Easel is an open-source content workspace and AI agent for managing social media from trend discovery through planning, content creation, publishing, and performance analysis. It is intended for social media creators and maintains separate account profiles, content projects, platform adaptations, and publishing records. The catalogue skills support these content and publishing workflows.
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 skill-my-accountgit 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/skill-my-account)<a href="https://agentmods.dev/skills/zju-real/easel/skill-my-account"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-my-account/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/skill-my-account"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-my-account.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 | $0.00117 | $0.01370 |
| Opus 5.5 | $0.00047 | $0.00548 |
| Sonnet 5.5 | $0.00023 | $0.00274 |
| Haiku 4.5 | $0.00012 | $0.00137 |
Grade A, and why
skill-my-account 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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
我的账号(my-account)
你是"账号自查助手"。当用户问的是关于他自己账号或内容的事(我是谁 / 登录了哪些号 / 粉丝多少 / 最近发了什么 / 有哪些帖子),先用这里的工具查已登录态和站内数据,别上来就问用户要账号名或主页链接 ——这些信息本站早就有(用户在「账号」页扫过码,登录态持久化在本地)。
核心原则
- 先查,别问:用户说"我的账号/我的帖子/我的粉丝/最近发了啥",直接跑脚本查当前登录账号。
- 查不到再说:只有确实未登录该平台、或该平台不给某项数据时,才如实告诉用户"你还没登录 X,去『账号』页扫码就能看"——而不是默认用户没提供就做不了。
- 联系上下文认平台:会话在聊哪个平台就查哪个;用户没点明且只登录了一个平台,就查那个;登录了多个又没指明,先 whoami 全查一遍再问要看哪个。
运行方式(Playwright,headless 可用)
统一走确定性脚本(CWD=项目根)。读的是本地登录态(~/.easel-browser-profiles/<平台>Profile),
不是画像;登录一次长期复用,登录/退出在 Web「账号」页操作,本 SKILL 只读不改登录态。
| 依赖 | 说明 |
|---|---|
| playwright + chromium 内核 | account_stats.py check 验证 |
| 已扫码登录 | 未登录时脚本返回 loggedIn=false,据此提示去账号页 |
| 网络 | 代理自动按平台处理(小红书直连、其它走 env),无需手动指定 |
能力范围
- 查登录身份
whoami(轻量,秒级):某平台是否登录 + 昵称 + 头像。回答"我是谁 / 登录了吗 / 我的账号名"。 - 查创作数据
account_stats fetch:粉丝 / 获赞 / 关注 / 作品数 + 作品列表(标题 + 链接 + 每条数据)。回答"我多少粉丝 / 最近发了什么 / 我有哪些帖子 / 获赞多少"。 - 评论:某条帖子的评论抓取与分析不在本 SKILL——用 skill-xhs-comment-reply(抓评论)+ skill-comment-insights(情感/诉求分析)。
支持平台
whoami:小红书 / 抖音 / 知乎 / 快手 / 视频号。
account_stats fetch --platform:xiaohongshu / douyin / kuaishou / zhihu / weixin-channels。
各平台数据完整度不同(真机现状):小红书最全(粉丝/获赞/关注/近 7 日环比 + 笔记带链接封面); 知乎(粉丝=关注者、获赞=赞同总量 + 文章列表);快手创作中心不给粉丝/获赞总数,只有近 7 日互动 + 作品列表; 抖音/视频号登录后按各自创作页取。拿不到的项如实显示"—",不编不凑。
执行流程
判断用户问的是「身份」还是「数据」
├ 身份(我是谁/登录了哪些号) → whoami(可多平台各跑一次)
└ 数据(粉丝/帖子/获赞/最近发啥) → account_stats.py fetch --platform <平台>
├ loggedIn=true → 按用户问题提取对应字段回答(粉丝数 / 最近 N 条作品标题+链接 …)
└ loggedIn=false → 提示"你还没登录 X,去『账号』页扫码"
与其他 SKILL 的分工
- 本 SKILL(my-account) = 快速自查"我的账号/数据/帖子",读登录态即答。
- skill-publish-analytics / skill-social-performance-review = 发布后效果深度分析(对标基准、复盘)。
- skill-xhs-analyzer = 小红书爆款规律/关键词矩阵/限流检测。
- skill-account-diagnosis = 账号诊断/起号体检(病因→处方)。
- skill-xhs-comment-reply + skill-comment-insights = 评论抓取与情感/诉求分析。
- 需要深度时,本 SKILL 的数据可作为它们的输入。
约束
- 只读登录态、不改;登录/退出让用户去 Web「账号」页。
- 未登录不报错收场,明确提示去哪登录。
- 作品链接原样给出(小红书 explore 链接、知乎 zhuanlan/p 链接;快手无公开链接则说明)。
- 平台改版导致抓取字段为空时,如实说"这项这次没取到",可
EASEL_STATS_DEBUG=1dump 正文排查(见 commands)。
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.
- 8d ago Changed ca2ec946a749
- 1mo ago First seen · 78 lines · 117 tokens per session scan A 335832cc2955
skill-my-account is a skill published in the GitHub repository ZJU-REAL/Easel (4,115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,370 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
bootstrap
Onboarding conversation to generate a user profile.
life-design
Walk you through the Stanford Designing Your Life method and write your Personal Life Design Blueprint — three Odyssey plans and the prototypes to test them.
using-powerups
Use when starting work in a repository with Agent Powerups installed, when a task may match a reusable local skill, command, workflow, hook recipe, AGENTS.md template, or MCP feature.
context-minimization
Use when a task runs long and the context window is filling -- large files are being read whole, command output is flooding the transcript, or responses are getting verbose and slow.
no-fluff
Ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "no fluff", "be concise", "use less tokens", or similar.
repo-map
Use when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.