New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Memex Organize

by iamtouchskyer in iamtouchskyer/memex

Periodic maintenance of the Zettelkasten card network. An agent skill from iamtouchskyer/memex.

MITAuto-check passedKnowledge Management

Install Memex Organize

skills CLI
$ npx skills add iamtouchskyer/memex --skill memex-organize -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install iamtouchskyer/memex memex-organize --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/iamtouchskyer/memex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/memex-organize .claude/skills/memex-organize && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
memex-organize
GitHub stars
143
Token cost
~1.7k tokens
SKILL.md length
704 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Periodic maintenance of the Zettelkasten card network. An agent skill from iamtouchskyer/memex.

  • Works in 6 steps: Run memex links to get global link graph… → Orphan detection: For cards with 0… → Hub detection: For cards with >= 10… → …
  • Tasks that involve Note-taking
  • SKILL.md covers Tools Available, Process, Keyword Index Maintenance and Incremental Strategy, plus 1 more section
  • Calls node

What it does

Memex Organize is an agent skill from iamtouchskyer/memex. Periodic maintenance of the Zettelkasten card network.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Note-taking. It works with Visual Studio Code. The repository describes itself as: Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB — just markdown + git… The licence is MIT.

When your agent uses it

  • Tasks that involve Note-taking

Example prompts

  • “/memex-organize”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Run memex links to get global link graph stats
  2. Orphan detection: For cards with 0 inbound links
  3. Hub detection: For cards with >= 10 inbound links
  4. Contradiction/staleness detection: The organize report includes recently modified cards paired with their neighbors. For each pair
  5. Resolve existing conflicts: Check the "Unresolved Conflicts" section. For each card with status: conflict
  6. Rebuild keyword index (always, as last step)

What it can do on your machine

Read from SKILL.md and the folder at commit 453c0e3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memex Organize loads about 1.7k tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from iamtouchskyer/memex at commit 453c0e3, republished under its MIT licence (© iamtouchskyer). 704 words, ~1,684 tokens.

Download SKILL.mdSave it as .claude/skills/memex-organize/SKILL.md (or your agent's skills folder).
name
memex-organize
description
Periodic maintenance of the Zettelkasten card network.
whenToUse
When the user asks to organize, maintain, or clean up their memory cards. Also when running scheduled maintenance to detect orphans, hubs, contradictions, and…

Memory Organize

You are maintaining a Zettelkasten memory system. Your job is to keep the card network healthy.

Tools Available

Three equivalent interfaces — use whichever your environment supports:

CLI (memex in PATH)Plugin CLI fallback (Claude Code)MCP tool (VSCode / Cursor)
memex search [q]node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js search [q]memex_search with optional query arg
memex read <slug>node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js read <slug>memex_read with slug arg
memex write <slug>node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js write <slug>memex_write with slug arg and body
memex linksnode ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js linksmemex_links with no args
memex links <slug>node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js links <slug>memex_links with slug arg
memex archive <slug>node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js archive <slug>memex_archive with slug arg

Resolution order: Try memex in PATH first. If not found, define a shell function and use it:

bash
memex() { node $HOME/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js "$@"; }

If both CLI approaches fail, use MCP tools.

The rest of this skill uses memex CLI syntax for brevity.

The rest of this skill uses CLI syntax for brevity. Substitute MCP tool calls if CLI is unavailable.

Process

dot
digraph organize {
    "Organize report" -> "Detect orphans (in=0)";
    "Detect orphans (in=0)" -> "For each orphan: memex read + search related";
    "For each orphan: memex read + search related" -> "LLM decides: append links / mark stale / leave alone";
    "Organize report" -> "Detect hubs (in >= 10)";
    "Detect hubs (in >= 10)" -> "LLM decides: split into smaller cards or leave alone";
    "Organize report" -> "Recently modified pairs";
    "Recently modified pairs" -> "Genuinely contradicts?" [shape=diamond];
    "Genuinely contradicts?" -> "Mark status: conflict, surface to human" [label="yes"];
    "Genuinely contradicts?" -> "Evolution?" [label="no"];
    "Evolution?" -> "Merge + archive old card" [label="yes"];
    "Evolution?" -> "Leave alone" [label="no"];
    "Organize report" -> "Resolve existing conflicts";
    "Resolve existing conflicts" -> "Ask user which belief wins";
    "All checks done" -> "Rebuild keyword index";
}
  1. Run memex links to get global link graph stats
  2. Orphan detection: For cards with 0 inbound links:
    • memex read the orphan
    • memex search for potentially related cards
    • Decide: append a link from a related card to this orphan, or leave alone if truly standalone
  3. Hub detection: For cards with >= 10 inbound links:
    • memex read the hub and its linkers
    • Decide: is this card too broad? Should it be split into smaller atomic concepts?
  4. Contradiction/staleness detection: The organize report includes recently modified cards paired with their neighbors. For each pair:
    • Read both cards' content (excerpts are in the report, memex read for full content if needed)
    • Determine: do these cards genuinely contradict each other, or is one simply an evolution of the other?
    • If evolution (new info supersedes old): merge the cards — append the old card's unique content to the new one, then memex archive the old card
    • If genuine contradiction (two conflicting beliefs, unclear which is correct): mark the newer card with status: conflict in frontmatter and add a note explaining the contradiction. Do NOT auto-resolve — the human decides which belief wins
    • If no conflict: leave both cards alone
  5. Resolve existing conflicts: Check the "Unresolved Conflicts" section. For each card with status: conflict:
    • Surface it to the user: "Card X conflicts with card Y — which perspective should we keep?"
    • If the user resolves it, remove status: conflict from frontmatter and merge/archive as directed
  6. Rebuild keyword index (always, as last step)
Show full SKILL.md (295 more words)Show less

Keyword Index Maintenance

The keyword index (index card) is a curated concept → card mapping, inspired by Luhmann's Schlagwortregister. It is the primary entry point for the recall skill.

After completing all checks, rebuild the index:

  1. memex search (no args) to get all card slugs and titles
  2. memex read each card (or at least new/modified ones)
  3. Group cards by concept/topic — use your judgment to create meaningful categories
  4. Write the index card:
markdown
---
title: Keyword Index
created: <original creation date>
source: organize
---

## <Concept Category 1>
- [[slug-a]] — one-line description
- [[slug-b]] — one-line description

## <Concept Category 2>
- [[slug-c]] — one-line description

Rules for the index:

  • Each card should appear under 1-2 categories (not more)
  • Categories should be meaningful concepts, not arbitrary groupings
  • Descriptions should be one line, explaining what the card is about (not just the title)
  • Archived cards must be removed from the index
  • New cards must be added

Use memex write index to save the index.

Incremental Strategy

  1. Read last run date: cat ~/.memex/.last-organize 2>/dev/null
  2. If the file exists, only process cards where frontmatter modified >= that date, plus their linked neighbors
  3. If the file doesn't exist, this is the first run — process all cards
  4. After completing all checks, write today's date: echo "YYYY-MM-DD" > ~/.memex/.last-organize (use actual date)

When the organize skill creates new cards (e.g., splitting hubs), use source: organize in the frontmatter.

Operation Rules

  • Append only: When adding links to existing cards, append to the end of the body. Never modify existing prose.
  • Merge: Read both cards, append source content to target card via memex write, then memex archive the source.
  • Archive: Use memex archive <slug> to move stale cards out of active search.
  • No raw secrets: Never search for or write actual secrets, credentials, tokens, or exact secret file contents. Use redacted examples and abstract descriptions instead.
  • Be conservative: When in doubt, leave cards alone. It's better to under-organize than to break useful connections.

© iamtouchskyer, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/memex-organize of iamtouchskyer/memex.

Open the folder on GitHubat commit 453c0e3

Compare with similar skills

Memex Organize next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Memex Organize compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memex Organize this skilliamtouchskyer/memex143—~1.7kAutomated safety check: PassMIT
Qmdalsk1992/CloddsBot3k3 repos~1.2kAutomated safety check: PassMIT
Obsidian Canvas BoardsAgriciDaniel/claude-obsidian15k—~1.4kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Para Memory Filespaperclipai/paperclip99k1 repos~909Automated safety check: PassMIT
Copilot History IngestAr9av/obsidian-wiki3.5k—~4.4kAutomated safety check: NotesMIT

Similar skills

  • Qmd

    alsk1992/CloddsBot

    Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.

    3k GitHub starsUsed in 3 repos~1.2k tokens
    Knowledge ManagementAuto-check passed

  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed

  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed

  • Para Memory Files

    paperclipai/paperclip

    Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions.

    99k GitHub starsUsed in 1 repo~909 tokens
    Knowledge ManagementAuto-check passed

  • Copilot History Ingest

    Ar9av/obsidian-wiki

    Ingest GitHub Copilot CLI/session history into Obsidian as distilled knowledge.

    3.5k GitHub stars~4.4k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check: notes

  • Add Frontmatter

    heyitsnoah/claudesidian

    Add or update YAML frontmatter properties to enhance Obsidian note organization.

    2.6k GitHub stars~951 tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check passed

More from iamtouchskyer/memex

  • Agent Prompts Warmup

    iamtouchskyer/memex

    Audit and sync agent instruction files across all coding agent formats.

    143 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Memex Agentic Memory

    iamtouchskyer/memex

    A-MEM-inspired agentic memory workflow for structured knowledge capture.

    143 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Memex Best Practices

    iamtouchskyer/memex

    Zettelkasten best practices for building a high-quality knowledge graph.

    143 GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed

  • Memex Recall

    iamtouchskyer/memex

    Load prior knowledge from Zettelkasten memory when the task likely benefits from past context.

    143 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Memex Retro

    iamtouchskyer/memex

    Save insights from completed tasks to Zettelkasten memory. An agent skill from iamtouchskyer/memex.

    143 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Memex Sync

    iamtouchskyer/memex

    Sync Zettelkasten cards across devices via git. An agent skill from iamtouchskyer/memex.

    143 GitHub stars~533 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Memex Organize

What does Memex Organize do?

Periodic maintenance of the Zettelkasten card network. An agent skill from iamtouchskyer/memex. Memex Organize is an agent skill from iamtouchskyer/memex. Periodic maintenance of the Zettelkasten card network.

When should I use Memex Organize?

Memex Organize fits situations like: tasks that involve Note-taking.

How do I install Memex Organize in Claude Code?

Run `npx skills add iamtouchskyer/memex --skill memex-organize -a claude-code`. Or copy the skill folder (skills/memex-organize in iamtouchskyer/memex) into .claude/skills/memex-organize in your project. Claude Code loads it when a task matches its description.

How do I install Memex Organize in Codex?

Run `npx skills add iamtouchskyer/memex --skill memex-organize -a codex`. Or copy the skill folder (skills/memex-organize in iamtouchskyer/memex) into .agents/skills/memex-organize in your project. Codex loads it when a task matches its description.

Can I use Memex Organize in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add iamtouchskyer/memex --skill memex-organize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memex-organize, .gemini/skills/memex-organize, .github/skills/memex-organize and .opencode/skills/memex-organize in your project.

What does Memex Organize need to run?

Going by SKILL.md and its folder, Memex Organize needs the command-line tools its instructions call (node).

Does Memex Organize access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Memex Organize safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Memex Organize use?

Memex Organize is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memex Organize use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memex Organize?

Skills that share tags, products or a category with Memex Organize: Qmd (alsk1992/CloddsBot, 3k stars), Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and Para Memory Files (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memex Organize?

iamtouchskyer (a GitHub user) maintains it in iamtouchskyer/memex, which has 143 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 8, 2026.

Source: iamtouchskyer/memex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.