inventory

    sickn33/agentic-awesome-skills

    Maintain IT asset inventory and configuration management database.

    47k GitHub starsUsed in 2 repos~3.4k tokens
    Auto-check passed
  • Asset It Management

    sickn33/agentic-awesome-skills

    Asset and IT register: serial, model, condition, assignee, location, purchase value, warranty expiry and return date, as CSV, SQL, JSON Schema or Notion on request.

    47k GitHub starsUsed in 1 repo~4k tokens
    Documents & OfficeAuto-check passed

More from ZJU-REAL/Easel

All 114 skills in this repo
  • Gzh Design

    ZJU-REAL/Easel

    微信公众号文章排版引擎:把 Markdown / Word(.docx) / PDF / 纯文本转成可直接粘贴进公众号编辑器的 HTML,自动章节编号、关键词标记、引言卡、目录、代码块、图片/GIF、作者签名;主题从 references/theme-index.md…

    3.4k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • 微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。

    3.4k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Card Design

    ZJU-REAL/Easel

    社媒卡片视觉设计系统:提供配色、中文字体层级、满画幅布局、品类骨架和死空白/密度质检,避免模板化 PPT 与廉价 AI 感。

    3.4k GitHub stars~657 tokensUpdated today
    Auto-check passed
  • Ecom Details Image

    ZJU-REAL/Easel

    生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1.1k tokensUpdated today
    Auto-check: notes
  • Infographic

    ZJU-REAL/Easel

    将数据或文字内容转化为可视化信息图,支持静态(AntV)和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画;要单张静态图片 URL 用 chart-visualization,要 CSV/JSON→整页报告用 data-report

    3.4k GitHub stars~643 tokensUpdated today
    Auto-check passed
  • Novel Writer

    ZJU-REAL/Easel

    长篇小说/网文连载创作:从世界观、人设和三级大纲写到逐章正文,并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1k tokensUpdated today
    Auto-check passed

Questions about Asset Manager

What does Asset Manager do?

outputs/ 目录下的产物管理:按日期/平台/类型归档、打标签、搜索历史内容、生成素材清单. An agent skill from ZJU-REAL/Easel. Asset Manager is an agent skill from ZJU-REAL/Easel.

How do I install Asset Manager in Claude Code?

Run `npx skills add ZJU-REAL/Easel --skill asset-manager -a claude-code`. Or copy the skill folder (skills/openclaw/asset-manager in ZJU-REAL/Easel) into .claude/skills/asset-manager in your project. Claude Code loads it when a task matches its description.

How do I install Asset Manager in Codex?

Run `npx skills add ZJU-REAL/Easel --skill asset-manager -a codex`. Or copy the skill folder (skills/openclaw/asset-manager in ZJU-REAL/Easel) into .agents/skills/asset-manager in your project. Codex loads it when a task matches its description.

Can I use Asset Manager in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJU-REAL/Easel --skill asset-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/asset-manager, .gemini/skills/asset-manager, .github/skills/asset-manager and .opencode/skills/asset-manager in your project.

What does Asset Manager need to run?

Going by SKILL.md and its folder, Asset Manager needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Asset Manager access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Asset Manager safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Asset Manager use?

Asset Manager is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Asset Manager use?

About 964 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Asset Manager?

Skills that share tags, products or a category with Asset Manager: Assets (BuilderIO/agent-native, 7.1k stars), Game Asset Audit (Donchitos/Claude-Code-Game-Studios, 26k stars), 3D Asset Generation (calesthio/OpenMontage, 66k stars) and Game Asset Spec Writer (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Asset Manager?

ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,376 GitHub stars. The repository holds 114 skills in this directory. The repository was last updated on October 9, 2026.

Source: ZJU-REAL/Easel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.