Agent skill

Auto Sync

by autopus-ai in autopus-ai/autopus-adk

문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다. An agent skill from autopus-ai/autopus-adk.

MITAuto-check passedDevelopment

Install Auto Sync

skills CLI
$ npx skills add autopus-ai/autopus-adk --skill auto-sync -a claude-code

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

GitHub CLI
$ gh skill install autopus-ai/autopus-adk auto-sync --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/autopus-ai/autopus-adk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.omp/skills/auto-sync .claude/skills/auto-sync && 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
auto-sync
GitHub stars
111
Token cost
~1.1k tokens
SKILL.md length
591 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다. An agent skill from autopus-ai/autopus-adk.

  • Works in 6 steps: SPEC 상태 → completed → API 문서 갱신 → 아키텍처 다이어그램 업데이트 → …
  • Tasks that involve Changelog and release notes
  • SKILL.md covers OMP Invocation, 설명, 사용법 and Codex 기본 실행 모델, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Auto Sync is an agent skill from autopus-ai/autopus-adk. 문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: omp

It sits in Development, covering Changelog and release notes. The repository describes itself as: Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking… The licence is MIT.

When your agent uses it

  • Tasks that involve Changelog and release notes

Example prompts

  • “/auto-sync”

Requirements

  • Compatibility (from SKILL.md): omp

Workflow steps

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

  1. SPEC 상태 → completed
  2. API 문서 갱신
  3. 아키텍처 다이어그램 업데이트
  4. Lore 의사결정 기록
  5. CHANGELOG 갱신
  6. Lore 형식 자동 커밋

What it can do on your machine

Read from SKILL.md and the folder at commit 3f15677. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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.

  • Compatibility

    omp

    From compatibility in the SKILL.md frontmatter.

Context cost

Auto Sync loads about 1.1k tokens when it runs. Until then it costs about 13 tokens; SKILL.md has 591 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~13
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from autopus-ai/autopus-adk at commit 3f15677, republished under its MIT licence (© autopus-ai). 591 words, ~1,117 tokens.

Download SKILL.mdSave it as .claude/skills/auto-sync/SKILL.md (or your agent's skills folder).
name
auto-sync
description
문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다
compatibility
omp

auto-sync — 문서 동기화 스킬

OMP Invocation

  • /auto sync ...
  • /auto-sync ...
  • Load detail skill auto-sync for either entrypoint.

프로젝트: autopus-adk | 모드: full

설명

구현 완료 후 코드와 문서를 동기화합니다.

사용법

/auto-sync SPEC-ID
/auto-sync

Codex 기본 실행 모델

  • Codex에서는 sync도 기본적으로 task batch 기반 subagent-first를 따릅니다.
  • 메인 세션은 동기화 범위 결정, 최종 상태 갱신, 커밋 판단을 담당합니다.
  • 변경점 검토, 문서 영향 분석, 검증 로그 정리는 필요 시 서브에이전트로 위임합니다.
  • 사용자가 --auto 또는 --solo를 명시하지 않았고 현재 Codex 런타임 정책이 암묵적 task batch 호출을 제한하면, 진행을 멈추고 하네스 기본값과 제약을 명시한 뒤 서브에이전트 opt-in 또는 --solo 확인을 먼저 받아야 합니다.
  • 변경 범위가 작으면 메인 세션에서 직접 마무리할 수 있습니다.

동기화 항목

  1. SPEC 상태 → completed
  2. API 문서 갱신
  3. 아키텍처 다이어그램 업데이트
  4. Lore 의사결정 기록
  5. CHANGELOG 갱신
  6. Lore 형식 자동 커밋

구조 문서 동기화

구조 변경이 감지되면 다음 문서를 함께 갱신합니다.

  • ARCHITECTURE.md
  • .autopus/project/structure.md
  • .autopus/project/tech.md
  • .autopus/project/product.md
  • .autopus/project/workspace.md

특히 repo 경계, 빌드/릴리스 스크립트, desktop/browser/API surface가 바뀌면 workspace.md의 QA/Journey Pack 대상 리포와 auto qa init --project-dir <repo> 명령도 함께 갱신합니다. meta workspace의 root .autopus/qa/**는 runtime/generated evidence로 취급하고 제품 리포 Journey Pack 위치와 섞지 않습니다.

@AX Lifecycle Management

동기화 시 코드베이스의 @AX 태그 수명주기를 관리합니다.

TODO Cycle Tracking
  1. @AX:TODO 태그를 찾습니다.
  2. @AX:CYCLE:N 카운터를 증가시키거나 없으면 @AX:CYCLE:1을 추가합니다.
  3. CYCLE이 3 이상이면 @AX:WARN 으로 승격하고 이유를 기록합니다.
ANCHOR Fan-In Verification
  1. @AX:ANCHOR 태그를 찾습니다.
  2. 함수 참조 수를 grep 기반으로 점검합니다.
  3. caller count가 3 미만이면 @AX:NOTE 로 내리고 이유를 갱신합니다.
NOTE Cleanup
  1. 특정 함수/심볼을 참조하는 @AX:NOTE 를 찾습니다.
  2. 해당 함수/심볼이 아직 존재하는지 확인합니다.
  3. orphan NOTE는 제거합니다.

품질 게이트

  • 에러: 0 / 경고: 최대 10

Lore 커밋

동기화 완료 후 변경 파일을 Lore 형식으로 자동 커밋합니다.

  • SPEC-ID가 있으면: docs(<scope>): sync SPEC-{ID} 문서 및 상태 갱신
  • SPEC-ID가 없으면: docs(sync): 프로젝트 문서 동기화
  • 구현 코드 포함 시 SPEC 주요 타입(feat, fix 등) 사용
  • 변경 사항 없으면 커밋 생략
2-Phase Commit
  1. Module repo 커밋: {TARGET_MODULE} 내부 SPEC 및 모듈 변경
  2. Meta repo 커밋: 루트 문서(ARCHITECTURE.md, .autopus/project/, CHANGELOG.md)

판단 기준:

  • {TARGET_MODULE}/ 내부 파일 → module commit
  • 루트 문서 → meta commit
  • 구현 코드가 포함되면 SPEC의 주요 타입(feat/fix/refactor 등) 사용
  • 문서만 바뀌면 docs 사용
Show full SKILL.md (246 more words)Show less

Completion Gates

sync 완료를 선언하거나 workflow lifecycle bar를 표시하기 전에 아래 gate를 모두 기록해야 합니다.

  1. Context Load 결과
    • 읽은 프로젝트 컨텍스트 파일 목록 또는 missing/no-op 사유를 남깁니다.
  2. SPEC Path Resolution 결과
    • SPEC_PATH, TARGET_MODULE, WORKING_DIR를 명시합니다.
  3. Completion Verdict 결과
    • Outcome Lock 만족 여부, mandatory requirements 충족 수, Must acceptance 충족 수를 기록합니다.
    • Completion Debt가 하나라도 있으면 SPEC 상태를 completed로 바꾸지 말고 blocked reason을 남깁니다.
    • Evolution Ideas는 사용자에게 optional improvement로만 표시하고, 자동 follow-up SPEC이나 sibling SPEC으로 추천하지 않습니다.
  4. @AX Lifecycle Management 결과
    • TODO/ANCHOR/NOTE 처리 결과를 남기고, 대상 태그가 없으면 @AX: no tags found, annotation을 요청하지 않은 실행이면 @AX: not requested로 기록합니다.
  5. Lore 커밋 결과
    • 변경 사항이 있으면 Lore 커밋을 시도하고 commit hash를 남깁니다.
    • 커밋이 실패했거나 보류되면 blocked reason을 남기고 sync를 completed로 선언하지 않습니다.
  6. 2-Phase Commit 판단 결과
    • module commit / meta commit / skip 중 무엇을 했는지와 이유를 남깁니다.
  7. 완료 출력 순서
    • 완료 배너, workflow lifecycle bar, 다음 단계 추천은 위 gate가 모두 기록된 뒤에만 표시합니다.

Completion Verdict Format

markdown
## Completion Verdict
- Outcome Lock: satisfied / blocked
- Mandatory requirements: N/N
- Must acceptance: N/N
- Completion Debt: none / {items}
- Evolution Ideas: surfaced as optional, not scheduled

Branding Formats

Workflow Lifecycle (show after sync completes)
🐙 Workflow: {SPEC-ID}
  ✓ plan  →  ✓ go  →  ● sync
Milestone Celebration (show when full pipeline completes)
╭────────────────────────────────────╮
│ 🐙 파이프라인 완료!                 │
│ {SPEC-ID}: {title}                 │
│ 태스크: N/N | 커버리지: N%          │
│ 리뷰: {verdict}                    │
╰────────────────────────────────────╯

Field mappings: {title} from spec.md, N/N = completed/total tasks, {verdict} = APPROVE or N/A.

Next Step Auto-Detection (show after sync completes)
다음 단계: {recommendation}

Detection order:

  1. SPEC status completed → 🐙 {SPEC-ID} 완료. 다음 기능: /auto plan "기능 설명"
  2. Existing pending SPECs created by an approved Sibling SPEC Decision exist → recommend next SPEC to implement
  3. Do not recommend or create pending SPECs from Evolution Ideas
  4. Always append: 배포 후 검증: /auto canary

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

Files

Just SKILL.md in .omp/skills/auto-sync of autopus-ai/autopus-adk.

Open the folder on GitHubat commit 3f15677

Compare with similar skills

Auto Sync 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.

Auto Sync compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Auto Sync this skillautopus-ai/autopus-adk111—~1.1kAutomated safety check: PassMIT
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
StarRocks Release NotesStarRocks/starrocks12k—~1.9kAutomated safety check: NotesApache-2.0
Cutting A ReleaseTriliumNext/Trilium38k—~3.2kAutomated safety check: PassAGPL-3.0
React Router Release Notes Prepremix-run/react-router57k—~1.1kAutomated safety check: PassMIT
Mole CLI Release Flowtw93/Mole70k—~2.5kAutomated safety check: PassGPL-3.0

Similar skills

  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • StarRocks Release Notes

    StarRocks/starrocks

    Drafts English release notes for a StarRocks patch release from the PRs merged into its release branch, then opens a documentation PR and hands translation to /translate.

    12k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check: notes
  • Cutting A Release

    TriliumNext/Trilium

    A skill your agent uses when cutting, preparing, or debugging a Trilium release — bumping the monorepo version, tagging, or diagnosing a failed "Release" workflow run.

    38k GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check passed
  • React Router Release Notes Prep

    remix-run/react-router

    Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.

    57k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Runbook for assessing and executing a Mole CLI release: distribution channels, pre-flight checks, capital-V tags, build artifacts and the handoff to curated release notes.

    70k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Release

    PrefectHQ/fastmcp

    Cut a FastMCP release end to end. An agent skill from PrefectHQ/fastmcp.

    28k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed

More from autopus-ai/autopus-adk

All 11 skills in this repo
  • Auto Idea

    autopus-ai/autopus-adk

    아이디어 브레인스토밍 — 멀티 프로바이더 토론과 ICE 평가로 아이디어를 정리합니다. An agent skill from autopus-ai/autopus-adk.

    111 GitHub stars~2.4k tokensUpdated 4 days ago
    Auto-check passed
  • Auto QA

    autopus-ai/autopus-adk

    QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence

    111 GitHub stars~2.3k tokensUpdated 4 days ago
    Auto-check passed
  • Auto Setup

    autopus-ai/autopus-adk

    프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다

    111 GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed
  • Ax Annotation

    autopus-ai/autopus-adk

    @AX code annotation workflow skill for agent-driven tag application

    111 GitHub stars~1k tokensUpdated 4 days ago
    Auto-check passed
  • Browser Automation

    autopus-ai/autopus-adk

    터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증. An agent skill from autopus-ai/autopus-adk.

    111 GitHub stars~2.1k tokensUpdated 4 days ago
    Auto-check passed
  • Codebase Design

    autopus-ai/autopus-adk

    작은 인터페이스 뒤에 많은 동작을 숨기는 deep module을 설계하기 위한 공용 어휘(module, interface, seam, adapter, depth)와 원칙

    111 GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about Auto Sync

What does Auto Sync do?

문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다. An agent skill from autopus-ai/autopus-adk. Auto Sync is an agent skill from autopus-ai/autopus-adk.

When should I use Auto Sync?

Auto Sync fits situations like: tasks that involve Changelog and release notes.

How do I install Auto Sync in Claude Code?

Run `npx skills add autopus-ai/autopus-adk --skill auto-sync -a claude-code`. Or copy the skill folder (.omp/skills/auto-sync in autopus-ai/autopus-adk) into .claude/skills/auto-sync in your project. Claude Code loads it when a task matches its description.

How do I install Auto Sync in Codex?

Run `npx skills add autopus-ai/autopus-adk --skill auto-sync -a codex`. Or copy the skill folder (.omp/skills/auto-sync in autopus-ai/autopus-adk) into .agents/skills/auto-sync in your project. Codex loads it when a task matches its description.

Can I use Auto Sync 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 autopus-ai/autopus-adk --skill auto-sync -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-sync, .gemini/skills/auto-sync, .github/skills/auto-sync and .opencode/skills/auto-sync in your project.

What does Auto Sync need to run?

SKILL.md names no scripts, command-line tools or credentials: Auto Sync is instructions for the agent only. Compatibility (from SKILL.md): omp.

Does Auto Sync 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 Auto Sync 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. Review the folder before installing.

What licence does Auto Sync use?

Auto Sync is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Auto Sync use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Auto Sync?

Skills that share tags, products or a category with Auto Sync: Simple English (moeru-ai/airi, 50k stars), StarRocks Release Notes (StarRocks/starrocks, 12k stars), Cutting A Release (TriliumNext/Trilium, 38k stars) and React Router Release Notes Prep (remix-run/react-router, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Auto Sync?

autopus-ai (a GitHub organization) maintains it in autopus-ai/autopus-adk, which has 111 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 4, 2026.

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