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-voice-buildergit 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-voice-builder)<a href="https://agentmods.dev/skills/zju-real/easel/skill-voice-builder"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-voice-builder/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-voice-builder"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-voice-builder.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 | $0.00116 | $0.01394 |
| Opus 5 | $0.00058 | $0.00697 |
| Sonnet 5 | $0.00023 | $0.00279 |
| Haiku 4.5 | $0.00012 | $0.00139 |
Grade A, and why
skill-voice-builder 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
声音画像构建
通过结构化访谈 + 写作样本分析,生成个人声音画像(about-me.md + voice.md),确保后续内容创作的品牌一致性。
输入
用户参与访谈并提供 3-5 篇写作样本(小红书笔记、抖音文案、B站文稿、微博帖子、公众号文章等)。
若用户没有样本,可输入 use samples 加载默认样本集 references/sample-content.md。
输出
两个文件,输出至项目根目录(独立的轻量声音产物,不属于 Profile 六维 schema;如需并入画像,可把要点回写到 profiles/<画像>/style.md):
- about-me.md(≤300 词)— 个人定位:身份定位、目标受众、主题支柱、行业观点、人设承诺、内容禁区
- voice.md(≤500 词)— 声音画像:正向信号(怎么写)+ 缺失信号(从不怎么写),合并在同一文件
执行步骤
1. 自动启动访谈
加载即执行,不做任何前言、摘要或确认。第一条消息必须是访谈问题。
禁止:
- 总结本 SKILL 的功能
- 询问用户是否准备好
- 解释将生成哪些文件
2. 分两批提问(共 6 题)
使用 AskUserQuestion 工具,每批最多 4 题。
- Batch 1(4 题):身份定位、目标受众、主题支柱、行业观点
- Batch 2(2 题):人设承诺、内容禁区
问题详情及选项 → interview-questions.md
Batch 1 回答后立即发送 Batch 2,中间不做评论。若有答案为空,单独追问一次后继续。
3. 生成 about-me.md
根据 6 题答案撰写,结构:
# 我的定位
## 身份与定位
## 目标受众
## 内容主题支柱
## 行业观点
## 人设承诺
## 内容禁区
≤300 词。每一行都应是后续创作时可直接引用的信息。
4. 收集写作样本
提示用户粘贴 3-5 篇写作样本。支持一次性粘贴或逐篇发送。
- 最少 3 篇才可进入分析,不足时追问
- 用户输入
use samples→ 加载references/sample-content.md,告知样本作者并提醒可随时替换
5. 分析样本
跨所有样本寻找模式,不依赖单篇特征。
分析维度详情 → voice-analysis-dimensions.md
四个分析维度:
- 声音信号 — 句长、段落节奏、开头风格、人称、语调、标志性短语、CTA 风格
- 结构信号 — 长度范围、列表 vs 散文、开头/结尾模式、过渡手法
- 主题信号 — 跨样本的高频主题、隐含受众、作者立场
- 缺失信号 — 从未出现的词汇/标点、从未使用的开头类型、从未触及的语调
6. 生成 voice.md
综合声音画像,正向信号与缺失信号合并在同一文件:
# 我的声音画像
## 我听起来像谁
## 语气基调
## 句子节奏
## 开头钩子
## 我怎么开头
## 我怎么收尾
## 标志性表达
## 内容禁区
## 这个声音从不做的事
≤500 词。每个章节必须基于样本实证,不得编造。内容禁区 和 这个声音从不做的事 必须有样本缺失证据支撑。
7. 确认完成并提示下一步
告知用户两个文件已就绪,后续创作将自动引用。提示可用的下一步操作。
Profile 感知
- 有 Profile — 从 Profile 中预填受众、平台、调性偏好等已知信息,访谈时跳过已有答案或用于验证;voice.md 中标注与 Profile 的一致性。
- 无 Profile — 完整执行全部 6 题访谈,生成通用声音画像。
规则
- 加载即执行 — 不做摘要、不做解释、直接开始访谈
- 最少 3 篇样本 — 少于 3 篇不启动分析
- 基于实证 — 从样本中提取模式,不编造不存在的特征
- 矛盾保留 — 样本间风格矛盾时如实记录,不做平滑处理
- 字数限制 — about-me.md ≤300 词,voice.md ≤500 词
- 产物格式 — 所有样本内容使用代码块输出,保留换行和空白
- 不重复 — voice.md 不重复 about-me.md 中已有的受众和主题信息
- 语言 — 产物文件默认使用中文(除非样本明确为英文)
- 禁用破折号 — 产物文件和草稿中不使用 em dash
What ships with it
4 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 · 123 lines · 116 tokens per session scan A 22ff695da7fc
skill-voice-builder is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 116 tokens to every session and 1,394 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.…
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.