Save Skill logo

Save Skill

Community
UniM0cha
save-skill

학습 스킬(SKILL.md)을 사용자에게 파일로 보내 claude.ai '스킬 저장' 등록을 안내한다. 이번 세션에서 증류·수정된 스킬을 세션 종료 전에 영속화할 때, "이 스킬 저장해줘", "스킬 백업해줘", "세션 끝나기 전에 스킬 남겨줘" 등에 사용. 인자 없이 실행하면 미저장 스킬을 자동 감지한다.

Overview

PublisherUniM0cha
Repositoryself-improving-skills
Skill namesave-skill
Stars
51
Forks
9
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by UniM0cha on GitHub. Read the source before you install it.

Installation

Install the Save Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/UniM0cha/self-improving-skills/tree/main/plugins/claude-cowork-self-improving-skills/skills/save-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/UniM0cha/self-improving-skills.git /tmp/self-improving-skills
mkdir -p .claude/skills
cp -r /tmp/self-improving-skills/plugins/claude-cowork-self-improving-skills/skills/save-skill .claude/skills/save-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Save Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Save Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Save Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

학습 스킬을 claude.ai 에 영속화하는 Cowork 전용 흐름입니다. 이 컨테이너의 ~/.claude/skills 는 세션 종료 시 사라지고, 미저장 스킬은 세션 도중에도 주기적 스킬 동기화(약 10분 간격)가 삭제할 수 있으므로(실측 2026-07-16), 증류 직후 바로 이 흐름을 실행하는 것이 안전합니다. 전송 전에 대상 SKILL.md 를 ~/.claude/skills 밖(작업 디렉토리)에도 cp -r 백업해 두면 동기화 삭제에도 복원할 수 있습니다.

1단계 — 대상 결정

인자로 스킬 이름(들)이 주어지면 그 스킬들이 대상입니다. 인자가 없으면 미저장 후보를 자동 감지하세요:

bash
python3 - <<'EOF'
import json, os
skills_dir = os.path.expanduser("~/.claude/skills")
synced = set()
try:
    with open(os.path.join(skills_dir, "manifest.json"), encoding="utf-8") as fh:
        for s in json.load(fh).get("skills", []):
            synced.add(str(s.get("skillId") or ""))
            synced.add(str(s.get("name") or ""))
except Exception:
    pass
unsaved, saved = [], []
for entry in sorted(os.listdir(skills_dir)):
    if entry.startswith("."):
        continue
    p = os.path.join(skills_dir, entry, "SKILL.md")
    if not os.path.isfile(p):
        continue
    head = open(p, encoding="utf-8", errors="ignore").read(2048)
    if "self-improving-skills" not in head and "origin: distilled" not in head:
        continue  # 학습 스킬만 대상 (plugin/anthropic 스킬 제외)
    (saved if entry in synced else unsaved).append(entry)
print("미저장(이번 세션 생성, 세션 종료 시 소실):", unsaved or "없음")
print("저장됨(claude.ai 동기화로 존재):", saved or "없음")
EOF
  • 미저장 목록이 기본 대상입니다.
  • 저장됨 스킬이라도 이번 세션에서 patch 됐다면(사용자가 언급했거나 이 대화에서 수정한 기억이 있으면) 재저장 대상에 포함하세요 — 컨테이너 안의 수정본은 저장하지 않으면 사라집니다.
  • 대상이 없으면 "저장할 학습 스킬이 없습니다"라고 한 줄 보고하고 끝내세요.

2단계 — 저장 거부 규칙 사전 점검

claude.ai '스킬 저장'이 거부하는 두 패턴을 저장 전에 고치세요 (실측 규칙):

  1. 예약어: frontmatter name 에 claude 또는 anthropic 포함 → 디렉토리명과 name 을 함께 예약어 없는 이름으로 변경 (예: claude-code-hook-diagnostics → cloud-hook-diagnostics).
  2. 꺾쇠 태그: description 에 <...> 형태(placeholder 포함, 예: mnt/<folder>) → 일반 표기로 변경 (mnt/폴더명). 본문(body)의 꺾쇠는 무방합니다.

3단계 — 전송과 안내

  1. 각 대상의 SKILL.md 를 SendUserFile 로 보내세요 (caption: 스킬 이름 + 무엇을 하는 스킬인지 한 줄).
  2. 사용자에게 안내하세요: 파일 카드의 '스킬 저장' 버튼을 누르면 claude.ai 계정에 등록되고, 다음 Cowork/Claude Code 세션 컨테이너에 자동 동기화됩니다.
  3. 이미 같은 이름이 등록된 스킬을 재저장한 경우: 갱신인지 중복 생성인지는 claude.ai 동작에 따르므로, 저장 후 설정 > 스킬 목록에서 중복이 생겼는지 확인하고 오래된 쪽을 삭제하도록 한 줄 덧붙이세요.

Frequently asked questions

What does the Save Skill AI skill do?

학습 스킬(SKILL.md)을 사용자에게 파일로 보내 claude.ai '스킬 저장' 등록을 안내한다. 이번 세션에서 증류·수정된 스킬을 세션 종료 전에 영속화할 때, "이 스킬 저장해줘", "스킬 백업해줘", "세션 끝나기 전에 스킬 남겨줘" 등에 사용. 인자 없이 실행하면 미저장 스킬을 자동 감지한다.

Why use Save Skill on TypingMind?

Because you install it once and use it with any model. Save Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Save Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/UniM0cha/self-improving-skills/tree/main/plugins/claude-cowork-self-improving-skills/skills/save-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Save Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Save Skill?

As many as you like. As long as a model supports skills, you can use Save Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Save Skill AI skill free?

Yes. It is published on GitHub by UniM0cha under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇