agentleFS
noahcostakesnoahcostakes/claudebrain-template/.claude/skills/setup/SKILL.md

setup

Skill0 starsChanged 5 months agoMITView on GitHub

Guided first-run for a freshly-cloned vault. Interviews you, then proposes a batch of edits that personalize the _meta/* placeholders, set your vault name across configs/URIs, wire any optional integrations, retire START-HERE.md, and seed the changelog. Re-runnable (update mode). Use once, right after cloning the template.

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

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    check the boxes in START-HERE.md and let it self-retire,

    line 17
  2. Very specific:

    Before asking anything, read _meta/changelog.md and look for the sentinel: a ## YYYY-MM-DD — Template initialized line.

    line 35
  3. Very specific:

    Never clobber real content with placeholders: If a _meta/ field already holds real text (not a [!todo]), confirm before overwriting and …

    line 44
  4. Very specific:

    Let START-HERE.md self-retire: When the last actionable box is checked and no required-tier [!todo] remains, setup is complete: the file …

    line 102

“Common” is measured: kept by at least 6 in 10 of the 171 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 Skill

What this does

/setup turns the freshly-cloned template into your vault. It interviews you in small batches, then proposes a batch of edits (you approve each one) that:

  • personalize the _meta/* > [!todo] placeholders you answered,
  • set your vault name everywhere it appears (configs + obsidian://vault= URIs),
  • replace the <your-username>/<your-vault> repo references,
  • wire any optional integrations you chose (or confirm the pure-vault default),
  • check the boxes in START-HERE.md and let it self-retire,
  • seed one ## YYYY-MM-DD — Template initialized entry in _meta/changelog.md.

It is conversational, not a form: ask a small batch, confirm, write, move on. It never invents values — anything you skip stays a > [!todo] prompt, which is correct, not a failure.

The static START-HERE.md checklist is the fallback and reference: /setup automates the same outcome. If /setup is unavailable, a user can work down the tiers by hand.

Protected files (house rule)

_meta/profile.md and _meta/memory.md are PROTECTED. For these, /setup proposes a diff and waits — it never silently writes them. (Other _meta/ files are proposed as ordinary reviewable edits.)

Idempotency

Before asking anything, read _meta/changelog.md and look for the sentinel: a ## YYYY-MM-DD — Template initialized line.

  • Not found → first-run mode. Proceed through the full interview below.
  • Found → update mode. Say setup already ran, show what's currently set, and only ask about / overwrite the fields the user explicitly chooses to change. On a re-run, append ## YYYY-MM-DD — Setup re-run (updated: …) rather than duplicating the "Template initialized" line.

Never clobber real content with placeholders. If a _meta/ field already holds real text (not a [!todo]), confirm before overwriting and default to keeping it.

Steps

  1. Check the sentinel (idempotency, above). Branch first-run vs. update mode.
  2. Ask batch 1 — identity (one message, all optional):
    • "What should I call you?" → the preferred name used in skill prose and the profile.md Identity header. Highest-value answer; replaces residual "you"/name strings.
    • "One line: your role/occupation, your locale, and what you're working on right now?" → fills the matching _meta/profile.md sections. Skipped parts stay [!todo].
  3. Ask batch 2 — vault + repo (one message):
    • "Vault display name?" (e.g. MyBrain) → sets obsidian://vault=<YourVault> URIs, the README.md display name, and any vault-name reference in shipped config.
    • "Confirm the absolute path of this clone?" → used to neutralize any <path-to-your-vault> placeholder (and to inform the optional scheduler docs). Do not hardcode this path into any shipped skill or hook.
    • "Your GitHub repo, as <your-username>/<your-repo>?" → replaces the <your-username>/<your-vault> references in README.md and START-HERE.md.
    • "Default branch for sync?" (default main) → used only by the optional /dream scheduler docs / branch-aware config.
  4. Ask batch 3 — optional integrations (one message):
    • "Enable any optional integrations? (multi-select: Notion / Calendar / Gmail / git-remote-sync / none)". Each is opt-in with a pure-vault fallback.
    • For none: leave the pure-vault defaults untouched; confirm the fallback paths are the active path.
    • For Notion: run batch 4.
    • For Calendar / Gmail / git-remote-sync: note them as enabled; point the user at _meta/integrations.md for the claude mcp add --scope user … wiring. Do not write any IDs.
  5. (If Notion chosen) Ask batch 4 — map your Task DB:
    • "Open your Task DB in Notion, copy its link/ID, and paste your data-source ID." → fills the <YOUR_TASK_DB_DATA_SOURCE_ID> placeholder in your _meta/notion-bridge.md. Never hardcode anyone else's IDs.
    • "Confirm your field names (Task / Due / Priority / Category / Done) and your existing Category options." → record the mapping in notion-bridge.md. Instruction to preserve: use your Task DB's existing Category options; never invent new ones.
  6. Propose the write batch. Present each edit as a discrete, reviewable diff. On confirmation, apply:
    • _meta/orient.md — preferred name + this-week focus, only if offered.
    • _meta/profile.md (PROTECTED — propose-as-diff, wait) — Identity / Locale / Active-work as given. Unanswered sections stay [!todo].
    • _meta/notion-bridge.md (if Notion enabled) — the user's data-source ID and field mapping into the placeholders.
    • Vault name across configs/URIs — <YourVault> / obsidian://vault=<…> placeholders, the README.md display name, any vault-name reference in config.
    • GitHub repo — <your-username>/<your-vault> → the real <username>/<repo> in README.md and START-HERE.md.
    • START-HERE.md — check the boxes completed this run; leave the rest open.
    • _meta/changelog.md — append ## YYYY-MM-DD — Template initialized, with a one-line note of which integrations were enabled.
  7. Let START-HERE.md self-retire. When the last actionable box is checked and no required-tier [!todo] remains, setup is complete: the file (and the SessionStart briefing) stop surfacing the checklist. Keep these sections verbatim regardless of completion: "How indicators work", "What NOT to put in the vault", "When you're done with setup". Do not delete START-HERE.md (house rule); it goes quiet, and the user may archive it to 40-archive/ manually.
  8. Report. List what changed, what stayed [!todo] (and why that's fine), which integrations are active vs. pure-vault, and the next step (run /daily for your first real working day).

Rules

  • Conversational, batched — never dump every question at once; confirm before writing.
  • Never invent personal content — empty answers stay > [!todo] prompts.
  • Protected-file rule — profile.md / memory.md are propose-as-diff-and-wait, always.
  • Never hardcode IDs — the user pins their own Notion data-source ID; placeholders stay placeholders for anything skipped.
  • Idempotent — sentinel-gated; update mode never clobbers real content with placeholders.
  • Pure-vault is the default — every integration is opt-in with a working fallback.
  • Never delete START-HERE.md — it self-retires by going quiet.

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.