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-brand-onboardinggit 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-brand-onboarding)<a href="https://agentmods.dev/skills/zju-real/easel/skill-brand-onboarding"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-brand-onboarding/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-brand-onboarding"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-brand-onboarding.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 | $0.00112 | $0.01628 |
| Opus 5 | $0.00056 | $0.00814 |
| Sonnet 5 | $0.00022 | $0.00326 |
| Haiku 4.5 | $0.00011 | $0.00163 |
Grade A, and why
skill-brand-onboarding 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
品牌入驻
通过结构化访谈 + 公开信息采集，为创作者/品牌生成完整的 Easel 账号画像（Profile）。
输入
用户提供品牌/账号名称，以及可选的社媒链接、截图、品牌资料。
输出
profiles/<name>/ 目录，包含：
| 文件 | 内容 |
|---|---|
identity.md |
品牌名、定位、使命、差异化、核心产品/服务 |
style.md |
视觉风格、语气调性、内容节奏、Do/Don't 规则 |
audience.md |
目标人群画像、用户语言、痛点与需求 |
platforms.md |
活跃平台、账号信息、发布频率、标签策略 |
preferences.md |
内容支柱、主推产品、禁区话题、合规底线 |
memory.md |
初始为空，后续由归因层更新 |
Phase 0 — 环境准备
- 询问画像名称（英文小写，用于目录名，如
my-brand） - 检查
profiles/<name>/是否已存在：- 已存在 → 摘要现有内容，询问：更新还是重建？
- 不存在 → 继续
- 确保
profiles/<name>/目录存在
Phase 1 — 信息采集
先采集公开信息，再问用户补缺口。
步骤 1：收集社媒链接
向用户询问（有哪些提供哪些）：
- 小红书 / 抖音 / B站 / 微博主页链接或 ID
- 个人网站 / 公众号名称
- 已有的品牌手册、VI 文件、截图（可提供文件路径）
步骤 2：公开信息提取
对每个链接使用 WebFetch 抓取公开页面，提取：
可确认的事实（标注来源）：
- 品牌名、账号昵称、简介/签名
- 所在地、服务范围
- 产品或服务品类
- 品牌价值观（如简介中有声明）
- 社媒数据：粉丝数、获赞与收藏、笔记/视频数
- 视觉观察：封面风格、滤镜偏好、排版习惯、主色调
WebFetch 无法获取的信息标记为待确认缺口。
仅用户能回答的缺口：
- 精确品牌色（hex 值）、字体名称
- 目标人群描述（ICP）
- 主推产品/服务、核心差异化
- 社媒运营目标、当前运营现状
- 标志性内容格式和真实文案示例
- 绝对不做的事
Phase 2 — 预填访谈文档
生成面向用户的访谈文档，写入 outputs/品牌名/品牌入驻.md。
文档四部分：
第一部分 — 我们已经了解的 将 Phase 1 确认的事实以陈述形式呈现，让用户核对纠正。
"以上信息是否准确？有无遗漏或需要纠正的？"
第二部分 — 需要你来回答的（仅真正缺口）
- 目标用户是谁？（ICP）
- 主推产品/服务？
- 和同类账号最大的不同？
- 社媒核心目标？（涨粉 / 带货 / 品牌认知 / 社群 — 选 1-2 个）
- 目前运营节奏？什么效果好/不好？
第三部分 — 素材清单 必须：品牌色值、Logo、产品实拍图（高清原图） 有则更好：场景图、品牌手册、代表性帖子截图、欣赏/想避开的账号
第四部分 — 品牌与内容细节
- 文字排版偏好、标志性内容格式
- 3-5 条真实文案示例（标注"最有价值的输入"）
- 内容支柱（勾选 + 自定义）
- 绝对不发的内容、内容形式比例、近期重要节点
根据品牌调性调整文档语气。
Phase 3 — 素材与回复审核
用户返回填写的文档和素材后：
- 素材处理 — Logo →
profiles/<name>/assets/logo.png；产品图 →assets/products/；场景图 →assets/lifestyle/；示例帖子 →assets/examples/ - 回复整合 — 将用户回答与 Phase 1 采集合并，识别剩余缺口
- 补充确认 — 如有关键缺口，针对性追问（不超过 3 个问题）
Phase 4 — 生成画像档案
将所有信息综合写入 profiles/<name>/ 下各文件。
按 profile-templates.md 中的模板结构生成六个文件：
identity.md— 基本信息、核心产品、差异化、内容方向style.md— 语气调性、视觉风格、标志性格式、文案示例、Do/Don'taudience.md— ICP、用户语言、痛点需求、互动特征platforms.md— 各平台账号数据、内容形式、发布频率、标签preferences.md— 内容支柱、主推产品、禁区、合规底线、运营目标memory.md— 初始为空模板
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 · 156 lines · 112 tokens per session scan A ee1cb152c66a
skill-brand-onboarding is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 112 tokens to every session and 1,628 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
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.