SkillsAdd

mphinance/alpha-skills

portable-memory-core

A meta-skill that establishes a 'One Brain' portable memory folder (.agent/). It persists context, user preferences, identity rules, and execution history across different AI harnesses (Claude Code, Cursor, Windsurf, OpenClaw).

First seen May 9, 2026

Installation

$ npx skills add mphinance/alpha-skills --skill portable-memory-core
View on skills.sh ↗ GitHub repository ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

portable-text-serialization Similar name
sanity-io/agent-toolkit

Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text.

2.2K installs
portable-text-conversion Similar name
sanity-io/agent-toolkit

Convert HTML and Markdown content into Portable Text blocks for Sanity.

2.2K installs
portable-document-handler Similar name
qodex-ai/ai-agent-skills

Comprehensive PDF processing and manipulation. Creates, extracts, merges, splits, and transform…

148 installs

Also in this package

Other skills from mphinance/alpha-skills · top by installs.

npx skills add mphinance/alpha-skills
us-stock-analysis 99 quant-feature-engineer 99 backtest-expert 95 pinescript-to-python-translator 95 portfolio-manager 92 finance-report 91 sprite-animation 91 data-quality-checker 89 economic-calendar-fetcher 89 invoice 89

Browse all from mphinance/alpha-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 21
License LICENSE
Default branch main
Open issues 0
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code cursor windsurf

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,317 B
  • docs README.md 1,317 B
  • docs SUMMARY.md 255 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 86 installs

SKILL.md

Portable Memory Core

"Never explain yourself twice."

This skill enforces the One Brain protocol. Instead of scattering your preferences across dozens of system prompts, it centralizes them into a portable .agent/ directory that any LLM runner can hook into.

Core Directives

  1. Memory Synchronization: Upon startup, read from .agent/memory.yaml.
  2. Context Passing: Whenever the user switches contexts (e.g., from Cursor to OpenClaw), this skill ensures the new context loads the latest state from .agent/state.json.
  3. Identity Enforcement: Enforces the IDENTITY.md rules (e.g., "Caveman mode", "No em dashes", "Substack voice") universally across all generated code and text.
  4. Harness Agnostic: Works seamlessly whether the upstream harness is Claude CLI, a custom Python script, or a GUI.

Usage

When activated, you will automatically:

  • Load .agent/preferences.yaml
  • Update .agent/history.json with the current session summary.
  • Export relevant variables to the local workspace.