AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Prompt Engineering/
nuwa-skill
nuwa-skill logo

nuwa-skill

Active·★ 38.5k·MIT·Updated 2026-11-17
★ Most Popular

nuwa-skill (女娲) is an agent skill created by Alchain that distills the cognitive operating systems, mental models, and decision-making frameworks of prominent thinkers—such as Steve Jobs, Charlie Munger, Richard Feynman, and Naval Ravikant—into custom, queryable agent personas. Departing from conventional surface-level roleplay or famous-quote repetition, the skill focuses on extracting fundamental reasoning primitives, such as Jobs' product-taste focus, Munger's inversion, or Musk's physical-limits reasoning.

The workflow is triggered simply by supplying a thinker's name or background materials. Nuwa autonomously executes a multi-step research and structuring loop: identifying core mental paradigms, distilling recurring decision heuristics, calibrating debate tone, and subjecting the newly formed persona to cross-examination before outputting a reusable prompt and skill module.

Built on the open Agent Skills protocol, Nuwa installs across more than 50 compatible runtimes, including Claude Code (`npx skills add alchaincyf/nuwa-skill`), Cursor, Codex, OpenClaw, and Hermes Agent. Users should keep in mind that Nuwa's effectiveness is strongly bounded by the underlying LLM's reasoning depth; running on lightweight models can degrade outputs into conversational mimicry. Furthermore, it serves as a creative catalyst and brainstorming sounding-board rather than a substitute for rigorous professional or legal analysis.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-12.

License
MIT
Latest release
v2.0.1 · 2026-11-10
Last commit
2026-11-10
Contributors
4
Forks
4,881
Open issues and PRs
24
First published
2026-04-05

Source: GitHub, npm and PyPI public APIs.

#agent-skills#ai-agents#claude-code#claude-code-skills#claude-skills#codex#cursor#decision-making
$ Install
$ npx skills add alchaincyf/nuwa-skill
↗ Visit site★ GitHub
01

Features

01Researches source material about a selected person.
02Organizes cognitive frameworks and expression patterns.
03Produces skills usable in compatible agent hosts.
02

Why choose it

+Focuses on deep mental model extraction and decision heuristics rather than superficial roleplay.
+Automated pipeline handles background research, paradigm structuring, and persona validation.
+Standard Agent Skills compliance enables immediate deployment across 50+ AI runtimes.
+Excellent for strategic brainstorming, product dilemma reframing, and cognitive stress-testing.
03

Trade-offs

!Output depth heavily relies on the host model; lightweight models frequently collapse into generic quote parroting.
!Niche or historical figures with sparse public writing yield shallow, overly broad generalizations.
!The multi-turn distillation research workflow consumes considerable context window and API tokens.
!Speculative and philosophical by nature; cannot replace formal legal, financial, or engineering due diligence.
04

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-10
Commits, last 90 days
10
Releases, last 90 days
3
Latest release
v2.0.1 (2026-11-10)
Open issues
24
Recent issues with at least one comment
15/26
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 1, 0, 0, 0, 0, 0, 0, 3, 1, 0, 2, 3

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #79 Install nuwa skill2 comments · 2026-09-24
  • #74 建议:将 skill 运行时文件收敛到 skills/ 子目录,营销素材移出 skill 树1 comments · 2026-08-11
  • #99 10 comments · 2026-10-27
  • #97 [Enhancement] 将女娲 Skill 的运行内容放在独立的子目录0 comments · 2026-10-23
  • #96 [Enhancement] 为 SKILL.md 中推荐的第三方 Skill 补充安装来源0 comments · 2026-10-23

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

agent-skills
Requires an Agent Skills-compatible host
Verified via docs
06

Quick start

1
$ npx skills add alchaincyf/nuwa-skill
07

Use cases

↳Create a reusable product-review perspective.
↳Compare several approaches to a decision.
↳Build an explanation style from documented source material.
08

Alternatives

⚡Top VS:
VSawesome-agent-skills★37.3k→VShuashu-design★29.7k→VShumanizer★70.4k→VSdarwin-skill★7.0k→
awesome-agent-skills logo
awesome-agent-skills★ 37.3k
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
VSCompare→
huashu-design logo
huashu-design★ 29.7k
Huashu Design 3.0 · 在 agent 里打一句话,拿回能交付的设计:网页 / App 原型 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 84 种带样张的风格库 · 越用越懂你的外观账本与设计体检 · HTML-native design skill for Claude Code, Codex, Cursor & any agent
VSCompare→
video-shotcraft logo
video-shotcraft★ 21.0k
AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.
humanizer logo
humanizer★ 70.4k
Agent skill that removes signs of AI-generated writing from text
VSCompare→
darwin-skill logo
darwin-skill★ 7.0k
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
VSCompare→
pstack logo
pstack★ 4.4k
Use pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering
VSCompare→
taste-skill logo
taste-skill★ 117.7k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
VSCompare→
planning-with-files logo
planning-with-files★ 28.1k
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
alchaincyf /
nuwa-skill
↗

Cognitive framework distillation skill turning real-world thinkers into specialized agents

38.5k4.9kMIT
Last commit1d ago
StatusActive
CategoryPrompt Engineering
Contributors4
Latest releasev2.0.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.