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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/xhs-note-creatorWrote 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/xhs-note-creator)<a href="https://agentmods.dev/skills/zju-real/easel/xhs-note-creator"><img src="https://agentmods.dev/badge/skills/zju-real/easel/xhs-note-creator/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/xhs-note-creator"><img src="https://agentmods.dev/badge/skills/zju-real/easel/xhs-note-creator.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 | $0.00125 | $0.02491 |
| Opus 5.5 | $0.00050 | $0.00996 |
| Sonnet 5.5 | $0.00025 | $0.00498 |
| Haiku 4.5 | $0.00013 | $0.00249 |
Grade A, and why
xhs-note-creator 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 14d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书笔记创作
把一个主题 + 可选素材，生成图文卡片组或短视频分镜脚本，按规范输出到 outputs/。
核心理念
小红书读者看的不是长文，是卡片组或短视频。长文原稿只是中间产物。
- 图文帖：3-9 张 3:4 竖版卡片（cover + content × N + ending），每张 ≤80 字
- 视频帖：15-90 秒竖屏视频分镜 + 封面卡
爆款 5 大原则
- 真实素材优先：截图、对比图 > 纯 AI 生图
- 聚焦核心卖点：用公式判断优先级（稀缺性 × 实用性 × 可感知）
- 高级感视觉（走 card-design，别做糙卡）：卡片视觉统一走 card-design 设计系统（选风格锁 spec、字大字细、填满画幅、禁大 emoji 廉价感）。文案要口语化、真实感，但视觉不能糙——想要「素人 / 手账」质感就选 card-design 的手账贴纸 / 奶油温柔风格（仍是高质量 HTML 渲染，不是糙 t2i 大 emoji）。
- 痛点导向："能解决什么问题" > 堆砌功能列表
- 快速迭代：V1(60 分) → 用户反馈 → V2(70 分)
详细方法论：references/xiaohongshu-viral-methodology.md
工作流
按顺序执行，不要跳步。
Step 0 — Intake（必问，一次问完）
- 主题 / 目标读者 / 核心观点
- 输出形态：图文 or 视频？（默认图文）
- 素材：有无现成文字/图片/视频？
- 风格：视觉风格走 card-design 风格库（9 种：瑞士极简/杂志编辑/新中式墨韵/奶油温柔/多巴胺 Y2K/高奢黑金/手账贴纸/极客终端/植物清新）——在 Step 5A 出卡时由 card-xiaohongshu 引导选定，这里先不锁死。
- 卡片数量 / 视频时长：图文默认 5-7 张；视频默认 30-60 秒
Step 0.5 — 卖点/亮点分析（推广/分享/测评类必做）
- 列出所有功能/特性/亮点
- 让用户对每个点打分：
- 稀缺性（1-5）：别人有吗？
- 实用性（1-5）：解决多大问题？
- 可感知（1-5）：用户能直接看到吗？
- 得分 = 稀缺性 × 实用性 × 可感知
- 选 Top 1-2 作为核心卖点
Step 1 — 素材清点（有素材才做）
如果用户提供了素材，先用脚本生成清单：
python3 skills/builtin/xhs-note-creator/scripts/analyze_material.py <path>... \
--out <work-dir>/reference/materials.json \
--frames-dir <work-dir>/reference/frames
素材价值排序：对比图 > 功能演示 > 数据图表 > 品牌素材
Step 2 — 采集外部参考（观点类/资讯类必做）
按 references/reference-search.md 执行，核心数据 ≥2 个来源交叉验证。
Step 3 — 写长文原稿（2000-4000 字）
从 H2 开始（不写 H1），写完先给用户确认再继续。
Step 4 — 去 AI 化（强制）
去 AI 感规则统一走 text-polisher 权威源，不在本 SKILL 维护副本：
- 中文规则（含小红书素人感/闺蜜语气/emoji 节奏特化）→
../text-polisher/references/zh-ai-markers.md - 通用填充短语 →
../text-polisher/references/phrases-to-remove.md - 公式化结构 →
../text-polisher/references/structures-to-avoid.md
按其五层原则完整扫描重写，质量评分满分 50。
Step 5 — 分发：图文 or 视频
5A. 图文帖：拆成 3-9 张卡片
- cover（第 1 张）+ content（中间）+ ending（最后 1 张）
- 每张 ≤80 字
- 一张卡只讲一个论点
- 全套配色/字体/风格保持一致（由 card-design 选中的那一套贯穿整组）
What ships with it
13 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.
- EASEL-META.md 554 B
- references/image-sourcing.md 3.8 KB
- references/material-intake.md 5.4 KB
- references/meta-schema.md 4.6 KB
- references/output-spec.md 2.3 KB
- references/reference-search.md 2.9 KB
- references/xiaohongshu-viral-methodology.md 7.3 KB
- scripts/analyze_material.py 4.9 KB runs code
- scripts/collage_3x4.py 3.4 KB runs code
- scripts/crop_watermark.py 1.6 KB runs code
- scripts/normalize_slug.py 2.1 KB runs code
- scripts/text_on_image.py 5.0 KB runs code
- scripts/validate_meta.py 5.8 KB runs code
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.
- 14d ago Changed ee6546985dfb
- 1mo ago First seen · 172 lines · 125 tokens per session scan A 1372ff820d27
xhs-note-creator is a skill published in the GitHub repository ZJU-REAL/Easel (4,115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 125 tokens to every session and 2,491 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
bmad-spec
Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and validates existing specs. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec".
bmad-advanced-elicitation
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
jacky-motion2-0
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.
bmad-build
Turns implementation work into working code, reviewed and verified. Use when the user delegates a feature, story, bug fix, or meaningful change; a bare story or issue link counts. Skip obvious, low-risk mechanical maintenance such as small ignore-file, typo-only, formatting-only, or configuration-hygiene edits.…
bmad-retrospective
Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports…
bmad-review
Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit…