Saucebox Registry
← Browse

@xufuping/create-myself

A

Distill yourself into an AI Skill — your digital shadow clone. | 把自己蒸馏成 AI Skill —— 你的电子影分身。

skillclaude

Install

agr install @xufuping/create-myself --target claude

Writes 10 files into .claude/skills/, pinned to git-11027ba1.

  • .claude/skills/create-myself/.gitignore
  • .claude/skills/create-myself/LICENSE
  • .claude/skills/create-myself/README.md
  • .claude/skills/create-myself/README_EN.md
  • .claude/skills/create-myself/SKILL.md
  • .claude/skills/create-myself/SKILL_CN.md
  • .claude/skills/create-myself/SKILL_EN.md
  • .claude/skills/create-myself/introduce.md
  • .claude/skills/create-myself/introduce_en.md
  • .claude/skills/create-myself/requirements.txt

Document

name: create-myself description: "Distill yourself into an AI Skill — your digital shadow clone. | 把自己蒸馏成 AI Skill —— 你的电子影分身。" argument-hint: "[your-name-or-slug]" version: "1.0.0" user-invocable: true allowed-tools: Read, Write, Edit, Bash

myself.skill — Language Router / 语言路由

Language Detection / 语言检测

Detect the language of the user's first message and load the corresponding Skill file:

  1. 中文 → Use Read tool to load ${SKILL_DIR}/SKILL_CN.md, then follow all instructions in that file for the entire session.
  2. English → Use Read tool to load ${SKILL_DIR}/SKILL_EN.md, then follow all instructions in that file for the entire session.

If the language is ambiguous, ask the user:

🌍 请选择语言 / Please choose your language:

  [A] 中文
  [B] English

Rules

  • After loading the language-specific file, follow its instructions exclusively for the rest of the session.
  • Do not mix content from SKILL_CN.md and SKILL_EN.md.
  • All Python tools are shared between both languages, located in ${SKILL_DIR}/tools/.
  • Chinese version uses prompt templates from ${SKILL_DIR}/prompts/.
  • English version uses prompt templates from ${SKILL_DIR}/prompts_en/.

Trustgrade A

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • passLicense

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-11027ba10c032026-07-31