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-ugc-discoverygit 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-ugc-discovery)<a href="https://agentmods.dev/skills/zju-real/easel/skill-ugc-discovery"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-ugc-discovery/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-ugc-discovery"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-ugc-discovery.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 | $0.00096 | $0.01456 |
| Opus 5 | $0.00048 | $0.00728 |
| Sonnet 5 | $0.00019 | $0.00291 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
skill-ugc-discovery 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UGC 内容发现
搜索与创作者品牌/账号相关的用户生成内容，发现粉丝内容、测评、提及和社区讨论，输出可互动的 UGC 列表。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| brand_keywords | 是 | 品牌名/账号名，可多个（逗号分隔） |
| platforms | 否 | 聚焦平台（小红书/B站/微博/知乎/抖音），默认全平台 |
| content_type | 否 | reviews / mentions / fan_art / complaints / all（默认 all） |
| time_range | 否 | recent / this_month / this_quarter（默认 recent） |
输出
# UGC 内容发现报告
## 发现概览
- 搜索关键词: {keywords}
- 搜索平台: {platforms}
- 发现 UGC 内容: {count} 条
- 正面/中性/负面: {positive}/{neutral}/{negative}
## 高价值 UGC（推荐互动/转发）
| # | 平台 | 内容摘要 | 来源链接 | 互动量估计 | 情感 | 建议动作 |
|---|------|---------|---------|-----------|------|---------|
## 负面反馈（需关注）
| # | 平台 | 内容摘要 | 来源链接 | 严重程度 | 建议回应 |
|---|------|---------|---------|---------|---------|
## 互动建议
- {具体建议: 转发/评论/联动/感谢}
三条发现路径
路径 1 — 平台搜索（主路径）
用 WebSearch 搜索创作者/品牌名相关内容：
搜索关键词组合：
"{账号名} 推荐"/"{账号名} 测评"/"{品牌名} 体验""{账号名} site:xiaohongshu.com"/"site:bilibili.com""{账号名} 好物"/"{账号名} 同款"
按 platforms 参数聚焦平台，未指定时逐平台搜索。
路径 2 — 话题/标签监控
搜索创作者品牌话题和关联标签：
"#{账号名}# site:weibo.com"— 微博话题"#{品牌话题}#"— 跨平台品牌话题"{账号名} 话题"/"{品牌名} 标签"
路径 3 — 社区讨论扫描
搜索论坛、问答社区、讨论帖：
"{品牌名} 怎么样"/"{产品名} 好用吗"— 知乎/贴吧"{品牌名} 值得买吗"/"{账号名} 靠谱吗"— 购买决策讨论"{品牌名} 吐槽"/"{品牌名} 避坑"— 负面反馈定向搜索
执行步骤
- 确认关键词：从用户输入获取 brand_keywords。若有 Profile，从
identity.md补充账号名、品牌名、产品名等关键词。 - 确定搜索范围：根据 platforms 参数确定目标平台；根据 content_type 调整搜索关键词侧重（reviews 侧重"测评/推荐"，complaints 侧重"吐槽/避坑"）。
- 执行三条路径：
- 路径 1：对每个平台执行 2-3 组关键词搜索（WebSearch）
- 路径 2：搜索品牌话题和标签
- 路径 3：搜索社区讨论
- 内容采集：对搜索结果中高相关的链接，用 WebFetch 获取内容摘要和互动数据。
- 去重与分类：去除重复结果，按情感倾向分类（正面/中性/负面）。
- 情感判断：基于内容文本判断情感倾向，区分事实性提及和评价性内容。
- 价值排序：按互动量和内容质量排序，筛选出高价值 UGC（值得互动/转发的内容）。
- 负面标注：单独列出负面反馈，按严重程度排序，给出建议回应策略。
- 互动建议：针对高价值 UGC 给出具体互动建议（转发并感谢 / 评论区互动 / 联动合作邀约）。
- 输出报告：按输出模板生成完整报告，保存到
outputs/。
Profile 感知
有 Profile 时：
- 读取
identity.md获取账号名、品牌名、产品线关键词，自动扩展搜索关键词 - 读取
platforms.md确定活跃平台，优先搜索这些平台 - 读取
audience.md判断哪些 UGC 来自目标受众群体（更具互动价值） - 读取
style.md匹配互动建议的语气和方式
What ships with it
1 file 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 First seen · 115 lines · 96 tokens per session scan A a88d0bbf2eff
skill-ugc-discovery is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 96 tokens to every session and 1,456 once invoked, about $0.0005 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 2026-09-03.
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.