dym-nuwa-skill-distill-a-person

dym-nuwa-skill-distill-a-person is a skill for Claude Code from Rheinmir/setup. It costs 70 tokens per session (2,111 once invoked), scanned A, original, MIT.

A research workflow for turning a known person's books, talks, and writing into a reusable agent skill. It creates a self-contained skill folder with instructions and source references.

In plain words
What is it for?
Use it to build a skill representing people such as Charlie Munger, Richard Feynman, or Paul Graham, with the supporting research kept alongside it.
Why use it?
It gives an agent traceable material instead of an invented imitation of someone's views or style. Different research depths let you choose between a quicker pass and a fuller study.

Skill for Claude Code

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

Good fit Use it to build a skill representing people such as Charlie Munger, Richard Feynman, or Paul Graham, with the supporting research kept alongside it.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-nuwa-skill-distill-a-person"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-nuwa-skill-distill-a-person.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,111 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 $0.00070 $0.02111
Opus 5.5 $0.00028 $0.00844
Sonnet 5.5 $0.00014 $0.00422
Haiku 4.5 $0.00007 $0.00211

Measured yesterday against content hash 03f23cea5f36, 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-distill-a-person 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-distill-a-person/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-nuwa-skill-distill-a-person — Chắt lọc một nhân vật (đường trực tiếp, chat-only)

Vì sao dùng: bạn đã biết muốn chắt lọc ai (Munger, Feynman, Paul Graham, Trương Nhất Minh…) và muốn ra một skill chạy được, có nguồn truy vết. Sinh ra cái gì: một thư mục skill tự chứa .claude/skills/<tên>-perspective/ gồm SKILL.md, references/research/01-06.md, references/sources/.

⚠️ Toàn bộ file này là lệnh CHAT, gõ vào cửa sổ hội thoại của agent, không phải terminal. Lệnh shell nằm ở 05-helper-scripts-cli.md.


Câu lệnh khởi động

蒸馏一个保罗·格雷厄姆
造一个张小龙的视角Skill
distill Paul Graham

Việc agent sẽ hỏi (Phase 0A) và cách trả lời để không bị kẹt

SKILL.md quy định 6 mục xác nhận. Mục quan trọng nhất là 档位 (mức chắt lọc) — vì đây là tác vụ dài, nhiều agent, nhiều vòng tìm kiếm; tài liệu của repo nói thẳng rằng một lần chạy trên model cao cấp có thể tốn hàng chục USD:

Mức Quy mô khảo cứu Dùng khi Chi phí
快速 (nhanh) 3 chiều (著作 + 对话 + 表达), mỗi chiều tối đa 5 nguồn thử hiệu quả / nhân vật ít tư liệu / ngân sách chặt ≈ 1/3 mức chuẩn
标准 (chuẩn, mặc định) 6 chiều đầy đủ đa số trường hợp trung bình
深度 (sâu) 6 chiều + tải toàn bộ tư liệu gốc (sách/phụ đề/trường văn) định open-source bản tinh phẩm cao nhất

Trả lời gọn để chạy thẳng mức chuẩn:

Nhân vật: Charlie Munger. Chân dung toàn diện. Dùng làm cố vấn tư duy.
Skill mới (chưa có sẵn). Không có tư liệu local. Mức 标准.

Muốn rẻ:

蒸馏芒格,走快速档,只要3个维度

Có tư liệu gốc trong tay thì nói ngay — sách PDF, transcript phỏng vấn, phụ đề video, export blog. Repo gọi đây là 本地语料模式: agent đọc tư liệu bạn đưa trước, rồi chỉ tìm mạng cho các chiều còn thiếu. Chất lượng cao hơn hẳn so với tìm mạng thuần.

Tôi có 2 quyển PDF và 3 file transcript ở ~/tulieu/munger/, ưu tiên dùng chúng.

Đường ống 6 pha, và 4 chốt dừng bạn phải duyệt

Pha Agent làm gì Sản phẩm
0.5 Tạo cây thư mục skill trước khi khảo cứu references/research/, references/sources/{books,transcripts,articles}/
1 Bung 6 subagent song song, mỗi agent một chiều 01-writings.md … 06-timeline.md
🔴 1.5 CHỐT — bảng tóm tắt chất lượng khảo cứu bảng số nguồn / phát hiện chính / điểm mâu thuẫn
2 Chắt lọc khung tư duy (mô hình tâm trí 3–7, heuristic 5–10, DNA biểu đạt, tension, ranh giới trung thực) ghi chú chắt lọc
🔴 2.5 CHỐT — xác nhận bản chắt lọc trước khi viết tóm tắt N mô hình / N heuristic
3 Lắp thành SKILL.md theo references/skill-template.md SKILL.md hoàn chỉnh
🔴 4 CHỐT — 3 bài kiểm tra bằng subagent độc lập báo cáo pass/fail 6 tiêu chí
🔴 5 CHỐT — 2 agent tinh luyện song song bản vá cải thiện

Read the full file on GitHub · 120 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 · 120 lines · 70 tokens per session scan A 03f23cea5f36

Subscribe to this mod's changes

dym-nuwa-skill-distill-a-person is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 70 tokens to every session and 2,111 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-distill-a-person compared with skills from other repositories

dym-nuwa-skill-distill-a-person next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dym-nuwa-skill-distill-a-personRheinmir/setupSkill1120d agoMITA70Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code