New to Claude Skills? Learn how to install them →

paperclipai on GitHub

PARA Memory Files

Free

Organize your knowledge with a structured memory system.

Get this skill

Free · Opens the source repo

What PARA Memory Files does

PARA Memory Files implements a file-based memory system based on Tiago Forte's PARA method, allowing users to store, retrieve, and organize knowledge efficiently across sessions. It features three distinct layers: a knowledge graph for entity-based storage, daily notes for recording events, and tacit knowledge for capturing user-specific patterns and preferences. This structure ensures that important information is easily accessible and systematically organized, promoting better retention and recall.

The first layer, the Knowledge Graph, organizes information into projects, areas, resources, and archives, with each entity having its own folder. Users can quickly access a summary of the entity and its detailed facts stored in YAML format. The second layer consists of Daily Notes, which serve as a chronological record of events and interactions, allowing users to capture insights and facts as they occur. The final layer, Tacit Knowledge, focuses on documenting the user's operational patterns, preferences, and lessons learned, ensuring that personal insights are preserved for future reference.

This skill is particularly useful for developers and designers who need to manage a large volume of information, whether it be project details, ongoing responsibilities, or personal insights. By using a structured approach to memory management, users can enhance their productivity and ensure that critical information is never lost, even across sessions. The ability to write down thoughts and facts immediately into files prevents reliance on short-term memory, which can often lead to missed details and forgotten insights.

With the integration of semantic search capabilities via qmd, users can efficiently retrieve information even when phrasing differs, making it easier to find relevant facts and insights quickly. This skill is ideal for anyone looking to create a robust system for managing their knowledge and experiences over time, ensuring that nothing important slips through the cracks.

When to use it

Use this skill when you need a reliable method to document and retrieve knowledge, especially for ongoing projects and personal insights.

When not to use it

This skill may not be suitable for users who prefer a more transient or less structured approach to note-taking and memory management.

What you can build with it

Managing Project Knowledge

Use PARA Memory Files to document project details, deadlines, and relevant resources, ensuring all information is organized and easily retrievable.

Capturing Daily Insights

Record daily notes during meetings or brainstorming sessions to capture insights and facts that can be later organized into the knowledge graph.

Documenting Personal Patterns

Utilize tacit knowledge to track your working patterns and preferences, helping you to refine your processes and improve productivity.

How to install PARA Memory Files

View source

1. Install with the skills CLI

npx skills add paperclipai/paperclip/para-memory-files --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by paperclipai

PARA Memory Files

Persistent, file-based memory organized by Tiago Forte's PARA method. Three layers: a knowledge graph, daily notes, and tacit knowledge. All paths are relative to $AGENT_HOME.

Three Memory Layers

Layer 1: Knowledge Graph ($AGENT_HOME/life/ -- PARA)

Entity-based storage. Each entity gets a folder with two tiers:

  1. summary.md -- quick context, load first.
  2. items.yaml -- atomic facts, load on demand.
$AGENT_HOME/life/
  projects/          # Active work with clear goals/deadlines
    <name>/
      summary.md
      items.yaml
  areas/             # Ongoing responsibilities, no end date
    people/<name>/
    companies/<name>/
  resources/         # Reference material, topics of interest
    <topic>/
  archives/          # Inactive items from the other three
  index.md

PARA rules:

  • Projects -- active work with a goal or deadline. Move to archives when complete.
  • Areas -- ongoing (people, companies, responsibilities). No end date.
  • Resources -- reference material, topics of interest.
  • Archives -- inactive items from any category.

Fact rules:

  • Save durable facts immediately to items.yaml.
  • Weekly: rewrite summary.md from active facts.
  • Never delete facts. Supersede instead (status: superseded, add superseded_by).
  • When an entity goes inactive, move its folder to $AGENT_HOME/life/archives/.

When to create an entity:

  • Mentioned 3+ times, OR
  • Direct relationship to the user (family, coworker, partner, client), OR
  • Significant project or company in the user's life.
  • Otherwise, note it in daily notes.

For the atomic fact YAML schema and memory decay rules, see references/schemas.md.

Layer 2: Daily Notes ($AGENT_HOME/memory/YYYY-MM-DD.md)

Raw timeline of events -- the "when" layer.

  • Write continuously during conversations.
  • Extract durable facts to Layer 1 during heartbeats.

Layer 3: Tacit Knowledge ($AGENT_HOME/MEMORY.md)

How the user operates -- patterns, preferences, lessons learned.

  • Not facts about the world; facts about the user.
  • Update whenever you learn new operating patterns.

Write It Down -- No Mental Notes

Memory does not survive session restarts. Files do.

  • Want to remember something -> WRITE IT TO A FILE.
  • "Remember this" -> update $AGENT_HOME/memory/YYYY-MM-DD.md or the relevant entity file.
  • Learn a lesson -> update AGENTS.md, TOOLS.md, or the relevant skill file.
  • Make a mistake -> document it so future-you does not repeat it.
  • On-disk text files are always better than holding it in temporary context.

Memory Recall -- Use qmd

Use qmd rather than grepping files:

qmd query "what happened at Christmas"   # Semantic search with reranking
qmd search "specific phrase"              # BM25 keyword search
qmd vsearch "conceptual question"         # Pure vector similarity

Index your personal folder: qmd index $AGENT_HOME

Vectors + BM25 + reranking finds things even when the wording differs.

Planning

Keep plans in timestamped files in plans/ at the project root (outside personal memory so other agents can access them). Use qmd to search plans. Plans go stale -- if a newer plan exists, do not confuse yourself with an older version. If you notice staleness, update the file to note what it is supersededBy.

Frequently asked questions about PARA Memory Files

Similar skills