Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Rheinmir/setup --skill dym-nuwa-skill-installgit clone --depth 1 https://github.com/Rheinmir/setupWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-install)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-install"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-install/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-install"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01331 |
| Opus 5.5 | $0.00029 | $0.00532 |
| Sonnet 5.5 | $0.00014 | $0.00266 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade B, and why
dym-nuwa-skill-install scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/nuwa-skill/SKILL.md # phải tồn tại How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-nuwa-skill-install — Cài nüwa (女娲) vào runtime của bạn
Vì sao dùng: đây là bước bắt buộc đầu tiên — nüwa không phải CLI, nó là một Agent Skill (một file SKILL.md + references/ + scripts/), phải nằm đúng thư mục skills thì agent mới nạp được.
Sinh ra cái gì: một thư mục skill trong runtime của bạn, và một agent biết phản ứng với các trigger như «蒸馏XX» / "distill [person]".
Repo này thực chất là gì
Không có package.json, pyproject.toml, Cargo.toml hay go.mod — không có gì để npm install hay pip install. Entry point duy nhất là SKILL.md ở gốc repo, mở đầu bằng YAML frontmatter:
---
name: huashu-nuwa
description: |
女娲造人：输入人名/主题/甚至只是模糊需求，自动深度调研→思维框架提炼→生成可运行的人物Skill。
...
---
Kèm theo là ba thư mục có ý nghĩa vận hành:
| Thư mục | Nội dung | Ai đọc |
|---|---|---|
references/ |
extraction-framework.md (phương pháp chắt lọc), fidelity-scorecard.md (thang chấm), skill-template.md (khung SKILL.md đích) |
agent đọc trong lúc chạy Phase 2–4 |
scripts/ |
4 script CLI thật (xem 05-helper-scripts-cli.md) | bạn hoặc agent gọi qua shell |
examples/ |
15 skill đã chắt lọc hoàn chỉnh (Jobs, Munger, Feynman, Naval, Taleb, MrBeast…) | dùng làm mẫu đối chiếu, hoặc copy thẳng ra dùng |
Cách 1 — installer đa runtime (khuyến nghị)
npx skills add alchaincyf/nuwa-skill
Installer là vercel-labs/skills; nó tự nhận runtime đang dùng. Ép chỉ định runtime khi máy có nhiều agent:
npx skills add alchaincyf/nuwa-skill -a claude-code
npx skills add alchaincyf/nuwa-skill -a codex
npx skills add alchaincyf/nuwa-skill -a cursor
Cách 2 — clone tay vào đúng thư mục skills
# Claude Code
git clone https://github.com/alchaincyf/nuwa-skill ~/.claude/skills/nuwa-skill
# Codex CLI
git clone https://github.com/alchaincyf/nuwa-skill ~/.codex/skills/nuwa-skill
# Cursor
git clone https://github.com/alchaincyf/nuwa-skill ~/.cursor/skills/nuwa-skill
# OpenClaw
git clone https://github.com/alchaincyf/nuwa-skill ~/.openclaw/workspace/skills/nuwa-skill
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 97 lines · 72 tokens per session scan B cd89fc94cc74
dym-nuwa-skill-install is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 72 tokens to every session and 1,331 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.
dym-nuwa-skill-install compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-nuwa-skill-installRheinmir/setup | Skill | 11 | 20d ago | MIT | B | 72 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |