一键在 Manus 中运行任何 Skill

fleet-divergence-doctor

星标0

分支0

更新时间2026年7月13日 04:16

Diagnose git divergence across the 7 managed ~/thaki repos and emit a SAFE reconciliation plan (read-only, never force-pushes). Use when sod-ship/eod-ship reports push rejected, repos are ahead/behind/diverged, "359/359 발산", history rewrite suspected, "리포 동기화 깨졌어", fleet sync broken. Do NOT use for normal commit/push (use sod-ship) or asset propagation (use claude-sync/cursor-sync).

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

sylvanus4

sylvanus4/github-to-notion-sync

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

fleet-divergence-doctor

Diagnose git divergence across all managed repos and print a safe reconciliation plan. Read-only: never runs push/pull/reset/checkout that mutates state.

Usage

# from repo root (ai-platform-strategy/)
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py

# skip network fetch (offline / fast check)
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --no-fetch

# JSON output for programmatic use
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --json

# check subset of repos
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --repos ai-platform-strategy,realtime-translator

# save plan to file
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --out /tmp/fleet-plan.md

Exit codes: 0 = all clean, 2 = actionable divergence/dirty found, 1 = error.

Managed Repos

Local Dir	Remote	Note
ai-platform-strategy	sylvanus4/ai-strategy	primary
realtime-translator	sylvanus4/realtime-translator
macro-factor-dashboards	sylvanus4/macro-factor-dashboards
github-to-notion-sync	sylvanus4/github-to-notion-sync
ai-template	sylvanus4/cursor-template	remote name differs
research	sylvanus4/research	sync hub
ai-model-event-stock-analytics	hyojunguy/ai-model-event-stock-analytics	different GitHub account

Classifications

Status	Meaning	Safe Command
`clean`	no divergence, tree clean	none
`push-needed`	local ahead only	`git push`
`ff-pull`	remote ahead only, fast-forward safe	`git pull --ff-only`
`diverged-rebase`	both ahead/behind, shared history	`git pull --rebase`
`history-rewrite`	both large + local HEAD unreachable from remote	see below
`no-upstream`	no tracking branch set	`git branch --set-upstream-to=origin/<branch>`
`dirty` overlay	uncommitted changes present	commit or stash first

History-Rewrite Recovery

When classified history-rewrite (e.g., 359/359 divergence from another machine):

git stash                              # save local work
git checkout -B <branch> origin/<branch>   # ← correct recovery
git stash pop                          # restore if needed

Do NOT use git reset --hard origin/<branch> — it is blocked by guardrails. Do NOT use git push --force — this tool never suggests it. Cherry-pick any unique local commits you want to keep BEFORE switching.

Safety

This script only runs read commands (git fetch, git status, git rev-list, etc.). It prints commands for YOU to review and run. It will never auto-execute push/pull/reset/checkout/rebase.

同仓库更多 Skills

同仓库

jarvis

sylvanus4/github-to-notion-sync

Meta-orchestrator that decomposes user goals into agent execution plans with model routing and dependency ordering, optionally pursuing them via Goal Mode with pursuing/paused/achieved/unmet/budget-limited lifecycle states. Maintains a persistent TODO backlog under state/todos/. Pipeline Mode auto-triggers for registered pipelines (report, persona, deep-research, research-report) and executes immediately. Use when: "jarvis", "자비스", "plan how to do X", "decompose this goal", "goal mode", "목표 모드", "pursue this until done", "jarvis goal", "jarvis plan", "자비스 계획", "자비스 목표", "long-running objective", "multi-turn goal", "멀티턴 목표", "장기 목표", "계획 세워줘", "jarvis todo", "자비스 TODO", "보고서 작성해줘", "리포트 만들어줘", "보고서 생성", "분석 보고서", "슬랙에 리포트 보고", "슬랙에 보고서 공유", "리서치해서 슬랙에 보고", "페르소나 분석", "관점 분석해줘", "관점 분석", "딥 리서치", "리서치해서 보고서로". Do NOT use for a single known skill (invoke directly), simple edits, or one-shot tasks. Do NOT use for daily pipeline (use today). Do NOT use for "딥 리서치" without "보고서" → use deep-research-pipeline.

2026-07-140

metis-finetune-eval

sylvanus4/github-to-notion-sync

End-to-end playbook to fine-tune and evaluate an LLM on ThakiCloud Metis (kubeflow-llm-training + vLLM serving on compute-h200). Covers served-model data generation, dataset→S3, TrainJob submission (with every admission gotcha), LoRA adapter serving for inference, and gate-based A/B eval. Use when "모델 학습시켜줘", "파인튜닝 돌려줘", "TrainJob 띄워줘", "학습 전후 평가/A/B", "데모 GPU로 학습", "fine-tune on the cluster", "train and evaluate", "serve the adapter and compare". General across models. Do NOT use for local/Colab training (use colab-unsloth-finetune) or serving-only ops (use demo-llm-inference-test).

2026-07-140

qa-issue-dedup-poster

sylvanus4/github-to-notion-sync

Sync the #ai-platform-internal-qa Slack channel (demo.thakicloud.net QA reports) to a local corpus with full threads, filter out completion-tagged (완료/확인_완료) items, and dedup-check a new QA finding before posting it in the team's expert template. Use when "QA 이슈 올리기 전 중복 체크", "내부 QA 슬랙 싱크", "demo qa 중복 확인", "이 버그 이미 올라왔나", "internal-qa 채널", "check if this QA issue is a duplicate", "post QA finding". Do NOT use for GitHub issue dedup (use github-issue-dedupe), monitor/alert spam throttling (use slack-alert-dedup-cooldown), or general Slack posting (use scripts/slack_post_message.py).

2026-07-140

tds-ui-generator

sylvanus4/github-to-notion-sync

Generate THAKI Design System (@thaki/tds) desktop-console UI from text / sketch / screenshot via a two-stage IR (UX-IR -> TDS-IR) with a deterministic compiler + validation gate + repair loop. Use when "TDS로 UI 생성", "화면 생성기", "디자인시스템 컴포넌트 트리 생성", "UI generator", "screenshot to TDS". Owns the TDS Component Registry (61 primitives) and the synthetic data engine for training a UI-gen model. Do NOT use for freehand React coding (use frontend-design) or Figma sync (use figma-to-tds).

2026-07-140

kakao-emoticon-forge

sylvanus4/github-to-notion-sync

Turn a known cartoon/comic character into a KakaoTalk-quality emoticon set (360x360 transparent, animated). Extracts a clean single-character reference, then generates held-cel sprite sheets with gpt-image-2 (body held, one part moves), splits/keys/stabilizes them, and compiles to KakaoTalk spec + GIF + PNG. Use when "이모티콘 만들어줘", "카카오 이모티콘", "캐릭터 이모티콘화", "움직이는 이모티콘", "emoticon set", "kakaotalk sticker set", "animate my character", "sprite emoticon". Do NOT use for one-off single stickers/messengers other than Kakao (use sticker-forge `stickerforge make`), plain image generation (use gpt-image-2), a pose sheet meant for dance/video (use pose-sheet-to-animation), or video (use video-producer).

2026-07-140

nunchi-map

sylvanus4/github-to-notion-sync

Resume/continue development of 눈치맵 (nunchi-map) — a real-time local crowd/wait/on-site-photo app (대국민 눈치게임): enter a destination, see how crowded it is now, expected wait, and live '지금 뜨는 곳' ranking. Routes to the repos, explains architecture + how to run/verify, and lists the exact next gaps. Use when the user says "눈치맵", "누치맵", "nunchi-map", "대국민 눈치게임", "혼잡도 앱", "지금 뜨는 곳", or asks to continue/extend/deploy that app or its landing page. Do NOT use for ThakiCloud product repos (see [[thaki-platform-repos]]) or generic Go/React scaffolding unrelated to this app.

2026-07-140

name

fleet-divergence-doctor

description

fleet-divergence-doctor

Diagnose git divergence across all managed repos and print a safe reconciliation plan. Read-only: never runs push/pull/reset/checkout that mutates state.

Usage

# from repo root (ai-platform-strategy/)
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py

# skip network fetch (offline / fast check)
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --no-fetch

# JSON output for programmatic use
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --json

# check subset of repos
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --repos ai-platform-strategy,realtime-translator

# save plan to file
python3 .claude/skills/fleet-divergence-doctor/scripts/diagnose.py --out /tmp/fleet-plan.md

Exit codes: 0 = all clean, 2 = actionable divergence/dirty found, 1 = error.

Managed Repos

Local Dir	Remote	Note
ai-platform-strategy	sylvanus4/ai-strategy	primary
realtime-translator	sylvanus4/realtime-translator
macro-factor-dashboards	sylvanus4/macro-factor-dashboards
github-to-notion-sync	sylvanus4/github-to-notion-sync
ai-template	sylvanus4/cursor-template	remote name differs
research	sylvanus4/research	sync hub
ai-model-event-stock-analytics	hyojunguy/ai-model-event-stock-analytics	different GitHub account

Classifications

Status	Meaning	Safe Command
`clean`	no divergence, tree clean	none
`push-needed`	local ahead only	`git push`
`ff-pull`	remote ahead only, fast-forward safe	`git pull --ff-only`
`diverged-rebase`	both ahead/behind, shared history	`git pull --rebase`
`history-rewrite`	both large + local HEAD unreachable from remote	see below
`no-upstream`	no tracking branch set	`git branch --set-upstream-to=origin/<branch>`
`dirty` overlay	uncommitted changes present	commit or stash first

History-Rewrite Recovery

When classified history-rewrite (e.g., 359/359 divergence from another machine):

git stash                              # save local work
git checkout -B <branch> origin/<branch>   # ← correct recovery
git stash pop                          # restore if needed

Safety

This script only runs read commands (git fetch, git status, git rev-list, etc.). It prints commands for YOU to review and run. It will never auto-execute push/pull/reset/checkout/rebase.