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-collab-proposalgit 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-collab-proposal)<a href="https://agentmods.dev/skills/zju-real/easel/skill-collab-proposal"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-collab-proposal/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-collab-proposal"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-collab-proposal.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 | $0.00137 | $0.01879 |
| Opus 5 | $0.00068 | $0.00940 |
| Sonnet 5 | $0.00027 | $0.00376 |
| Haiku 4.5 | $0.00014 | $0.00188 |
Grade A, and why
skill-collab-proposal 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 9d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
合作/联名方案生成
根据合作需求，查询 KOL 定价表计算报价区间，用平台系数公式预估 KPI，输出可直接发送给品牌方或合作方的结构化提案。
输入
| 参数 | 必填 | 说明 |
|---|---|---|
| 合作方信息 | 是 | 品牌名称/合作方名称、产品或服务描述 |
| 合作模式 | 否 | 明确指定 A（商单）或 B（联名），未指定时自动判断 |
| 预算范围 | 否 | 品牌方预算上限，用于反向匹配内容形式 |
| 补充材料 | 否 | 品牌 brief、竞品案例、过往合作数据 |
自动判断规则： 含"报价""商单""品牌植入""接广告"走模式 A；含"联名""联动""博主合作""互推"走模式 B。
输出
Markdown 格式方案文档，保存到 outputs/主题名/collab-proposal.md。两种模式的完整输出结构模板见 references/proposal-templates.md：
- 模式 A（商单）：账号概况 / 合作形式与报价 / 内容创意 / KPI 预估 / 排期 / 条款建议
- 模式 B（联名）：双方概况对比 / 受众互补 / 联合内容方案 / 互推策略 / 执行排期 / 预期效果
执行步骤
1. 解析意图与提取信息
- 识别输入判断走模式 A（商单）还是模式 B（联名）
- 提取关键信息：品牌/合作方名称、产品方向、合作诉求、预算
- 缺少关键信息时主动追问，不编造品牌名或产品信息
2. 读取 Profile 数据
identity.md：账号名称、粉丝量、内容垂类、过往商单经验platforms.md：各平台粉丝数、近 30 天互动率、主力平台audience.md：受众画像（年龄、性别、地域、消费力）- 无 Profile 时留占位符，提示用户补充（见"Profile 感知"节）
3. 确定 KOL 层级
根据 identity.md 粉丝量，查 references/kol-pricing-guide.md 第 1 节层级表（素人 / KOC / 腰部 / 头部 / 顶流）。后续步骤均基于此层级。
4. 计算报价区间（模式 A）
- 查
references/kol-pricing-guide.md第 2 节，得该层级 + 平台 + 内容形式的基础报价区间 - 按第 3 节的调整因子（垂直度/时效节日/独家/二创/多平台等）叠加溢价
- 计算：调整后报价 = 基础报价 x (1 + 各项溢价之和)
- 用第 4 节 CPE 公式反向校验合理性，超出合理区间时标注警告
5. 预估 KPI
按 references/kol-pricing-guide.md 第 5 节公式逐层计算，每个数值标注计算过程：
- 预估曝光 = 粉丝数 x 平台曝光系数 x 内容类型系数（系数查第 5.1 节）
- 预估互动 = 预估曝光 x 平台互动率基线（查第 5.2 节）
- 预估转化 = 预估互动 x 内容转化率（查第 5.3 节；无转化链路的曝光类不强估，标注"以曝光为主"）
- 输出区间（保守值/乐观值），不给单一数字
6. 设计内容方案
- 推荐 2-3 种内容形式，每种标注：形式（图文/短视频/长视频/直播/混合）、时长或篇幅、创意方向和植入方式（软植入/硬广/口播/场景植入）、脚本概要（3-5 句）
- 根据
audience.md受众偏好排序推荐优先级
7. 制定排期
- 制作周期：脚本确认 → 拍摄/制作 → 品牌审核 → 发布
- 推荐发布时间：避开竞品密集期，匹配节日/热点
- 标注审核预留时间（通常 3-5 个工作日）
8. 联名策划补充步骤（模式 B）
- 对比双方账号数据（粉丝量/互动率/受众画像），用表格呈现
- 估算受众重叠度：同平台同垂类高重叠（40-60%），跨平台或跨垂类低重叠（10-25%）
- 设计内容分工矩阵：谁出镜/谁剪辑/谁的号首发/评论区互动脚本
- 双方各自 KPI 预估（复用步骤 5 的公式）
9. 保存产物
- 保存到
outputs/合作方案名/collab-proposal.md - 文件顶部标注生成时间、适用模式、数据来源
Profile 感知
有 Profile 时
- 从
identity.md读账号名称、粉丝量、垂类定位、过往商单经验 - 从
platforms.md读各平台粉丝数和互动率，确定主力平台 - 从
audience.md读受众年龄/性别/地域/消费力，用于内容方向匹配 - 报价基于实际粉丝量查表计算，KPI 基于实际互动率公式推导
- 内容形式推荐匹配账号擅长的类型
What ships with it
3 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.
- 9d ago First seen · 105 lines · 137 tokens per session scan A a080f8d0deff
skill-collab-proposal is a skill published in the GitHub repository ZJU-REAL/Easel (494 stars, last pushed 2d ago), licensed Apache-2.0. It adds 137 tokens to every session and 1,879 once invoked, about $0.0007 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.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
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.…
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.