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-community-opsgit 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-community-ops)<a href="https://agentmods.dev/skills/zju-real/easel/skill-community-ops"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-community-ops/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-community-ops"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-community-ops.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 | $0.00215 | $0.01806 |
| Opus 5 | $0.00108 | $0.00903 |
| Sonnet 5 | $0.00043 | $0.00361 |
| Haiku 4.5 | $0.00021 | $0.00181 |
Grade A, and why
skill-community-ops 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
评论区运营与舆情危机应对
发布后的运营层能力：回复评论、从评论挖选题、负面事件时分级响应。三种模式，命中哪个做哪个。
三种模式
| 模式 | 触发场景 | 核心产出 |
|---|---|---|
| A 评论回复策略 | 有一批评论要回 / 问"评论怎么回" | 分层回复模板 + 分级处理规则 |
| B 评论区选题反哺 | 问"评论区能挖什么选题" / 给了一堆评论 | 3-5 条下一步选题建议 |
| C 舆情危机应对 | 出现负面事件、差评风波、被黑 | 危机分级 + 声明草稿 + 统一口径 + 红线 + 时效 |
一次请求可能命中多个模式（如"评论区吵起来了，帮我回一下顺便看要不要出声明"）。先判定模式，再按对应流程执行。若输入模糊，先问清"是要回评论、挖选题、还是处理负面"。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 评论内容 | 模式 A/B 必填 | 一批真实评论，或"我这类内容常收到 XX 类评论"的场景描述 |
| 负面事件描述 | 模式 C 必填 | 发生了什么、在哪个平台、扩散到什么程度、有无实锤 |
| 目标平台 | 推荐 | 小红书 / 抖音 / B站 / 微博 / 公众号 / 知乎，决定调性 |
| 品牌人设/红线 | 可选 | 无 Profile 时可手动提供，用于定语气和口径 |
模式 A：评论回复策略
- 读
references/reply-playbook.md「一、五类评论分层话术库」，按五类归类用户给的评论：普通赞美 / 专业提问 / 求购买求链接 / 杠精抬杠 / 黑粉恶意差评。 - 每类给 2-3 条可套用的回复模板（用
[占位符]表示品牌名、产品、链接等，不写死具体 case）。 - 按
references/reply-playbook.md「二、分级处理规则」给出处置分级：必回 / 引导私信 / 置顶 / 冷处理 / 删除拉黑，并说明每条评论归入哪级、为什么。 - 按目标平台调语气：读
references/platform-comment-ecology.md对应平台段（小红书亲和、B站梗感、知乎专业、抖音短平快、微博快节奏、公众号克制）。 - 输出：分类回复模板表 + 分级处置清单 + 平台语气提示。
模式 B：评论区选题反哺
- 通读评论，按
references/topic-mining.md「一、评论聚类维度」聚类出高频诉求、重复疑问、争议点、许愿、吐槽。 - 统计每类出现的信号强度（高频 / 中频 / 零星但尖锐）。
- 按
references/topic-mining.md「二、评论转选题公式」把高价值聚类转成 3-5 条具体选题建议。 - 每条选题给：选题标题方向 + 来自哪条/哪类评论 + 为什么值得做 + 建议形式（图文/视频/合集）。
- 输出：评论聚类摘要 + 3-5 条选题建议卡。
模式 C：舆情 / 危机应对
- 读
references/crisis-grading.md「一、危机三级分级标准」，按事件性质、扩散度、是否有实锤、是否触及安全/法律/伦理底线，判定：🟢 可忽略 / 🟡 需回应 / 🔴 需正式声明。给出判定依据（命中了哪几条标准）。 - 按判定档位取对应产出：
- 🟢 可忽略 → 给"不回应/轻回应"的判断理由 + 内部监测建议（盯什么信号会升级）。
- 🟡 需回应 → 按
references/crisis-grading.md「三、回应话术框架」出评论区/私信回应话术草稿。 - 🔴 需正式声明 → 按「四、正式声明结构」出声明草稿（含事实陈述、担责、措施、承诺四段）。
- 出「对外统一口径」：一句话核心立场 + 3-5 条 Q&A 应答口径，确保团队对外说法一致（
references/crisis-grading.md「五、统一口径」）。 - 出「红线清单」：此次绝对不要做的动作（
references/crisis-grading.md「六、危机红线」，如删评控评、甩锅、情绪化对线、大规模拉黑）。 - 出「响应时效建议」：按档位给黄金响应窗口（
references/crisis-grading.md「七、响应时效」）。 - 输出：危机分级结论 + 话术/声明草稿 + 统一口径 + 红线清单 + 时效建议。
Profile 感知
有 Profile 时：
- 读
preferences.md（要做的/不做的/合规底线）→ 回复语气与危机口径贴合品牌人设，不越红线。 - 读
style.md/identity.md→ 回复模板的用词、称呼、梗的尺度对齐账号风格。 - 读
platforms.md→ 自动确定主攻平台的评论调性，无需再问。 - 危机口径遵守
preferences.md「合规底线」，声明不承诺做不到的事。
What ships with it
5 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.
- 10d ago First seen · 85 lines · 215 tokens per session scan A 8858e2bf6575
skill-community-ops is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed yesterday), licensed Apache-2.0. It adds 215 tokens to every session and 1,806 once invoked, about $0.0011 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.