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-livestreamgit 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-livestream)<a href="https://agentmods.dev/skills/zju-real/easel/skill-livestream"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-livestream/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-livestream"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-livestream.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 | $0.00126 | $0.01211 |
| Opus 5 | $0.00063 | $0.00606 |
| Sonnet 5 | $0.00025 | $0.00242 |
| Haiku 4.5 | $0.00013 | $0.00121 |
Grade A, and why
skill-livestream 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.
What it actually says
直播策划 + 话术
为直播生成完整方案，覆盖主题策划、流程编排、全场话术脚本，适配带货/知识/娱乐多场景。
输入
| 参数 | 必填 | 说明 |
|---|---|---|
| 直播类型 | 是 | 带货直播 / 知识分享 / 娱乐互动 / 品牌活动 |
| 直播主题 | 否 | 未指定时根据赛道和热点推荐 |
| 直播时长 | 否 | 预计时长（默认 2 小时） |
| 商品/内容清单 | 否 | 带货需商品列表，知识直播需分享主题 |
| 目标平台 | 否 | 抖音 / 快手 / 视频号 / 淘宝直播 / 小红书（有 Profile 时自动提取） |
输出
按 references/output-template.md 的骨架生成完整方案（基本信息 / 准备清单 / 流程时间表 / 全场话术脚本 / 互动策划 / 应急预案 / 数据关注点），保存到 outputs/主题名/livestream-plan.md。
执行步骤
领域知识（流程架构、各类型话术结构、互动形式库、应急预案、准备清单）统一见 references/livestream-playbook.md，按需加载。
-
确认直播类型和场景
- 识别类型（带货/知识/娱乐/品牌），明确其核心目标（见 playbook 第一节）
- 用户未指定主题时，根据赛道定位和近期热点推荐 3 个主题选项
-
流程架构设计
- 按 playbook 第一节的"波浪式结构"设计整体节奏
- 带货直播额外规划商品上架顺序（引流款→利润款→福利款→压轴款）
-
开场白设计
- 前 30 秒抓人，含打招呼+自我介绍、亮点预告、互动指令
- 按平台特性调整节奏（见 playbook 第二节）
-
主体话术编写
- 按直播类型套用对应话术结构（带货/知识/娱乐，见 playbook 第三节）
-
互动环节设计
- 规划 3-5 个互动节点穿插主体，每个配完整话术（见 playbook 第四节）
-
过渡语和节奏控制
- 设计环节过渡语，标注节奏/情绪/动作提示（见 playbook 第五节）
-
收尾和引导关注
- 最后 10-15 分钟：总结、预告、引导关注、感谢；带货加福利冲刺（见 playbook 第六节）
-
应急预案编写
- 冷场/负面评论/技术故障/翻车的应对话术（见 playbook 第七节）
-
开播前准备清单
- 设备/内容/平台/团队/状态五类（见 playbook 第八节）
-
输出交付
- 按输出模板生成完整方案；话术口语化，标注时间节点、动作提示、情绪提示
Profile 感知
有 Profile 时：
- 读
identity.md调整话术风格和语气 - 读
audience.md定制互动方式和话题选择 - 读
platforms.md适配平台规则和节奏 - 读
style.md使话术语言风格一致 - 从
identity.md/preferences.md提取变现/商业化信息，优化转化环节设计
无 Profile 时：
- 话术用通用口语风格，流程用通用模板
- 询问关键信息（赛道、人设、目标受众）补充上下文
- 附注"提供 Profile 可获得更贴合人设的话术风格"
规则
- 话术必须口语化，避免书面语和官方说辞
- 每段话术不超过 200 字，保持直播即时感
- 催单话术不可虚假宣传（禁止"全网最低价"等绝对化用语）
- 带货话术需符合广告法，不使用违禁词
- 流程设计必须有弹性，标注可延长/缩短的环节
- 互动环节不少于 3 个，间隔不超过 30 分钟
- 话术中标注明确时间节点，方便主播和场控对表
自研溯源与参考方向见同目录
EASEL-META.md。
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 · 91 lines · 126 tokens per session scan A 70249cf742fc
skill-livestream is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 126 tokens to every session and 1,211 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 2026-09-03.
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.…
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
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.