agentsclimarketplace
Sign in

Memorb born

Skill iamjosuho/memOrb/skills/core/memorb-born

Phase 0 Vault Initialization Skill: setup user identity, AI advisor persona, communication preferences, and core vault structure into CLAUDE.md. Triggered when vault setup is missing, user requests re-initialization, or running /memorb-born.From its SKILL.md

Install
npx -y skills add iamjosuho/memOrb --skill memorb-born

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.
  • 1 stars1 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

2.5 KB, 619 tokens by cl100k_base, as published. Nobody here has run it

Memorb Born Skill (Vault Initialization & Persona Setup)

Purpose: Establish user identity seed, AI manager/career advisor persona, and vault settings without locking into a specific Agent framework.

Execution Sequence

  1. Check Existing Context:
    • Inspect CLAUDE.md and memorbs/HQ/identity.md if available.
  2. Interactive 3-5 Question Interview (using ask_question tool if running interactively):
    • Q1 (Communication & Language): Preferred language (e.g. Traditional Chinese), output constraints, and non-negotiable rules.
    • Q2 (Identity & Role): Warmly greet the user (e.g., "Welcome! Today is YYYY-MM-DD, and your Second Brain is officially born."), then collect their preferred name, birthday (optional), education/career history, current title/organization, and key target goals.
    • Q3 (AI Advisor Persona): Desired AI tone and relationship (e.g., Senior Manager & Career Advisor, technical strategist, concise assistant).
    • Q4 (Vault Path & Integrations): Second Brain root path and connected tools/MCPs.
  3. Create Folder Structure & Base Files (Strictly following memorb-conventions SSOT — everything memOrb owns lives under memorbs/; never create folders outside it, whatever else the vault happens to contain):
    • Execute directory creation: 
      mkdir -p "$VAULT/memorbs/HQ/Core"
mkdir -p "$VAULT/memorbs/HQ/Belief"
mkdir -p "$VAULT/memorbs/HQ/OrbTrack"
mkdir -p "$VAULT/memorbs/Islands"
mkdir -p "$VAULT/memorbs/Long-Term/Projects"
mkdir -p "$VAULT/memorbs/Long-Term/People"
mkdir -p "$VAULT/memorbs/Long-Term/Orgs"
mkdir -p "$VAULT/memorbs/Dump"
    • Ensure initial creation of the timeline memorbs/log.md if not present, seeded with a # Timeline — since {YYYY-MM-DD} header.
  4. Generate/Update HQ Hot Cache:
    • memorbs/HQ/persona.md: AI tone/role from Q3 (<100 lines).
    • memorbs/HQ/identity.md: name, birthday, education/career history, role, organization, goals, and key relationships table from Q1/Q2/Q4 (<100 lines).
    • Generate/Update CLAUDE.md and AGENT.md: add command "Must read memorbs/HQ/persona.md and memorbs/HQ/identity.md"
  5. Log Event:
    • Record initialization in memorbs/log.md.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.