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 text-polishergit 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/text-polisher)<a href="https://agentmods.dev/skills/zju-real/easel/text-polisher"><img src="https://agentmods.dev/badge/skills/zju-real/easel/text-polisher/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/text-polisher"><img src="https://agentmods.dev/badge/skills/zju-real/easel/text-polisher.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 | $0.00151 | $0.01480 |
| Opus 5 | $0.00076 | $0.00740 |
| Sonnet 5 | $0.00030 | $0.00296 |
| Haiku 4.5 | $0.00015 | $0.00148 |
Grade A, and why
text-polisher 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文本润色
两刀流打磨：系统化编辑提升质量 + 去 AI 感让文字像人写的。
输入
用户提供待编辑的文案文本。可选附加信息：
- 文案目标 — 品牌认知 / 转化 / 留存
- 侧重 — 全面打磨 / 只去 AI 感 / 只改语法风格
- 语言 — 中文 / 英文 / 双语
- 证据素材 — 可用的数字、评价、案例
输出
=== 修改后文案 ===
（完整修改后文本）
=== 评分 ===
| 维度 | 分数 (1-10) | 说明 |
|------|------------|------|
| 清晰度 | X | 是否直接明了？ |
| 节奏感 | X | 长短句变化？ |
| 真实感 | X | 像人写的还是 AI？ |
| 价值密度 | X | 还有可以删的吗？ |
| 语气匹配 | X | 与目标受众/品牌一致？ |
| 总分 | XX/50 | |
=== 主要修改 ===
- 修改点 1
- 修改点 2
...
两道门（顺序固定，都过才交付）：
- AI 味专项自检（前置门） — 中文用
references/zh-ai-markers.md五维（直接性/节奏/信任度/活人感/精炼度），阈值 ≥45/50；不过先改到过，别急着评综合。 - 通用润色五维（综合质量门） — 上表五维，阈值 ≥35/50；不过继续改。
先过 AI 味门，再过综合门——两者量纲相同但把关维度不同，不要混用。
执行步骤
第一阶段：七轮聚焦扫描
每轮只关注一个维度，不做全面修改：
| 轮次 | 维度 | 检查什么 |
|---|---|---|
| 1 | 清晰度 | 主旨是否 5 秒内可抓取？有没有模糊语句？ |
| 2 | 语气 | 是否匹配目标受众？品牌一致性？ |
| 3 | 价值感 | 每段是否提供具体价值？能否加数字/案例？ |
| 4 | 证据 | 论点有没有支撑？数字是否准确？ |
| 5 | 具体性 | "节省时间"→"每周报告从 4 小时缩短到 15 分钟" |
| 6 | 情感 | 是否与读者建立连接？有没有共鸣点？ |
| 7 | 风险 | 是否有歧义、冒犯、法律风险？ |
第二阶段：去 AI 感改写
加载清除清单 → references/phrases-to-remove.md
加载回避结构 → references/structures-to-avoid.md
中文文本 → references/zh-ai-markers.md（中文禁用词/标点/句式/活人感，含小红书平台特化）
8 条核心规则：
- 砍填充短语 — "首先/值得注意的是/毫无疑问/在当今…" 全删
- 打破公式结构 — 不用"不是 X，而是 Y"二元对比；不用修辞设置
- 主动语态 — 每句有人在做事。不让无生命物执行人类动作
- 具体化 — 不写 "reasons are structural"，说出具体原因
- 让读者身临其境 — "你"胜过"人们"，具体胜过抽象
- 变化节奏 — 长短句交替。两项胜过三项。不用破折号
- 信任读者 — 跳过铺垫和辩护，直接陈述事实
- 砍金句 — 听起来像拉引语的句子，重写
第三阶段：自检
- 副词？删掉
- 被动语态？找动作者
- 连续三句长度相近？打断
- "here's what/这里是" 开场白？直奔主题
- 模糊声明？说出具体含义
- 破折号？删掉
中文特有规则
处理中文时，完整规则见 references/zh-ai-markers.md。速查：
- 删除"在…中"冗余结构
- "进行/开展/实施+名词" → 直接用动词
- "对于…来说" → 简化
- "不得不承认/毫无疑问/众所周知" → 删除
- "以前所未有的方式" → 说出具体方式
Profile 感知
- 有 Profile：读取 style.md 匹配创作者风格，不追求通用"像人"而是匹配个人写作习惯
- 无 Profile：改为通用专业/对话体，追求清晰、直接、自然
参考资料
references/phrases-to-remove.md— 填充短语清除清单references/structures-to-avoid.md— 公式化结构回避清单references/zh-ai-markers.md— 中文去 AI 感权威源（禁用词/标点/句式/活人感 + 小红书特化）references/checklist.md— 编辑检查清单references/content-refresh.md— 旧稿翻新策略references/plain-english-alternatives.md— 简洁替代词表
What ships with it
7 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.
- 8d ago First seen · 117 lines · 151 tokens per session scan A 6576f47f0176
text-polisher is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 151 tokens to every session and 1,480 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.
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.