dym-nuwa-skill-diagnose-then-distill

dym-nuwa-skill-diagnose-then-distill is a skill for Claude Code from Rheinmir/setup. It costs 67 tokens per session (1,631 once invoked), scanned A, original, MIT.

A chat-only guide that helps choose a thinking framework for a problem before starting a deeper advisory workflow. It suggests two or three possible people or topics and lets you choose one.

In plain words
What is it for?
Use it for problems such as poor decisions, analysis paralysis, or writing that people do not read.
Why use it?
It is useful when you know the problem but do not know which perspective would help. It avoids turning the process into a long questionnaire.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it for problems such as poor decisions, analysis paralysis, or writing that people do not read.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rheinmir/setup/dym-nuwa-skill-diagnose-then-distill
Install

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.

Any agent
npx skills add Rheinmir/setup --skill dym-nuwa-skill-diagnose-then-distill
Clone the repo
git clone --depth 1 https://github.com/Rheinmir/setup

Made for: Claude Code.

Wrote 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.

agentmods badge for dym-nuwa-skill-diagnose-then-distill

README.md
[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-diagnose-then-distill/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-diagnose-then-distill)
Your own site
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-diagnose-then-distill"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-diagnose-then-distill/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.

agentmods 80×15 button for dym-nuwa-skill-diagnose-then-distill

Your own site · 80×15
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-diagnose-then-distill"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-diagnose-then-distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,631 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01631
Opus 5.5 $0.00027 $0.00652
Sonnet 5.5 $0.00013 $0.00326
Haiku 4.5 $0.00007 $0.00163

Measured yesterday against content hash 1d0e10c2e51b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-nuwa-skill-diagnose-then-distill scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.overstack/doyourmagic/nuwa-skill/skills/dym-nuwa-skill-diagnose-then-distill/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-nuwa-skill-diagnose-then-distill — Chưa biết chắt lọc ai: đường chẩn đoán (chat-only)

Vì sao dùng: bạn chỉ có một vấn đề ("hay ra quyết định sai", "viết không ai đọc"), chưa biết nên mượn đầu óc của ai. Sinh ra cái gì: 2–3 ứng viên có lý do, bạn chọn một rồi rơi thẳng vào luồng 02.

Đây là lệnh CHAT, không phải shell.


Câu lệnh khởi động

我想提升决策质量
有没有一种思维方式能帮我看透商业本质
I need a thinking advisor

Nói tiếng Việt vẫn hiểu được nếu skill đã nạp, nhưng an toàn nhất là mở bằng một trong các câu trên rồi mô tả tiếp bằng tiếng Việt.

Nhịp làm việc (Phase 0B)

Ba bước, tối đa 2 vòng hỏi lại — repo quy định thẳng "không được biến thành bảng khảo sát", và nếu bạn đã nói đủ rõ thì agent phải khuyến nghị luôn, không hỏi.

  1. Định vị nhu cầu — agent ánh xạ vấn đề của bạn vào một trong 10 chiều dưới đây.
  2. Đề cử 2–3 ứng viên — có thể là người hoặc chủ đề, kèm nhãn ⚡已有Skill (đã có sẵn trong .claude/skills/, dùng ngay) hoặc 🆕需要蒸馏 (phải chắt lọc mới).
  3. Bạn chọn → chuyển sang Phase 0.5 của luồng 02.
Chiều nhu cầu Câu nói điển hình Hướng khung tư duy
Quyết định & phán đoán "hay chọn sai", "tê liệt vì phân tích" đa mô hình tư duy, nghịch đảo, tư duy xác suất
Biểu đạt & viết "nói mãi không rõ", "bài không ai đọc" giản hoá kiểu Feynman, kể chuyện, năng lực ví von
Khởi nghiệp & kinh doanh "muốn làm indie dev", "không tìm ra PMF" nguyên lý đầu tiên, đòn bẩy, kiềm chế sản phẩm
Dạy & lan truyền "giảng không ai nghe" từ đã biết đến chưa biết, dạy bằng ẩn dụ
Tư duy phản biện "hay bị dắt mũi" tư duy phủ chứng, góc nhìn tiến hoá, nhận diện thiên kiến
Sáng tạo nội dung "video không ai xem" kỹ nghệ chú ý, test–lặp, tâm lý khán giả
Chiến lược đời người "mơ hồ hướng nghề", "lo âu" chủ nghĩa dài hạn, chọn đòn bẩy, lãi kép
Rủi ro & bất định "sợ thiên nga đen", "đầu tư toàn lỗ" phản mong manh, chiến lược lồi, quản trị rủi ro đuôi
Thiết kế & sản phẩm "UX tệ", "không biết cắt bớt" tối giản, mô hình tâm trí người dùng, ràng buộc là sáng tạo
Hài hước & sức biểu đạt "nói chuyện nhạt" tương phản phi lý, phá vỡ kỳ vọng, uy quyền tự trào

Read the full file on GitHub · 82 lines

Changes

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.

  1. yesterday First seen · 82 lines · 0 tokens per session scan A 1d0e10c2e51b

Subscribe to this mod's changes

dym-nuwa-skill-diagnose-then-distill is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 1,631 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Related

dym-nuwa-skill-diagnose-then-distill compared with skills from other repositories

dym-nuwa-skill-diagnose-then-distill next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dym-nuwa-skill-diagnose-then-distillRheinmir/setupSkill1120d agoMITA67Claude Code
hr-onboardingnexu-io/open-designSkill107ktodayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32ktodayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9kyesterdayApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA81Claude Code
eli5companion-inc/feynmanSkill10ktodayMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.5ktodayApache-2.0A25Claude Code, Codex