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 style-transfergit 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/style-transfer)<a href="https://agentmods.dev/skills/zju-real/easel/style-transfer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/style-transfer/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/style-transfer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/style-transfer.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 | $0.00167 | $0.01468 |
| Opus 5 | $0.00084 | $0.00734 |
| Sonnet 5 | $0.00033 | $0.00294 |
| Haiku 4.5 | $0.00017 | $0.00147 |
Grade A, and why
style-transfer 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 6d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文案风格迁移
把文案从一种风格改写成另一种风格，保留核心语义，只改表达方式。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
text |
是 | 待改写的原文 |
target_style |
是 | 目标风格（见预设风格列表，或自由描述） |
style_reference |
否 | 一段目标风格的示例文本，用于学习风格特征 |
preserve_keywords |
否 | 必须保留的关键词/术语列表 |
intensity |
否 | 迁移强度：light（微调语气）/ medium（默认）/ full（彻底改写） |
预设风格
详见
references/style-rules.md，含完整执行清单。
| 风格 key | 名称 | 核心规则 | 句式特征 | 禁止事项 |
|---|---|---|---|---|
humorous |
搞笑 | 每 3-4 句至少一个梗点/夸张/自嘲 | 短句为主，反转节奏 | 不用"哈哈哈"、不解释梗 |
colloquial |
口语 | 去掉所有书面连词，用"嗯""就是""反正" | ≤15字/句，多用问句和感叹 | 不用"综上""此外""因此" |
literary |
文艺 | 意象化表达，用比喻代替直述 | 长短交替，有留白 | 不堆砌形容词 |
sharp |
犀利 | 直接下判断，不留余地 | 短促有力，多用句号 | 不用"可能""也许""个人觉得" |
professional |
专业 | 术语准确，逻辑链完整 | 并列/递进结构清晰 | 不用口语化表达 |
healing |
治愈 | 温暖共情，"你"开头的句子多 | 中等句长，节奏舒缓 | 不用反讽/批判 |
sarcastic |
毒舌 | 一针见血指出问题，不留面子 | 极短句+反问 | 不人身攻击 |
social_media |
社交媒体感 | emoji+口语+互动句式 | 分行多，每行≤20字 | 不写长段落 |
custom |
自定义 | 需提供 style_reference |
— | — |
输出
- 改写后的文案（纯文本）
- 风格变更摘要（改了哪些维度：用词、句式、语气、修辞、节奏）
- 写入
outputs/目录，文件名含原风格和目标风格标识
执行步骤
Step 1 — 风格分析
分析原文的风格特征，识别以下维度：
- 用词层：正式/口语、抽象/具体、术语密度
- 句式层：长短句比例、主被动、复句/简单句
- 语气层：客观/主观、冷峻/热情、距离感
- 修辞层：比喻、排比、反问、夸张等手法的使用频率
- 节奏层：段落长度、停顿感、信息密度
Step 2 — 目标风格建模
如果提供了 style_reference：
- 用同样维度分析参考文本，提取风格特征向量
- 识别参考文本的标志性手法（如特定句式、口头禅、节奏模式）
如果使用预设风格：
- 加载预设风格的特征定义
Step 3 — 迁移改写
按迁移强度执行改写：
- 逐段处理，保证语义完整性
- 按优先级调整：语气 → 用词 → 句式 → 修辞 → 节奏
- 保留
preserve_keywords中指定的关键词不变 - 保持原文的信息完整度（不增不减核心信息）
Step 4 — 一致性校验
- 检查全文风格是否统一（避免前后风格不一致）
- 检查核心信息是否保留完整
- 检查
preserve_keywords是否全部保留 - 如果迁移后文意偏移超过阈值，回退该段重写
Step 5 — 输出变更摘要
列出改写涉及的风格维度变化，让用户了解改了什么：
风格迁移: 正式 → 口语化
- 用词: 书面语替换为日常用词 (12处)
- 句式: 长复句拆为短句 (8处)
- 语气: 增加语气词和互动感 (6处)
- 修辞: 移除排比，增加口语化比喻 (3处)
Profile 感知
- 有 Profile：从
style.md读取账号的惯用风格偏好，作为目标风格的微调参考；从identity.md读取品牌调性，确保改写后仍符合品牌边界 - 无 Profile：直接按用户指定的目标风格改写，不做品牌约束
自研溯源与参考项目见同目录
EASEL-META.md。
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.
- 6d ago First seen · 100 lines · 167 tokens per session scan A 0fae73efa972
style-transfer is a skill published in the GitHub repository ZJU-REAL/Easel (494 stars, last pushed 2d ago), licensed Apache-2.0. It adds 167 tokens to every session and 1,468 once invoked, about $0.0008 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.
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.