Retention skill

Skill Mickos79/aria-skills/retention-skill

Production AI agent skills for OpenClaw — extracted from a real personal AI OS. RAG memory, safety guards, cost tracking, architect agent and more.

Install

npx -y skills add Mickos79/aria-skills --skill retention-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.6 KB, 386 tokens by cl100k_base, as published. Nobody here has run it

Retention Skill — Layered Memory Archival

Automatically archives conversation history to prevent unbounded growth while preserving all knowledge.

Memory layers

Hot     → rag.messages          → last 7 days, exact messages
Warm    → rag.daily_summaries   → day-level summaries (7-30 days)
Cold    → rag.monthly_summaries → month-level summaries (30+ days)
Archive → never deleted

Archival rules

Messages older than 7 days → create daily_summary → delete messages
Daily summaries older than 30 days → create monthly_summary → delete daily
Monthly summaries → never delete

When to run

Daily cron at 02:00 UTC:

0 2 * * * node /path/to/retention.js

Key principle

Never lose information — always summarize before deleting. Each layer trades granularity for longevity.

SQL schema (PostgreSQL + pgvector)

-- Hot layer
CREATE TABLE rag.messages (
  id uuid PRIMARY KEY DEFAULT gen_random_uuid(),
  user_id text NOT NULL,
  channel text,
  role text NOT NULL,  -- 'user' | 'assistant'
  content text NOT NULL,
  embedding vector(1536),
  created_at timestamptz DEFAULT now()
);

-- Warm layer
CREATE TABLE rag.daily_summaries (
  id uuid PRIMARY KEY DEFAULT gen_random_uuid(),
  user_id text NOT NULL,
  summary_date date NOT NULL,
  content text NOT NULL,
  embedding vector(1536),
  UNIQUE(user_id, summary_date)
);

-- Cold layer
CREATE TABLE rag.monthly_summaries (
  id uuid PRIMARY KEY DEFAULT gen_random_uuid(),
  user_id text NOT NULL,
  summary_date date NOT NULL,
  content text NOT NULL,
  embedding vector(1536)
);

Gives 0 of the 12 instructions most analytics metrics skills give in 386 tokens

Counted across 368 of the 369 authors here whose files we hold, read 2026-08-06

read product marketing context before asking questionsin 18 of 368, across 12 files
use lowercase with underscores for event namesin 16 of 368, across 6 files
track events for decisions not vanity metricsin 15 of 368, across 5 files
use object-action format for event namesin 15 of 368, across 8 files
produce a tracking plan documentin 14 of 368, across 4 files
Call RUBE_SEARCH_TOOLS first to get current schemasin 13 of 368, across 2 files
establish consistent event naming conventions before implementingin 10 of 368, across 4 files
Verify dimension and metric compatibility before reportingin 9 of 368, across 2 files
Encrypt data at rest and in transitin 9 of 368, across 3 files
use snake_case for event namesin 9 of 368, across 5 files
monitor technical health during the testin 9 of 368, across 5 files
use consistent property namesin 8 of 368, across 4 files

Said here and by no other author read

summarize messages older than seven days
delete messages after creating daily summaries
summarize daily summaries older than thirty days
never delete monthly summaries
always summarize before deleting

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.