agentleFS
jakubtobiaszjakubtobiasz/second-brain-template/.agents/skills/setup/SKILL.md

setup

Skill0 starsChanged 7 days agoMITView on GitHub

Set up or refresh the second brain for its owner. Interview them (or read a pasted bio/assessment) to fill 90-system/about.md, check git, Obsidian and optional tools, and walk through the first ingest. Use when the owner says "set up my profile", "set up the vault", "onboard me", "update my profile", after a role change, or when 90-system/about.md is still empty.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the owner pastes a bio, CV, or assessment (Gallup, DISC, MBTI, etc.), extract from it first, then ask only about what's missing.

    line 9
  2. Distinctive:

    Keep questions short; offer examples.

    line 13
  3. Very specific:

    Must capture: language & tone, ingest check-in level (always / only for big sources / auto), always-do and never-do rules, current focus …

    line 14
  4. Very specific:

    If qmd is installed: run scripts/qmd-sync.sh --wait once.

    line 24
  5. Distinctive:

    Run it only on the owner's yes.

    line 30
  6. Very specific:

    If log.md has no entries yet:

    line 37

“Common” is measured: kept by at least 6 in 10 of the 168 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Setup: profile + first run

1. Profile (90-system/about.md)

  • If the owner pastes a bio, CV, or assessment (Gallup, DISC, MBTI, etc.), extract from it first, then ask only about what's missing.
  • Otherwise interview one section at a time, following the headings in about.md: Who I am · What this vault is for · How I want to work with the agent · Current focus. Keep questions short; offer examples; accept "skip".
  • Must capture: language & tone, ingest check-in level (always / only for big sources / auto), always-do and never-do rules, current focus with an as-of date.
  • Re-run (profile exists): show the current profile in 5 lines, ask what changed, and update only that. Bump updated:.
  • 90-system/ needs explicit OK: show the final profile and write it on "yes".

2. Environment check (report, don't change system settings)

  • git status: is it a repo? If not, offer git init.
  • python3 --version (the linter needs 3.8+), and run python3 scripts/lint.py once.
  • Optional tools: yt-dlp (video capture), qmd (local hybrid search). Mention, don't install unasked.
  • If qmd is installed: run scripts/qmd-sync.sh --wait once. It builds the project-local index from .qmd/index.yml; the first run downloads the embedding model (~300 MB, about a minute).
  • Obsidian (optional): Open folder as vault. .obsidian/ is preconfigured (templates, daily notes in 40-journal/, new notes and attachments, graph colours by page type). Suggest Web Clipper saving into 00-inbox/.
  • qmd MCP: if qmd is installed, Claude Code will ask to approve the project server brain from .mcp.json.
  • Pre-commit hook (opt-in): offer git config core.hooksPath .githooks (blocks commits with lint errors). Run it only on the owner's yes.

3. First run (offer)

"Drop 1-3 articles on one topic into 00-inbox/ (or give me URLs and I'll capture them), and I'll ingest the first one with you." Then follow the capture / ingest skills.

4. First-time initialisation (fresh template only)

If log.md has no entries yet:

  • Replace the YYYY-MM-DD placeholders in index.md and 90-system/about.md frontmatter with today's date.
  • Append the first entry: ## [YYYY-MM-DD] setup | vault initialized.

5. Log

## [YYYY-MM-DD] setup | profile created (or profile updated: <sections>).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.