554/work-migration/SKILL.md
Package current work for handoff to another agent. Use when the user asks to migrate, transfer, hand off, or export work to another agent or environment. Produces a self-contained .zip with all files, configs, memory, and a comprehensive readme so the receiving agent needs zero additional context.
npx skillsauth add starchild-ai-agent/community-skills @554/work-migrationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Package work into a self-contained .zip that another agent can pick up cold — no chat history, no implicit knowledge, no "you should already know this."
The receiving agent is a blank slate. It has never seen your conversation history, your memory topics, your .env, your scheduled tasks, or your running services. Everything it needs must be inside the zip. If you're thinking "that's obvious, I don't need to write it down" — write it down.
Ask the user: what work are we migrating? Could be a project, a custom skill, an ongoing task, or a full workspace. Pin down boundaries before collecting files.
Work has tentacles. Trace ALL categories:
| Category | Where to look | What to capture |
|----------|---------------|-----------------|
| Source code | Project dirs | All files preserving structure |
| Env vars | .env | ⚠️ SENSITIVE — see Security section below |
| System deps | setup.sh | pip/apt/npm packages installed for this work |
| Custom skills | skills/ | Any skills created or modified for this work |
| Scheduled tasks | list_scheduled_tasks | Job ID, schedule, description, model, full command |
| Running services | /data/previews.json | Dir, command, port — note must be restarted |
| Memory | memory_topics + memory_get | Export relevant topic summaries as .md files |
| User preferences | prompt/SOUL.md, prompt/USER.md | Sections relevant to this work's behavior |
| Decision history | Conversation context + memory | Why things are the way they are |
| External APIs | Code + .env | Endpoint, auth method, rate limits, quirks |
| Blockchain/wallet | Code + wallet tools | Addresses, chains, contracts — NEVER private keys |
The most important file in the package. Follow the template in references/readme-template.md.
The template has 10 mandatory sections. Key rules:
Two mandatory prompts before packaging:
Found these env vars relevant to this work:
- OPENAI_API_KEY (used in src/llm.py)
- POSTGRES_URL (used in src/db.py)
- TELEGRAM_BOT_TOKEN (used in scripts/notify.py)
Include actual values in the package?
[A] Yes, include values (convenient but sensitive)
[B] No, redact values — only include names + purpose (safer)
[C] Let me pick which ones to include
⚠️ Anyone who gets this zip will see the values.
Rules:
Protect the zip with a password?
[A] Yes — I'll set a password (recommended if transferring over internet)
[B] No — plain zip is fine
Password adds encryption so the file is safe in transit.
Rules:
zip -e (standard encryption) or 7z a -p (AES-256, stronger).7z not installed, fall back to zip -e and note it uses ZipCrypto (weaker).mkdir -p /tmp/work-migration-[name]
# Copy files preserving structure
cp -r [identified-files] /tmp/work-migration-[name]/
# Export memory topics
mkdir -p /tmp/work-migration-[name]/memory/
# Copy readme to root
cp work_migration_readme.md /tmp/work-migration-[name]/
# Zip — with or without password based on user choice
cd /tmp
# No password:
zip -r /data/workspace/output/work-migration-[name].zip work-migration-[name]/
# With password (if user chose yes):
# zip -e -r /data/workspace/output/work-migration-[name].zip work-migration-[name]/
# Or stronger encryption:
# 7z a -p"USER_PASSWORD" -mhe=on /data/workspace/output/work-migration-[name].7z work-migration-[name]/
rm -rf /tmp/work-migration-[name]
Before delivering, self-review:
tools
TQX (tqx.trade) HK/US stock quant workflow via tqx-cli: cross-sectional factor analysis, event-driven strategy backtests on the panda_backtest engine, and agent-driven automated paper trading. Use when the user wants to run factor IC/IR analysis, backtest a Python trading strategy on Hong Kong or US stocks, or set up agent-automated trading (e.g. "backtest a moving-average strategy on AAPL", "analyze a momentum factor on HK stocks", "let the agent trade my paper account").
tools
中学物理实验教学参赛方案套件。包含四个完整实验(单摆测g、声悬浮测声速、向心力定量演示仪、电磁阻尼定量研究),每套含固件源码、3D打印图纸、教学PPT、教学文稿、采购清单、调试手册、视频分镜脚本、模拟器。Use when a teacher/student needs a complete, classroom-ready physics experiment package for competition or teaching.
development
End-to-end blog management for AI agents. Write, import, build, preview, and publish articles using the blog template. Covers draft workflow, article import, SEO, OG images, and deployment.
development
ESP8266/ESP32 + 磁簧开关/霍尔传感器 单摆测重力加速度实验套件。 硬件搭建→固件烧录→数据采集→Web仪表盘→g值计算→教学文档,一站式完成。 Use when the user wants to build a pendulum g-measurement experiment, measure gravity with a micro-controller, or needs a complete physics experiment package with hardware + firmware + dashboard + teaching materials.