AGENT SKILL

ams-zettelkasten

暂无简介

License 许可
MIT
所属仓库
TanNhatCMS/jarvis
最近更新
2026-11-07
Stars
★ 0
Forks
1

03 SKILL.md 正文

Zettelkasten

Overview

The Zettelkasten ('slip box') is a note-taking method for thinking: atomic notes, densely linked, that surprise you with connections.

Developed by sociologist Niklas Luhmann, who credited it for his extraordinary output — the box became a conversation partner.

Principles: one idea per note, every note linkable, links that explain the relationship, and writing in your own words.

Tools don't matter much — index cards work. What matters is atomicity, linking discipline, and regular revisiting.

When to use

  • Academic research, thesis, or dissertation work
  • Writing books, long essays, or substantial articles
  • Building deep expertise in a field over years
  • Any knowledge work where ideas need to connect and compound
  • Moving beyond highlighting to genuine thinking in notes

Core concepts

  • Atomicity. One idea per note. If a note contains two ideas, split it. Atomic notes link cleanly; compound notes link messily.
  • Unique addresses. Every note gets a unique ID (timestamp, sequence). Links point to IDs, so notes can move and rename without breaking.
  • Own words. Rewrite everything in your language. Copy-paste is collecting; restating is thinking. Luhmann's rule: the box contains your thoughts, not quotes.
  • Link with context. Don't just link — say why: 'contradicts', 'extends', 'example of', 'prerequisite for'. The relationship is the knowledge.
  • Fleeting -> literature -> permanent. Fleeting notes (raw capture) -> literature notes (source summaries) -> permanent notes (your ideas, atomic, linked). Only permanent notes live in the box.
  • Branching, not filing. New notes attach to existing ones via links, forming branches of thought. No fixed hierarchy — structure emerges from connections.
  • The box as partner. Revisit randomly and by following links. Serendipitous encounters with old notes generate new ideas — if notes are atomic and well-linked.
  • Write from the box. Outlines assemble from linked note sequences. Writing becomes arranging existing thoughts, not generating from blank pages.

Practical workflow

  1. Set up the box. Any tool with unique IDs and backlinks (Obsidian, plain files, even cards). One inbox for fleeting notes, one home for permanent notes.
  2. Capture fleeting notes. Read with pen: jot raw reactions, quotes with page numbers, questions. Messy is fine — these are temporary.
  3. Write literature notes. After reading: summarize the source's argument in your words, one note per idea-cluster, with full reference.
  4. Create permanent notes. Convert: one idea per note, your words, unique ID, descriptive title. Link to 2-3 related notes with the relationship stated.
  5. Link deliberately. Each new note: which existing notes does it contradict, extend, exemplify, or depend on? Write the link sentence explicitly.
  6. Follow the branches. Weekly: pick a note, follow its links for 20 minutes. Add new links and notes as connections occur to you.
  7. Harvest for writing. When writing: gather the branch, arrange note sequences into an outline, draft from the notes. Cite the box, not memory.
  8. Maintain the garden. Monthly: merge duplicates, split compound notes, fix dead links, strengthen weak link-descriptions. The box improves with tending.

Common pitfalls

  • Collecting without atomicity. Long multi-idea notes that can't link precisely. Split ruthlessly — atomicity is the whole game.
  • Link-stuffing. Ten unexplained links per note. Links without stated relationships are noise, not knowledge.
  • Skipping your own words. Boxes full of quotes and highlights. If it's not in your words, it's not your thought.
  • No literature notes. Permanent notes without source grounding become unsourced opinions. Keep the chain: fleeting -> literature -> permanent.
  • Filing instead of linking. Elaborate folder hierarchies with few links. The Zettelkasten's power is the graph, not the folders.
  • Never revisiting. Writing notes and never returning. The serendipity engine needs regular visits — schedule them.
  • Perfectionist IDs. Agonizing over numbering schemes. Timestamps work fine; the ID just needs uniqueness, not meaning.
  • Tool-first adoption. Spending months configuring software before writing ten notes. Start with any tool; the method is the skill.

04 同仓库更多 Skills

TanNhatCMS
TanNhatCMS/jarvis

web-scrape

Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open/fetch fails on JS-heavy pages, or when you need clean markdown/structured extraction from a site. Requires FIRECRAWL_API_KEY.

★ 0
TanNhatCMS
TanNhatCMS/jarvis

design-taste-frontend

tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML/CSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, "AI-made", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.

★ 0
TanNhatCMS
TanNhatCMS/jarvis

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

★ 0
TanNhatCMS
TanNhatCMS/jarvis

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

★ 0
TanNhatCMS
TanNhatCMS/jarvis

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

★ 0
TanNhatCMS
TanNhatCMS/jarvis

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

★ 0