Para Memory Files
Give your coding agent durable, file-based PARA memory with decay-aware summaries instead of losing context every session.
Overview
Para Memory Files is a journey-wide agent skill that implements PARA-style file memory with atomic facts, access-based decay tiers, and summary curation—usable whenever a solo builder needs durable agent context before c
Install
npx skills add https://github.com/paperclipai/paperclip --skill para-memory-filesWhat is this skill?
- Atomic fact schema in items.yaml with categories, supersession, and entity links
- Hot/warm/cold recency tiers (7-day, 8–30-day, 30+ day) for summary.md curation
- Access_count and last_accessed updates when facts are used in conversation
- No deletion policy—decay affects retrieval priority only via weekly synthesis
- Tiago Forte PARA-inspired file layout for long-horizon agent memory
- 3 recency tiers (hot 7-day, warm 8–30-day, cold 30+ day)
- Atomic fact fields include id, category, status, superseded_by, and related_entities
Adoption & trust: 729 installs on skills.sh; 69.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent forgets relationships, milestones, and preferences between sessions because nothing structured persists on disk with sensible retrieval priority.
Who is it for?
Builders running long-horizon coding agents who want transparent, git-friendly memory files instead of opaque vector-only stores.
Skip if: One-off scripts with no recurring sessions, or teams that forbid agents writing persistent files on the developer machine.
When should I use this skill?
Setting up or maintaining file-based PARA memory, atomic facts in items.yaml, memory decay, heartbeat extraction, or weekly summary synthesis for an agent.
What do I get? / Deliverables
You get items.yaml facts with decay-aware summary.md curation and reheating on access, so later invocations surface the right context without bloating every prompt.
- items.yaml atomic facts with supersession and entity links
- summary.md curated by hot/warm/cold decay tiers
- Updated access_count and last_accessed metadata after fact use
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Persist competitor and audience facts with entity links before you narrow the MVP scope.
Bootstrap items.yaml and summary.md so implementation tasks reuse prior architectural decisions.
Keep incident and status facts warm in summary.md while cold historical notes stay retrievable from items.yaml.
Track customer preferences and milestones with access_count so outreach context stays hot across sessions.
How it compares
File-schema agent memory with explicit decay rules, not a hosted CRM or a generic note-taking template.
Common Questions / FAQ
Who is para-memory-files for?
Solo builders and indie hackers operating coding agents who need structured, inspectable long-term memory across projects and phases.
When should I use para-memory-files?
Use it during Build when wiring agent tooling, during Operate when tracking incidents and decisions, and during Grow when remembering customer or content context across campaigns.
Is para-memory-files safe to install?
The skill implies filesystem writes for memory files—avoid storing secrets in YAML and review the Security Audits panel on this Prism page before enabling in production workspaces.
SKILL.md
READMESKILL.md - Para Memory Files
# Schemas and Memory Decay ## Atomic Fact Schema (items.yaml) ```yaml - id: entity-001 fact: "The actual fact" category: relationship | milestone | status | preference timestamp: "YYYY-MM-DD" source: "YYYY-MM-DD" status: active # active | superseded superseded_by: null # e.g. entity-002 related_entities: - companies/acme - people/jeff last_accessed: "YYYY-MM-DD" access_count: 0 ``` ## Memory Decay Facts decay in retrieval priority over time so stale info does not crowd out recent context. **Access tracking:** When a fact is used in conversation, bump `access_count` and set `last_accessed` to today. During heartbeat extraction, scan the session for referenced entity facts and update their access metadata. **Recency tiers (for summary.md rewriting):** - **Hot** (accessed in last 7 days) -- include prominently in summary.md. - **Warm** (8-30 days ago) -- include at lower priority. - **Cold** (30+ days or never accessed) -- omit from summary.md. Still in items.yaml, retrievable on demand. - High `access_count` resists decay -- frequently used facts stay warm longer. **Weekly synthesis:** Sort by recency tier, then by access_count within tier. Cold facts drop out of the summary but remain in items.yaml. Accessing a cold fact reheats it. No deletion. Decay only affects retrieval priority via summary.md curation. The full record always lives in items.yaml. --- name: para-memory-files description: > File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans. --- # 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. ```text $AGENT_HOME/life/ projects/ # Active work with clear goals/deadlines <name>/ summary.md items.yaml areas/ # Ongoing responsibilities, no end date people/<name>/ companies/<name>/ resources/ # Reference material, topics of interest <topic>/ archives/ # Inactive items from the other three index.md ``` **PARA rules:** - **Projects** -- active work with a goal or deadline. Move to archives when complete. - **Areas** -- ongoing (people, companies, responsibilities). No end date. - **Resources** -- reference material, topics of interest. - **Archives** -- inactive items from any category. **Fact rules:** - Save durable facts immediately to `items.yaml`. - Weekly: rewrite `summary.md` from active facts. - Never delete facts. Supersede instead (`status: superseded`, add `superseded_by`). - When an entity goes inactive, move its folder to `$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](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 (