01
It starts by itself
monthly perspective refresh. Runs in Claude Code routine.
- ↻ monthly perspective refresh
0 8 1 * *
Your advisor skills stay up to date.
Install the Huashu Nuwa skill and make it a habit: follow https://gethabit.dev/skills/alchaincyf/huashu-nuwa.md
27K installs36K starsMIT licenceSource on GitHub ↗

Huashu Nuwa
by alchaincyf · 27K installs
The skill
Studies a public person and turns how they think into an advisor skill.
Only when you ask.
Sharper advice
Your advisor skills stay up to date. Better advice from fresher knowledge.
↻ Runs by itselfonce a month
When does it start? How does it check its work? What does it remember?
One perspective skill per run, at most two fix rounds, then ship with weak areas marked.
The agent picks a perspective skill under .claude/skills/ and reads its research date.
Only the conversation, decision and timeline research run again and save to 02, 05 and 06 files.
New facts add cases, mark changed views or suggest a new model.
It updates the latest-news section and research date without rewriting the skill.
It runs quality_check.py on the SKILL.md and fixes failing items.
It shows a change summary and waits for your OK.
It writes only in its own folder and asks you before anything goes out.
Read both lists. If the left one sounds like you, the Huashu Nuwa skill helps.
No. An update only adds new findings and refreshes the date; the rest stays.
The skill bans Zhihu, WeChat public accounts and Baidu Baike as sources for any dimension.
Copy the prompt at the top into your agent. It installs the skill from alchaincyf/nuwa-skill and sets up the habit. Or run npx skills add alchaincyf/nuwa-skill --skill huashu-nuwa.
Yes. It is published under MIT. Habit is free too.
Install the Huashu Nuwa skill and make it a habit: follow https://gethabit.dev/skills/alchaincyf/huashu-nuwa.md
All alchaincyf skills →More notes skills →
Works in
Made by alchaincyf, published under MIT. Habit links to the original and never changes it. Is this your skill?