Skip to content
Skills Library
AI & agents · Automation

setup

/setup

Use when the user says "set up the brain", "turn on memory", "install bernard", "my Claude forgets everything", "it ignores my rules", or when the session began with "BERNARD brain: not set up yet". Creates the vault and turns memory on.

Licence
MIT
Last repository change
03.11.2026

Assessment and security

96/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content31 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 03.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when the user says "set up the brain", "turn on memory", "install bernard", "my Claude forgets everything", "it ignores my rules", or when the session began with "BERNARD brain: not set up yet". Creates the vault and turns memory on.

Triggers from the description

set up the brainturn on memoryinstall bernardmy Claude forgets everythingit ignores my rulesBERNARD brain: not set up yet
Original author description

Use when the user says "set up the brain", "turn on memory", "install bernard", "my Claude forgets everything", "it ignores my rules", or when the session began with "BERNARD brain: not set up yet". Creates the vault and turns memory on.

How it works

SKILL.md has no level-two headings · 31 lines, 241 words

SKILL.md preview
---
name: setup
description: Use when the user says "set up the brain", "turn on memory", "install bernard", "my Claude forgets everything", "it ignores my rules", or when the session began with "BERNARD brain: not set up yet". Creates the vault and turns memory on.
---

# Set up the brain

1. Create the vault and the map:
   ```bash
   python3 "${CLAUDE_PLUGIN_ROOT}/bin/brain.py" init
   ```
   If `${CLAUDE_PLUGIN_ROOT}` is not expanded in your shell, use the CLI path printed in the session's first lines
   (`CLI: python3 "<plugin folder>/bin/brain.py"`). To keep notes somewhere else: `init --vault ~/some/folder`.

2. Confirm it worked:
   ```bash
   python3 "${CLAUDE_PLUGIN_ROOT}/bin/brain.py" status
   ```

3. Tell the user, in five short lines, what happens from now on:
   - Every prompt arrives with a "BERNARD ROUTE" packet: the notes from the vault that match it.
   - Every file Claude changes is recorded in the vault's devlog and an in-progress session note (full kit).
   - Before Claude finishes a turn that changed files, a rule asks for a real session note (full kit).
   - The rules that are on (from `status`); each blocks a specific thing and says what to do instead.
   - Where the notes live (the vault path from `status`), and that they are plain Markdown files.

4. Offer to write the first project note for the current folder. If the user says yes:
   - Read what is there: `README*`, `package.json`, `pyproject.toml`, or the folder listing.
   - Write `<vault>/projects/<folder-name-slug>.md` from `<vault>/templates/project-note.md`: a plain first
     sentence saying what the project is for, then Goal and Current state.
   - Rebuild the map: `python3 "${CLAUDE_PLUGIN_ROOT}/bin/brain.py" map`

5. Say that a new Claude Code session will start with `BERNARD brain: on`, and that the packet appears from the
   first real prompt in it.

Versions

RepositoryScoreLicence
This page · albygira-cmyk/claude-brain-kit96MIT
HwangSlater/harness-fit100MIT
nesquikm/dev-process-toolkit100MIT
userKael/rastro100MIT
als-apg/osprey100BSD-3-Clause
dedujeong/gemba100Apache-2.0
eigenwise/eigenwise-toolshed100MIT
awrshift/agent-memory-kit100MIT
lifecycle-innovations-limited/claude-ops100MIT

Database snapshot: 13.11.2026 · package version ad92b7243049 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100setup-project
    When setting up agentskel on a new project that does not yet have .memory/ or .agents/. Use when the user says "set up agentskel", "install agentskel", or "add agent memory to this project".
  • 90brain:init
    Use when setting up project memory in a new folder or on the first brain:init in a project. Creates project_brain.db, registers the project, and bootstraps it from CLAUDE.local.md, memory files, docs, and emails; safe to re-run.
  • 90second-brain
    Set up, audit or open the viewer of a Claude Code "second brain" for any project or area of life - an app, a codebase, a business, research, a book, a job search, a course, a home renovation. Creates a short CLAUDE.md map (150 lines max), a focus file, a decision log, folder…
  • 95configuring-agent-brain
    Installation and configuration skill for Agent Brain document search system. Use when asked to "install agent brain", "setup agent brain", "configure agent brain", "setting up document search", "installing agent-brain packages", "configuring API keys", "initializing project for…
  • 90mem9
    Persistent cloud memory for OpenClaw agents. Use when users say: - "install mem9" - "setup memory" - "add memory plugin" - "openclaw memory" - "mem9 onboarding" - "memory not working" - "import memories" - "upload sessions
  • 98claude-brain-builder
    Build (or rebuild, or verify) the user's claude-brain transcript database at ~/claude-brain — markdown transcripts, catalog, a single-file SQLite vector index, and an always-on local recall server — and install its three operating skills (brain-architect, brain-recall,…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.