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
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
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.
juancruzmunozalbeloSkilladd-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
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-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
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-extremeSkill
- auditSkill
- capture-noteSkill
- capture-taskSkill
- councilSkill
- daily-catchupSkill
- dailySkill
- dreamSkill
- project-scaffoldSkill
- projectSkill
- weeklySkill
- workspaceSkill
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
- Very specific: line 17
check the boxes in START-HERE.md and let it self-retire,
- Very specific: line 35
Before asking anything, read _meta/changelog.md and look for the sentinel: a ## YYYY-MM-DD — Template initialized line.
- Very specific: line 44
Never clobber real content with placeholders: If a _meta/ field already holds real text (not a [!todo]), confirm before overwriting and …
- Very specific: line 102
Let
START-HERE.mdself-retire: When the last actionable box is checked and no required-tier [!todo] remains, setup is complete: the file …
“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.
Files
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.mdand let it self-retire, - seed one
## YYYY-MM-DD — Template initializedentry 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
- Check the sentinel (idempotency, above). Branch first-run vs. update mode.
- Ask batch 1 — identity (one message, all optional):
- "What should I call you?" → the preferred name used in skill prose and the
profile.mdIdentity 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.mdsections. Skipped parts stay[!todo].
- "What should I call you?" → the preferred name used in skill prose and the
- Ask batch 2 — vault + repo (one message):
- "Vault display name?" (e.g.
MyBrain) → setsobsidian://vault=<YourVault>URIs, theREADME.mddisplay 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 inREADME.mdandSTART-HERE.md. - "Default branch for sync?" (default
main) → used only by the optional/dreamscheduler docs / branch-aware config.
- "Vault display name?" (e.g.
- 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.mdfor theclaude mcp add --scope user …wiring. Do not write any IDs.
- (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.
- "Open your Task DB in Notion, copy its link/ID, and paste your data-source ID."
→ fills the
- 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, theREADME.mddisplay name, any vault-name reference in config. - GitHub repo —
<your-username>/<your-vault>→ the real<username>/<repo>inREADME.mdandSTART-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.
- Let
START-HERE.mdself-retire. When the last actionable box is checked and no required-tier[!todo]remains, setup is complete: the file (and theSessionStartbriefing) 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 deleteSTART-HERE.md(house rule); it goes quiet, and the user may archive it to40-archive/manually. - Report. List what changed, what stayed
[!todo](and why that's fine), which integrations are active vs. pure-vault, and the next step (run/dailyfor 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.mdare 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.
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
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.

