Agent skill

Memex Recall

by iamtouchskyer in iamtouchskyer/memex

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

MITAuto-check passedKnowledge Management

Install Memex Recall

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

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

GitHub CLI
$ gh skill install iamtouchskyer/memex memex-recall --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-recall .claude/skills/memex-recall && 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-recall
GitHub stars
143
Token cost
~1.3k tokens
SKILL.md length
431 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

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

  • Works in 4 steps: Targeted keyword search (preferred) → Read the keyword index (when needed) → Follow links → …
  • Tasks that involve Note-taking
  • SKILL.md covers Tools Available, Process, Guardrails and Counting Rules, plus 1 more section
  • Calls node

What it does

Memex Recall is an agent skill from iamtouchskyer/memex. Load prior knowledge from Zettelkasten memory when the task likely benefits from past context.

Its SKILL.md is about 1.3k 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-recall”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Targeted keyword search (preferred)
  2. Read the keyword index (when needed)
  3. Follow links
  4. Summarize and proceed

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 Recall loads about 1.3k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 431 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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). 431 words, ~1,262 tokens.

Download SKILL.mdSave it as .claude/skills/memex-recall/SKILL.md (or your agent's skills folder).
name
memex-recall
description
Load prior knowledge from Zettelkasten memory when the task likely benefits from past context.
whenToUse
When the current task likely overlaps with prior work — debugging a familiar area, continuing a project, or referencing past decisions. Prefer a task-specific…

Memory Recall

You have access to a Zettelkasten memory system via the memex CLI. Before starting this task, search your memory for relevant prior knowledge.

Tools Available

Three equivalent interfaces — use whichever your environment supports:

CLI (memex in PATH)Plugin CLI fallback (Claude Code)MCP tool (VSCode / Cursor)
memex read indexnode ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js read indexmemex_read with slug index
memex search <q>node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js search <q>memex_search with query arg
memex read <slug>node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js read <slug>memex_read with slug arg
memex search (no args)node ~/.claude/plugins/cache/cc-plugins/memex/*/dist/cli.js searchmemex_search with no args

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.

Process

dot
digraph recall {
    "Task received" -> "Relevant to prior work?" [shape=diamond];
    "Relevant to prior work?" -> "Generate 1-3 search keywords" [label="yes"];
    "Relevant to prior work?" -> "Proceed without recall" [label="no"];
    "Generate 1-3 search keywords" -> "memex search <query>";
    "memex search <query>" -> "Review summaries";
    "Review summaries" -> "Relevant cards found?" [shape=diamond];
    "Relevant cards found?" -> "memex read <card>" [label="yes"];
    "Relevant cards found?" -> "Need broad overview?" [label="no"];
    "Need broad overview?" -> "memex read index" [label="yes"];
    "Need broad overview?" -> "Proceed without recall" [label="no"];
    "memex read index" -> "Pick relevant slugs" -> "memex read <card>";
    "memex read <card>" -> "See [[links]] in content";
    "See [[links]] in content" -> "Links worth following?" [shape=diamond];
    "Links worth following?" -> "memex read <linked-card>" [label="yes"];
    "Links worth following?" -> "Enough context?" [label="no"];
    "memex read <linked-card>" -> "See [[links]] in content";
    "Enough context?" -> "More queries to try?" [label="no"];
    "More queries to try?" -> "Generate new query" [label="yes"];
    "Generate new query" -> "memex search <query>";
    "More queries to try?" -> "Summarize findings, proceed with task" [label="no"];
    "Enough context?" -> "Summarize findings, proceed with task" [label="yes"];
}
Step 1: Targeted keyword search (preferred)

Generate 1-3 search keywords from the current task and run memex search <keyword> for each. This is faster and more focused than reading the full index.

Step 2: Read the keyword index (when needed)

If you need a broad overview of what's in memory (e.g. first time working in this area, or the task is vague), run memex read index. The index is a curated concept → card mapping. It's much smaller than all cards combined and gives you entry points.

When you read a card and see [[links]] in the prose, decide if they're worth following. If yes, memex read <linked-slug>.

Step 4: Summarize and proceed

When you have enough context, summarize your findings and proceed with the task.

Show full SKILL.md (173 more words)Show less

Guardrails

  • max_hops: 3 — Do not follow links more than 3 levels deep
  • max_cards_read: 20 — Do not read more than 20 cards in a single recall
  • no raw secrets — Never include actual secrets, credentials, tokens, or exact secret file contents in search queries. Use abstract descriptions instead (e.g. gitee pr auth workflow, not a token value or credential file contents).
  • If you hit either limit, stop and work with what you have

Counting Rules

  • Hop 0 = cards found directly via index or memex search. Following a [[link]] from there is hop 1, etc.
  • Keep a running count of memex read calls. If you've read 20 cards, stop immediately.

Important

  • Prefer targeted memex search <keyword> over reading the full index — it's faster and more focused
  • Only memex read index when you need a broad overview or search returns nothing useful
  • Generate search queries in BOTH Chinese and English to maximize recall
  • If search returns nothing useful, that's fine — proceed without memory context
  • Summarize what you found before proceeding, so the findings are in your context

© 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-recall of iamtouchskyer/memex.

Open the folder on GitHubat commit 453c0e3

Compare with similar skills

Memex Recall 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 Recall compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memex Recall this skilliamtouchskyer/memex143—~1.3kAutomated 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 29 days 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 yesterday
    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 Organize

    iamtouchskyer/memex

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

    143 GitHub stars~1.7k 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

Questions about Memex Recall

What does Memex Recall do?

Load prior knowledge from Zettelkasten memory when the task likely benefits from past context. Memex Recall is an agent skill from iamtouchskyer/memex. Load prior knowledge from Zettelkasten memory when the task likely benefits from past context.

When should I use Memex Recall?

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

How do I install Memex Recall in Claude Code?

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

How do I install Memex Recall in Codex?

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

Can I use Memex Recall 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-recall -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-recall, .gemini/skills/memex-recall, .github/skills/memex-recall and .opencode/skills/memex-recall in your project.

What does Memex Recall need to run?

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

Does Memex Recall 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 Recall 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 Recall use?

Memex Recall 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 Recall use?

About 1.3k tokens (SKILL.md is roughly 5k 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 Recall?

Skills that share tags, products or a category with Memex Recall: 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 Recall?

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.