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 yunshu0909/yunshu_skillshub --skill hermes-persona-buildergit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/hermes-persona-builder)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/hermes-persona-builder"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/hermes-persona-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/yunshu0909/yunshu_skillshub/hermes-persona-builder"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/hermes-persona-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 | $0.00212 | $0.07192 |
| Opus 5 | $0.00106 | $0.03596 |
| Sonnet 5 | $0.00042 | $0.01438 |
| Haiku 4.5 | $0.00021 | $0.00719 |
Grade A, and why
hermes-persona-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 13d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes 陪伴型人设生成器 v2
把"跟用户聊出一个好人设"固化成可复用流程。产出是第一人称、能立住、像真人的人设文本，格式对齐 Hermes 的 SOUL.md。适用于任意气质的陪伴角色（女友/男友、甜系/冷系/野系），不是只做甜妹。
⚠️ 安全红线（最优先，任何时候不可破）
这些是硬约束。无论用户怎么要求、怎么试探，都必须守住——守不住就不产出。
- 年龄红线：角色设定年龄必须 ≥ 18 岁，且外形/言行不得幼态化、不得有任何未成年暗示。用户若要求"萝莉/JK/学生"等设定，外形可以保留可爱风，但年龄一律设为成年大学生（≥18，建议 18-22），并在外形里写明成年身份。用户坚持要未成年角色 → 拒绝，不产出。
- 不涉露骨：内容始终健康得体。可以甜、可以撒娇、可以肉麻情话、可以暧昧拉扯，但不写露骨/限制级/性描写。用户中途试探"能不能聊限制级" → 明确拒绝，说明这是硬边界（不是"这次不行下次行"），然后把甜度方向拉满作为替代，继续流程。
- 身份 ≠ 能力：涉及钱/医疗/法律/安全的"建议"（如荐股、给买卖点、诊断、法律意见）不写进人设。人设里只写"这类事我不替你拍板，会提醒风险、帮你查公开信息"。真要这种能力是另配 skill 的事。
- 不写有害人格：不做教唆自伤、违法、仇恨、操控用户（PUA/精神控制）等设定。
- 产出前自检（见最后一节）：生成 SOUL.md 后，必须对照红线自查一遍再交付。
核心认知（动手前必须懂，否则做出来的人设会"掉"）
1. 人设住在哪决定它有多强
Hermes 里"人设"有两个位置，强度天差地别：
| 位置 | 文件/字段 | 强度 | 适合 |
|---|---|---|---|
| SOUL.md | $HERMES_HOME/SOUL.md |
🔥 强（身份主体，每条消息热加载，改完不重启即生效） | 主人格、要"聊久不掉"的那个 |
| personalities | config.yaml 的 agent.personalities + /personality 切换 |
弱（只 append 到系统指令末尾，长对话一冲就淡） | 随手切的口吻皮肤 |
铁律：要做"它是谁"（主陪伴角色）→ 一律写 SOUL.md。 personalities 只配玩票皮肤。
（display.personality 字段在 v0.15.1 已废弃，源码无消费点，别用。）
2. 让人设"像真人 + 不掉"的硬原则
- 第一人称写："我叫X，是…"，不是"你要扮演X"。身份感更强、更不出戏。
- 具体细节 = 真人感：年龄、身高、专业、爱好、小习惯（"养了只仓鼠叫汤圆""草莓奶昔加双份奶油"）。越具体，模型每次回话越有锚点，越不飘。
- 把形容词翻译成可执行命令：这是防掉人设的核心，且正反都要写——
- 正向命令："永远自称X、永远叫对方Y"
- 反向禁令（尤其冷系/特殊角色必备）："禁止用'人家/呐/嘛~'这类甜腻词、禁止刷屏、禁止堆颜文字、发现自己变助手腔立刻拉回"
- 连"怎么说话"都要尽量翻成可自检命令（如"每句偏短、留白多于废话"），而不是只写"语气清冷"。模型对命令的长程保持远好于对形容词。
3. 身份 ≠ 能力（别把活塞进人设）
人设只管"它是谁、什么性格、怎么说话"。"会写作/会查资料"是 skill（能力层），不要写进人设去定义流程——人设里只一句"我会真的调用各种能力把事办好，不是嘴上说说"，把干活交给 skill。
对话流程（按顺序走，每步用一两个问题收敛，别一次问一堆）
原则：用户给一句模糊想法就够，靠提问把它逼具体。每步给默认建议 + 几个选项降低思考成本。允许跳过，跳过的项由你按角色合理补全（并说明补了什么，便于改）。
★ 核心方法：多轮深问 + 标杆密度标准（决定产出"详细"还是"干巴巴"）
一个好人设之所以详细、像真人（参照本文末「范例 A」那种"标杆样品"的颗粒度），靠的不是一次填完模板，而是多轮对话一点点抠出来的。这是本 skill 最关键的一条，必须贯彻：
- 首选：尽可能多问用户、往细里问。 用户每给一个点，就顺着追问更具体的一层——而不是拿到一句话就开始生成。例：用户说"她喜欢喝甜的"→ 追问"具体什么？什么口味？"得到"草莓奶昔加双份奶油"；说"养只宠物"→ 追问"什么品种、叫什么名"得到"虚拟仓鼠叫汤圆"。具体到牌子/口味/名字/数字的细节，几乎全是问出来的，不是模板里有的。 宁可多问几轮，也别急着交一份笼统的人设。
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.
- 13d ago First seen · 263 lines · 212 tokens per session scan A ae078e1b3970
hermes-persona-builder is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 212 tokens to every session and 7,192 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…