agentleFS
choiyounggichoiyounggi/auto-velog/skills/setup/SKILL.md

setup

Skill1 starsChanged 44 days agoMITView on GitHub

auto-velog 최초 설정. 데이터 디렉토리 생성, config 작성, 플랫폼 로그인(쿠키 저장), 비공개 테스트 발행까지 안내. "auto-velog 설정", "auto-velog setup", "블로그 자동화 설정" 등에 트리거.

  • Installs packages

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

Files
SKILL.md

auto-velog 최초 설정

플러그인 루트(이 스킬 기준 ../..)를 $PLUGIN이라 한다. 순서대로 진행한다.

1. 데이터 디렉토리 + config

mkdir -p ~/.auto-velog/{queue,drafts,secrets}
[ -f ~/.auto-velog/config.json ] || cp "$PLUGIN/config.example.json" ~/.auto-velog/config.json

사용자에게 물어 ~/.auto-velog/config.json을 채운다:

  • velog.email — Velog 로그인 이메일 (네이버 메일 주소)
  • velog.username — Velog 아이디 (@아이디)
  • publish.mode — approve(초안+알림까지, 기본) / auto(무인 발행). auto의 의미 (사람 검토 없이 공개 발행됨)를 설명하고 명시적으로 선택받는다.
  • style.referencePosts — 말투를 따라 하고 싶은 블로그 글 URL (선택)
  • secretScan.denyPatterns — 절대 공개되면 안 되는 문자열 정규식 (서버 호스트명, 회사 도메인 등). 최소 1개 이상 넣기를 권장한다.

2. 의존성

cd "$PLUGIN" && npm i --no-fund --no-audit && npx playwright install chromium

3. 플랫폼 로그인 (velog 어댑터)

기존 ~/.claude/scripts/naver-cookies.json, velog-cookies.json이 있으면 ~/.auto-velog/secrets/로 복사해 재사용한다 (재로그인 불필요). 없으면:

  1. node "$PLUGIN/scripts/adapters/velog/save-naver-cookies.mjs" — 브라우저가 열리면 사용자가 직접 네이버 로그인 + 2FA 후 메일함까지 이동 (최초 1회)
  2. node "$PLUGIN/scripts/adapters/velog/login.mjs" — 자동 로그인
  3. node "$PLUGIN/scripts/adapters/velog/check-login.mjs" — STATUS:LOGGED_IN 확인

4. 비공개 테스트 발행

파이프라인 전체를 검증한다:

cat > ~/.auto-velog/drafts/setup-test.md <<'MD'
---
title: auto-velog 설정 테스트 (비공개)
tags: test
---
auto-velog 파이프라인 테스트 글입니다. 보이면 성공.
MD
node "$PLUGIN/scripts/secret-scan.mjs" ~/.auto-velog/drafts/setup-test.md \
  && node "$PLUGIN/scripts/adapters/velog/publish.mjs" ~/.auto-velog/drafts/setup-test.md --private

STATUS:PUBLISHED와 URL이 나오면 성공. 사용자에게 Velog에서 비공개 글을 확인하고 지워도 된다고 안내한다.

5. 운영 안내

마지막으로 다음을 알려준다:

  • 이제 아무 세션에서나 글감이 완결되면 자동으로 포착 → 세션 종료 시 초안 파이프라인이 돈다 (~/.auto-velog/autodraft.log)
  • 일시 정지: touch ~/.auto-velog/PAUSE / 재개: rm ~/.auto-velog/PAUSE
  • 완전 비활성화: 환경변수 AUTO_VELOG_AUTODRAFT=0
  • 밀린 글감 수동 처리: /auto-velog:flush

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.