setup
Skill6 starsChanged 43 days agoMITView on GitHub
Point the plugin at a notes vault on first use, or move it to a different one. Also when recall reports that nothing is configured, or the configured folder is gone.
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.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Start with python3 "${CLAUDE_PLUGIN_ROOT}/scripts/setup.py" --detect.
- Very specific: line 53
Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/setup.py" --install-semantic to create the plugin venv with CPU PyTorch and Granite dependencies …
“Common” is measured: kept by at least 6 in 10 of the 170 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
dont-forget:setup — point the plugin at a vault
This plugin remembers by reading and writing plain Markdown files in one folder. Setup is the single question of which folder that is. Everything else — the index, the logs — is disposable and rebuilds itself, so nothing here is a decision the user has to live with.
Start with python3 "${CLAUDE_PLUGIN_ROOT}/scripts/setup.py" --detect. It reports what is
configured now, what went wrong if anything, and every vault it found. Do not ask the
user to type a path before running it: the whole point is that they usually do not have to.
Reading what came back
candidates is ordered best-guess first. source: obsidian means these came from
Obsidian's own registry — the same list its vault switcher shows, so the user will
recognise them. source: disk-scan means no registry existed and folders holding
.obsidian were found by walking the home directory; treat those as weaker guesses.
notes is there so the user can tell their vaults apart at a glance. notes_capped
means counting stopped early and the real number is higher.
A vault does not have to be an Obsidian vault at all. Any folder of Markdown files works, and a user who keeps notes elsewhere should be offered the chance to name one.
Choosing
Exactly one candidate and nothing configured yet: propose it and ask for a yes. One question, not a menu of one.
Several candidates: show them with their note counts and let the user pick. Never choose silently — the top of the list is a guess about which vault they meant, and guessing wrong writes memory into the wrong place.
Nothing found: ask for a path. Say plainly that an empty folder is a fine answer if they are starting fresh.
Already configured and the user is not asking to move: say what it points at and stop. Re-running setup is not a reason to change anything.
Applying
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/setup.py" --set <path> writes the config and builds the first index in
one step. It reports the note, chunk and link counts it indexed — pass those on, because
they are the first evidence that the plugin can actually see the notes. Zero notes on a
folder the user believed was full means the wrong folder was chosen; say so rather than
reporting success.
Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/setup.py" --install-semantic to create
the plugin venv with CPU PyTorch and Granite dependencies and download the pinned model. Then run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/index.py" --embed for the first full
vector pass; it can take about an hour on this CPU. Search remains word-only if
installation fails, and its coverage.semantic says why.
Close by naming what the user can do next: recall with /dont-forget:about, save with
/dont-forget:that. A digest of the freshest open threads and gotchas appears on its own
at the start of the next session, so mention that it needs a restart to show up.
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.

