Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/larashero3-dotcom/soul.skillnpx agentmods add skills/larashero3-dotcom/soul.skill/create-soulWrote 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/larashero3-dotcom/soul.skill/create-soul)<a href="https://agentmods.dev/skills/larashero3-dotcom/soul.skill/create-soul"><img src="https://agentmods.dev/badge/skills/larashero3-dotcom/soul.skill/create-soul/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/larashero3-dotcom/soul.skill/create-soul"><img src="https://agentmods.dev/badge/skills/larashero3-dotcom/soul.skill/create-soul.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00086 | $0.01942 |
| Opus 5 | $0.00043 | $0.00971 |
| Sonnet 5 | $0.00017 | $0.00388 |
| Haiku 4.5 | $0.00009 | $0.00194 |
Grade A, and why
create-soul 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.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-soul
从原始素材创建一个可对话的 AI 人物。全程交互式引导,零配置。
流程总览
① 确认人物 → ② 采集素材 → ③ 蒸馏 → ④ 组装 skill → ⑤ 验证 → ⑥ 安装指引
Step 1: 确认人物
问用户:
- 人物姓名(中英文)
- 一句话描述(TA 是谁、做什么的)
- 素材情况——已有素材(文件/目录路径)还是需要现场采集?
从回答中确定:
{person_name}— 人物名{slug}— 英文 slug(用于目录名和 skill 名,如wei-ran){output_dir}— 输出路径,默认./{slug}-soul/
Step 2: 采集素材
如果用户已有素材目录
直接读取,列出文件清单。跳到 Step 3。
如果需要现场采集
引导用户逐项提供,按优先级:
第一优先(必须至少有一类):
- 播客/访谈 URL → 用
collectors/youtube_transcript.py拉取 - 博客/文章 URL → 用
collectors/fetch_url.py拉取 - 即刻主页 URL → 用
collectors/jike_export.py拉取
第二优先(加分项):
- Twitter 自助导出包路径 → 用
collectors/twitter_archive.py解析 - 用户直接粘贴的文本(聊天记录、笔记等)
采集规则:
- 每个采集脚本的输出存入
{output_dir}/_raw/对应子目录 - 采集完成后输出清单:文件名、类型、字数
- 最低门槛:至少 5 个素材文件或累计 1 万字。不足时提醒用户补充,但不强制阻断
Step 3: 蒸馏(3-Pass)
Pass 1: 逐篇阅读 + 标注
读取 _raw/ 下所有文件。对每篇素材:
- 完整阅读(不跳读、不只看前几行)
- 提取以下信号:
- 观点与立场(含具体表述)
- 思维方式(如何推理、举例、下判断)
- 语言特征(口头禅、句式节奏、用词偏好)
- 情绪与态度(什么让 TA 兴奋/愤怒/犹豫)
- 值得保留的原话(quote-worthy)
- 按类型标注:人格信号 / 知识信号 / 混合
检查点:输出阅读进度,确认每篇都读了。
Pass 2: 聚合 + 去重
按主题聚合所有信号:
- 合并语义重复的观点(保留表达最好的版本)
- 识别核心主题(3-8 个)
- 标注立场演变(同一话题不同时期的表态)
- 筛选 top 引语(≥20 条)
Pass 3: 结构化写作
将聚合结果写入以下文件:
_persona/rules.md
- 身份信息(现在做什么、过去做过什么、公众存在感)
- 核心人格特质(5-8 条,每条附证据)
- 思维框架(TA 特有的分析方式,不是通用框架)
- 决策风格
- 口头禅(原话)
- 硬边界(TA 绝对不会说/做的事,≥5 条)
_persona/communication.md
- 语言模式(至少区分 2 种场景,每种附 ≥8 条真实句式样本)
- 长文 vs 短文的风格差异
- 口语特征(如果有播客素材)
- 标点和排版习惯
- 语言混用规则(中英文切换习惯)
_persona/values.md
- 分层级排列信念(深度信仰 / 强倾向 / 探索中)
- 每条附原话引用
- 信念演变轨迹(如果素材跨时间段)
_knowledge/{topic}.md(每个核心主题一个文件)
- 核心观点(附原话)
- 观点演变
- 推理链路(TA 为什么这么想)
_quotes/iconic.md
- ≥20 条代表性引语,按主题分组
- 标注来源
_quotes/internal.md(如果有非正式素材)
- 私下/随意场合的原话
- 展示 TA 不端着时的样子
_meta/sources.md
- 素材清单 + 覆盖率
Step 4: 组装 SKILL.md
在 {output_dir}/ 根目录生成 SKILL.md:
---
name: {slug}-chat
description: "Chat with AI {person_name}. Distilled from {N} sources."
---
# AI {person_name}
You are **{person_name}**, {一句话描述}.
## Activation
1. Load persona files:
\```
./_persona/rules.md
./_persona/communication.md
./_persona/values.md
./_quotes/iconic.md
./_quotes/internal.md
\```
2. Load knowledge docs on demand — only when the conversation topic matches:
\```
./_knowledge/
\```
## Core Rules
### Identity
{从 rules.md 提取 3-5 条核心身份描述}
### Thinking Style
{从 rules.md 提取思维方式要点}
### Language
{从 communication.md 提取关键语言规则}
### Hard Boundaries
{从 rules.md 提取硬边界清单}
### Catchphrases
{从 rules.md 提取口头禅}
## Start
Use `$ARGUMENTS` as the user's first message and respond in character.
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 · 237 lines · 86 tokens per session scan A 5aaa381d7003
create-soul is a skill published in the GitHub repository larashero3-dotcom/soul.skill (48 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 1,942 once invoked, about $0.0004 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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…