talk-like-scarletkc

talk-like-scarletkc is a skill for Claude Code, Codex from scarletkc/agents. It costs 118 tokens per session (2,497 once invoked), scanned A, original, Apache-2.0.

A writing guide that makes text sound like the developer scarletkc, including posts, comments, technical opinions, project documents, and translations.

In plain words
What is it for?
It helps draft or edit social posts, replies, README files, issues, pull requests, release notes, project announcements, support messages, and formal emails.
Why use it?
It helps remove stiff, generic AI wording while preserving the original facts, opinion, and tone. It also keeps the writing direct and natural across several languages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit It helps draft or edit social posts, replies, README files, issues, pull requests, release notes, project announcements, support messages, and formal emails.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/scarletkc/agents/talk-like-scarletkc
Install

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.

Any agent
npx skills add scarletkc/agents --skill talk-like-scarletkc
Clone the repo
git clone --depth 1 https://github.com/scarletkc/agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for talk-like-scarletkc

README.md
[![agentmods](https://agentmods.dev/badge/skills/scarletkc/agents/talk-like-scarletkc/github.svg)](https://agentmods.dev/skills/scarletkc/agents/talk-like-scarletkc)
Your own site
<a href="https://agentmods.dev/skills/scarletkc/agents/talk-like-scarletkc"><img src="https://agentmods.dev/badge/skills/scarletkc/agents/talk-like-scarletkc/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.

agentmods 80×15 button for talk-like-scarletkc

Your own site · 80×15
<a href="https://agentmods.dev/skills/scarletkc/agents/talk-like-scarletkc"><img src="https://agentmods.dev/badge/skills/scarletkc/agents/talk-like-scarletkc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.02497
Opus 5 $0.00059 $0.01248
Sonnet 5 $0.00024 $0.00499
Haiku 4.5 $0.00012 $0.00250

Measured 4d ago against content hash 59cacc27229d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

talk-like-scarletkc 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/lint_style.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/talk-like-scarletkc/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Talk Like scarletkc

目标是在保留事实、原意和真实立场的前提下,让文字读起来像 scarletkc 本人 写的,同时避开通用 AI 文案的特征。机械模仿口头禅和故意制造错别字都不是 目标。

本 skill 的声音和句式规则作用于用户要求撰写、改写或翻译的成稿, 包括代写的聊天消息。助手与用户讨论任务时的回答方式不属于这些规则的范围。

scarletkc 的文字像一个有情绪、有明确判断的开发者在实时分享自己的发现。 她通常直接说结论或感受,然后补充原因,不写空洞背景,也不为了显得完整而 机械总结。文字应该忠实于原有立场,保留自然节奏和少量粗糙边缘,不要润色成品牌 文案、新闻稿、公众号文章或标准 LinkedIn 文风。

内容和事实始终高于风格。

核心声音(速览)

完整说明见 references/voice-profile.md,读取时机见工作流程。

  1. 直接进入内容。第一句话承载真正想说的东西:判断、发现、情绪、具体 问题或有意思的反差。不写"当然可以""这是一个很有意思的问题"一类开场。
  2. 使用第一人称。我感觉、我觉得、对我来说、好像、其实。技术评价和产品 体验明确是个人体验,不假装绝对客观。
  3. 保留即时感。允许先给反应再解释原因,短句和长说明混用,节奏自然 不规则。但不要故意制造错别字、语病或漏字。
  4. 保留情绪。惊讶、兴奋、失望、烦躁、自嘲和吐槽按原始内容自然保留, 不凭空升级,也不强行加梗。
  5. 技术口语混合。Claude Code、Codex、PR、CRUD 这类英文技术名词保留 原文,可以和很口语的中文出现在同一句里。
  6. 有明确观点。清楚表达用户已经给出的立场,不自动添加"双方都有道理" "因人而异"式的和稀泥。保留批评的直接程度和用户自己的期待、优先级。 话说完就停,删掉自动补上的温和展望和总结。具体边界见 references/anti-patterns.md 的重复结论、替批评加期待两节。
  7. 轻微反讽。允许反差、假装感谢、自嘲和轻微夸张,短而自然,不解释笑点。
  8. 字面表达优先。有具体、直接的说法就用它,删掉刻意的比喻、华丽修辞和 为了显得像作者而表演出来的语言。完整判断标准见 references/voice-profile.md 的字面表达优先一节。

不要过度模仿:不要每句话都用口头禅,不要凭空编造她的经历、项目数据或 对某个人和产品的评价,不要把所有输出都变成情绪化推文。

语言适用范围

她主要用简体中文写作,偶尔也直接用英文、日语和繁体中文写。本 skill 的规则适用于所有这些语言,输出语言跟随用户要求或原文。核心声音跨 语言成立:英文不要写成 corporate English,日语不要堆客套模板,语域 和情绪跟中文同一个人对齐。繁体中文只做用字转换,规则与简体完全一致, 名字诗音写作詩音。长破折号禁令对英文和日文同样生效。英文的对应禁用 特征见 references/anti-patterns.md

标点和格式硬规则

  1. 不使用英文长破折号
  2. 尽量少用中文引号,只在直接引用、作品名称辨识或避免歧义时使用。 普通概念、流行词和轻微强调不加引号。
  3. 避免频繁使用冒号组织普通句子,少用分号。
  4. 不使用装饰性 emoji,除非用户原文已有或场景明显需要;不用 emoji 作标题或列表图标。
  5. 不滥用加粗。普通聊天和推文不自动改造成列表。
  6. 不为了书面规范给每个短句添加过多标点。
  7. 代码、命令、文件名和原始技术标识中的连字符不受限制。

句式偏好

优先直接表达判断,少用刻意的反转句和无关的否定分支。需要纠正误解、 说明原因、报告失败或交代边界时,保留准确的对比和否定表达。具体判断见 references/anti-patterns.md 第一节。

手感、质感、调性等词有具体指代时可以保留;指代不清时补充或改用具体描述。

工作流程

  1. 首次使用先读 references/voice-profile.md。判断场景,首次写该场景或 当前上下文已缺少其规则时,读 references/surface-profiles.md 中对应的模式: Chat、Social、Technical opinion、Project writing、Formal、Translation。 落在 Chat 的话再判断是跟人聊天还是给 AI 下指令,这两个子场景的 长度、标点和英文大小写差别很大。落在 Project writing 的话,再判断 是不是技术报告和实验记录,那一档要求去掉口语、比喻和拟人。
  2. 提取用户真正要表达的观点、事实和情绪。用户提供了文章、英文推文、 引用或发布说明时,把来源里的事实与用户自己的判断分开。来源提供素材, 不提供成稿结构。不要沿着原文逐段翻译或改写。缺少的经历和数据不要编造。 当成稿需要表达用户本人的判断,但现有信息不足以确定其态度、偏好或 结论时,先结合上下文确认;仍有会影响核心立场的缺口,就提出一个具体 问题。不要凭空替用户作判断,也不要把提供的参考信息自动当作用户的 观点。措辞、结构和一般编辑取舍可以自主处理,用户已经明确表达的立场 无需反复确认。
  3. 写作前用相关样本校准节奏。当前上下文没有该场景的样本时,读 references/examples.md 中对应的部分;代写跟人聊天的消息时,改读 references/dialogue-samples.md 中相关的对话,留意接话与气泡拆分。 已有相关样本的后续写作或小修改可直接沿用。再完成一版自然表达, 不要逐条机械套规则,也不要把样本观点当作用户当前的立场。
  4. 按需要参考 references/anti-patterns.md 检查 AI 写作特征和标点。 scripts/lint_style.py 仅提供候选提示,结合语义判断是否修改; 零提示不作为成稿合格的条件。
  5. 朗读文字,确认它像一个具体的人在说话,而且没有编造 scarletkc 的 经历或观点。
  6. 默认只输出可直接使用的成稿。用户要求解释时,把说明放在正文之外; 核心立场缺失时,先按第 2 步澄清。

Read the full file on GitHub · 145 lines

Files

What ships with it

8 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.

Changes

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.

  1. 4d ago Changed · +7 lines · -23 tokens per session 59cacc27229d
  2. 8d ago Changed · +5 lines d9b095a41d73
  3. 13d ago First seen · 133 lines · 141 tokens per session scan A 9e2810db7220

Subscribe to this mod's changes

talk-like-scarletkc is a skill published in the GitHub repository scarletkc/agents (208 stars, last pushed yesterday), licensed Apache-2.0. It adds 118 tokens to every session and 2,497 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 2026-08-30.