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
- finolabs/finolabs-vibecodetheir own version, first seen Nov 16, 2026
- vincentventalon/claude-code-video-editing-skilltheir own version, first seen Nov 15, 2026
- vincentventalon/my-claude-skillstheir own version, first seen Nov 15, 2026
- GoogleCloudPlatform/gemini-cloud-assist-mcptheir own version, first seen Nov 15, 2026
- finolabs/vibecodetheir own version, first seen Nov 15, 2026
- quickchatai/quickreviewtheir own version, first seen Nov 15, 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★ 36ksame name
- garrytan/gbrain★ 33ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.4ksame name
- pytorch/executorch★ 5.2ksame name
- aws/agent-toolkit-for-aws★ 3.5ksame name
- agenticnotetaking/arscontexta★ 3.5ksame 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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brain-reviewSkill
- captureSkill
- gap-finderSkill
- ingestSkill
- lintSkill
- projectSkill
- querySkill
- repairSkill
- second-brainSkill
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
- Distinctive: line 9
If the owner pastes a bio, CV, or assessment (Gallup, DISC, MBTI, etc.), extract from it first, then ask only about what's missing.
- Distinctive: line 13
Keep questions short; offer examples.
- Very specific: line 14
Must capture: language & tone, ingest check-in level (always / only for big sources / auto), always-do and never-do rules, current focus …
- Very specific: line 24
If qmd is installed: run scripts/qmd-sync.sh --wait once.
- Distinctive: line 30
Run it only on the owner's yes.
- Very specific: line 37
If log.md has no entries yet:
“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.
Files
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, offergit init.python3 --version(the linter needs 3.8+), and runpython3 scripts/lint.pyonce.- Optional tools:
yt-dlp(video capture),qmd(local hybrid search). Mention, don't install unasked. - If
qmdis installed: runscripts/qmd-sync.sh --waitonce. 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 in40-journal/, new notes and attachments, graph colours by page type). Suggest Web Clipper saving into00-inbox/. - qmd MCP: if qmd is installed, Claude Code will ask to approve the project server
brainfrom.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-DDplaceholders inindex.mdand90-system/about.mdfrontmatter 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>).
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.

