Agent skill

Talk Like Scarletkc

by scarletkc in scarletkc/agents

按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。

Apache-2.0Auto-check passedDevelopment

Install Talk Like Scarletkc

skills CLI
$ npx skills add scarletkc/agents --skill talk-like-scarletkc -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install scarletkc/agents talk-like-scarletkc --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/scarletkc/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/talk-like-scarletkc .claude/skills/talk-like-scarletkc && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
talk-like-scarletkc
GitHub stars
226
Token cost
~1.2k tokens
SKILL.md length
234 words
Files
9 (incl. scripts, references)
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。

  • Works in 8 steps: 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 → 自然使用第一人称。我感觉、我觉得、对我来说、好像、其实。技术评价和 → 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 → …
  • Development work in your project
  • SKILL.md covers 核心声音(速览), 语言适用范围, 标点和格式硬规则 and 句式偏好, plus 5 more sections
  • Runs Python scripts from its folder

What it does

Talk Like Scarletkc is an agent skill from scarletkc/agents. 按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `evals/evals.json`, `references/anti-patterns.md` and `references/dialogue-samples.md`).

It sits in Development. It works with GitHub. The repository describes itself as: Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents. The licence is Apache-2.0.

When your agent uses it

  • Development work in your project

Example prompts

  • “/talk-like-scarletkc”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  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
  2. 自然使用第一人称。我感觉、我觉得、对我来说、好像、其实。技术评价和
  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
  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,
  5. 技术口语混合。Claude Code、Codex、PR、CRUD 这类英文技术名词保留
  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"
  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. 直接表达与解释性类比。用具体说法讲清事实,保留帮助目标读者理解的比喻、

What it can do on your machine

Read from SKILL.md and the folder at commit eb55005. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Talk Like Scarletkc loads about 1.2k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~17k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from scarletkc/agents at commit eb55005, republished under its Apache-2.0 licence (© scarletkc). 234 words, ~1,155 tokens.

Download SKILL.mdSave it as .claude/skills/talk-like-scarletkc/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
talk-like-scarletkc
description
按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。
license
Apache-2.0
metadata.author
scarletkc
metadata.source
https://github.com/scarletkc/agents
metadata.summary
Write and translate in scarletkc's natural voice without generic AI phrasing.

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。

X 的选题和帖文组织见 x-content。 仅调整语气或忠实翻译时使用本 skill。

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。 正文和结尾也不靠预告下一句来卖关子,见 references/anti-patterns.md 的 AI 式铺垫一节。
  2. 自然使用第一人称。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;介绍事实时不必硬加我觉得。
  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. 直接表达与解释性类比。用具体说法讲清事实,保留帮助目标读者理解的比喻、 类比和原稿趣味;需要时可以补充贴切的类比,再接上实际机制。修正会误导的 部分,删除纯装饰性的加工。完整判断标准见 references/voice-profile.md 的直接表达与解释性类比一节。

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,少用刻意的正反对照、排比和对偶。禁止在每句正面或肯定 陈述后惯例式追加“但不代表……”“但不能说明……”等否定、免责声明或自我 反驳。必要条件直接融入当前主张,实际失败和用户要求的对比照实表达。 具体判断见 references/anti-patterns.md 的反转句、原因和对比,以及机械 排比和对偶两节。

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

先按请求确定是起草、整体改写还是局部编辑。用户提供的待修改稿件以最新 版本为基准。微调、局部润色和事实修正只改实现本次要求所必需的词句,其余 句子原样保留,包括结构、开头、类比、情绪和节奏。风格检查也遵守这个范围; 完成后逐处对照原稿,确认每个改动都能对应到本次要求。

  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,那一档用准确术语陈述可核对的事实。
  2. 提取用户真正要表达的观点、事实和情绪。区分外部参考资料与用户要求修改 的稿件:参考资料用于提取事实,待修改稿件按已确定的范围编辑。把来源里的 事实与用户自己的判断分开。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。 修改已有稿件时,默认把局部改动放回原稿,给整合后的完整版本。 用户只要一句或局部时按指定范围返回。

交付前自检

完整清单在 references/anti-patterns.md 末尾。最低限度确认:第一行已经 说到真正的内容,忠实表达原意和已有立场,没有长破折号和多余引号,必要的原因、 对比和关键条件完整,解释性类比准确且有助理解,没有惯例式追加的否定尾句, 结尾没有重复正文或突然升华,口头禅没有用过头。

评测标准优先级

  1. 事实和意图准确
  2. 像 scarletkc
  3. 没有明显 AI 写作痕迹
  4. 符合具体场景
  5. 标点和禁用句式合规

资源

文件内容什么时候读
references/voice-profile.md核心声音的完整说明和边界首次使用,或需要重新校准声音时
references/surface-profiles.md六个场景模式的详细规则首次写该场景,或上下文已缺少其规则时
references/anti-patterns.md句式偏好、AI 写作特征、自检清单按需要检查
references/examples.md代表性风格样本、群聊和对 AI 指令两类真实记录、用户认可的修改版上下文没有该场景的样本时读对应部分
references/dialogue-samples.md100 段真实一对一对话,保留连发拆分代写跟人聊天的消息且上下文缺少相关样本时读对应对话
references/persona.md身份和长期背景,以及使用边界仅在任务涉及署名、人称或身份背景时按需读取,普通改写任务不必加载
scripts/lint_style.py风格检查脚本,只提示不改写交付前可选运行

维护

本 skill 的规范版本在 https://github.com/scarletkc/agents 的 skills/talk-like-scarletkc/。如果你是在复制到本地的副本 (比如 ~/.claude/skills/)里工作,修改了规则或在 examples.md 里 积累了新样本,建议把改动整理成 PR 提回原仓库,否则改进只留在这台 机器上,下次重新安装就丢了。

© scarletkc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in skills/talk-like-scarletkc of scarletkc/agents.

  • SKILL.md
  • evals/evals.json
  • references/anti-patterns.md
  • references/dialogue-samples.md
  • references/examples.md
  • references/persona.md
  • references/surface-profiles.md
  • references/voice-profile.md
  • scripts/lint_style.py

Open the folder on GitHubat commit eb55005

Compare with similar skills

Talk Like Scarletkc next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Talk Like Scarletkc compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Talk Like Scarletkc this skillscarletkc/agents226—~1.2kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Setup Matt Pocock Skillsbestofjs/bestofjs3.1k20 repos~1.7kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Setup Matt Pocock Skills

    bestofjs/bestofjs

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout.

    3.1k GitHub starsUsed in 20 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

More from scarletkc/agents

All 11 skills in this repo
  • Antigravity CLI

    scarletkc/agents

    Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent.

    226 GitHub stars~1.6k tokensUpdated 19 days ago
    Auto-check passed
  • Grok CLI

    scarletkc/agents

    Delegate bounded tasks to Grok Build from a supervising agent such as Codex.

    226 GitHub stars~1.5k tokensUpdated 19 days ago
    Auto-check: warnings
  • Ask To Plan

    scarletkc/agents

    Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices.

    226 GitHub stars~2.4k tokensUpdated 19 days ago
    Auto-check passed
  • Codex CLI

    scarletkc/agents

    When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort.

    226 GitHub stars~2.8k tokensUpdated 19 days ago
    Auto-check passed
  • Marketing Copy

    scarletkc/agents

    Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls…

    226 GitHub stars~1.3k tokensUpdated 19 days ago
    Auto-check passed
  • Scoped Change

    scarletkc/agents

    Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it.

    226 GitHub stars~1.3k tokensUpdated 19 days ago
    Auto-check passed

Works with

Categories

Questions about Talk Like Scarletkc

What does Talk Like Scarletkc do?

按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本,适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔,或在翻译中保留本人语气和立场时使用,无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。. Talk Like Scarletkc is an agent skill from scarletkc/agents.

When should I use Talk Like Scarletkc?

Talk Like Scarletkc fits situations like: development work in your project.

How do I install Talk Like Scarletkc in Claude Code?

Run `npx skills add scarletkc/agents --skill talk-like-scarletkc -a claude-code`. Or copy the skill folder (skills/talk-like-scarletkc in scarletkc/agents) into .claude/skills/talk-like-scarletkc in your project. Claude Code loads it when a task matches its description.

How do I install Talk Like Scarletkc in Codex?

Run `npx skills add scarletkc/agents --skill talk-like-scarletkc -a codex`. Or copy the skill folder (skills/talk-like-scarletkc in scarletkc/agents) into .agents/skills/talk-like-scarletkc in your project. Codex loads it when a task matches its description.

Can I use Talk Like Scarletkc in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add scarletkc/agents --skill talk-like-scarletkc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/talk-like-scarletkc, .gemini/skills/talk-like-scarletkc, .github/skills/talk-like-scarletkc and .opencode/skills/talk-like-scarletkc in your project.

What does Talk Like Scarletkc need to run?

Going by SKILL.md and its folder, Talk Like Scarletkc needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Talk Like Scarletkc access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Talk Like Scarletkc safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Talk Like Scarletkc use?

Talk Like Scarletkc is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Talk Like Scarletkc use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 16k tokens, read only when the agent opens those files.

What are the alternatives to Talk Like Scarletkc?

Skills that share tags, products or a category with Talk Like Scarletkc: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Setup Matt Pocock Skills (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Talk Like Scarletkc?

scarletkc (a GitHub user) maintains it in scarletkc/agents, which has 226 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 21, 2026.

Source: scarletkc/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.