# Screenpipe Durable Learning

Turn a verified correction or repeated workflow into a reusable local learning.

- Repository: https://github.com/screenpipe/screenpipe (22202 stars)
- Category: Engineering
- License: see repository
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add screenpipe/screenpipe --skill screenpipe-durable-learning -g -a claude-code -y`
Codex: `npx skills add screenpipe/screenpipe --skill screenpipe-durable-learning -g -a codex -y`
Cursor: `npx skills add screenpipe/screenpipe --skill screenpipe-durable-learning -g -a cursor -y`
Gemini CLI: `npx skills add screenpipe/screenpipe --skill screenpipe-durable-learning -g -a gemini-cli -y`

## Description

Turn a verified correction or repeated workflow into a reusable local learning.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# durable learning

Verify the original request, correction, and result. Treat assistant success claims as claims until checked. Search existing skills before proposing a new one.
Save a concise reusable method, not a transcript, private identity, credential, or temporary task state. Include when to use it, steps, validation, and a stop condition.
Use skill_manage when available. Read first, preserve user/imported skills, and use the current hash for an agent-owned patch. Creating a skill requires the user’s explicit request or an enabled task whose stated scope authorizes it. No new permissions, outbound actions, or recursive agents.
A no-change result is valid. Assess the next relevant use before claiming improvement.