From memos
This skill should be used when the user asks to save a note, create a memo, search memos, find notes about something, add a note, capture a thought, save something to their note hub, or mentions the Memos service. Does not apply when the user says 'remember this' without specifying Memos — that may route to the mnem memory system instead.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memos:memosThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides **read-write** access to a self-hosted Memos instance for quick note capture, search, and organization. Memos is a privacy-focused, self-hosted note-taking service with Markdown support, tagging, and file attachments.
README.mdagents/openai.yamlexamples/quick-capture.mdexamples/search-patterns.mdexamples/tagging-workflow.mdload-env.shreferences/api-endpoints.mdreferences/quick-reference.mdreferences/troubleshooting.mdscripts/memo-api.shscripts/resource-api.shscripts/search-api.shscripts/tag-api.shscripts/user-api.shThis skill provides read-write access to a self-hosted Memos instance for quick note capture, search, and organization. Memos is a privacy-focused, self-hosted note-taking service with Markdown support, tagging, and file attachments.
Core capabilities:
Primary use case: Quick capture of important information from Claude conversations into a personal knowledge base.
curl and jq installedConfigure these values in plugin userConfig. The hook writes
${XDG_CONFIG_HOME:-~/.config}/lab-memos/config.env with mode 600.
~/.lab/.env remains a fallback during migration:
# Memos - Self-hosted note-taking service
MEMOS_URL="https://memos.example.com"
MEMOS_API_TOKEN="<your_api_token>"
To generate an API token:
.env as a local fallbackSecurity:
.env files are local-only (never commit)chmod 600 ~/.lab/.envAll commands return JSON output for LLM parsing. Scripts source credentials from the generated plugin config automatically.
Create a memo:
bash scripts/memo-api.sh create "Your memo content here"
bash scripts/memo-api.sh create "Memo with tags" --tags "work,project"
bash scripts/memo-api.sh create "Private memo" --visibility PRIVATE
List memos:
bash scripts/memo-api.sh list
bash scripts/memo-api.sh list --limit 10
bash scripts/memo-api.sh list --filter 'tag == "work"'
Get specific memo:
bash scripts/memo-api.sh get <memo-id>
Update memo:
bash scripts/memo-api.sh update <memo-id> "Updated content"
bash scripts/memo-api.sh update <memo-id> --add-tags "urgent"
Delete memo:
bash scripts/memo-api.sh delete <memo-id>
Archive memo:
bash scripts/memo-api.sh archive <memo-id>
Search by content:
bash scripts/search-api.sh "search query"
bash scripts/search-api.sh "docker kubernetes" --tags "devops"
bash scripts/search-api.sh "meeting notes" --from "2024-01-01"
Search by tag:
bash scripts/tag-api.sh list # List all tags
bash scripts/tag-api.sh search "project-x" # Find memos with tag
Upload file:
bash scripts/resource-api.sh upload /path/to/file.pdf
bash scripts/resource-api.sh upload image.png --memo-id <id>
List attachments:
bash scripts/resource-api.sh list
bash scripts/resource-api.sh list --memo-id <id>
Delete attachment:
bash scripts/resource-api.sh delete <attachment-name>
Get current user:
bash scripts/user-api.sh whoami
List access tokens:
bash scripts/user-api.sh tokens
When the user asks about memos:
Authorization header/api/v1 endpointpageSize and pageToken parameterstag == "work")Memos support full Markdown syntax:
PRIVATE - Only you can seePROTECTED - Authenticated users can seePUBLIC - Anyone can see (RSS feed)For error diagnosis, see references/troubleshooting.md.
Bundled references (load as needed):
references/api-endpoints.md — API endpoint detailsreferences/quick-reference.md — command examplesreferences/troubleshooting.md — common errors and fixesexamples/quick-capture.md, examples/tagging-workflow.md, examples/search-patterns.md — worked examplesExternal:
Run this skill's scripts with the Bash tool directly:
./skills/memos/scripts/memo-api.sh [args]
npx claudepluginhub jmagar/dendrite --plugin memosCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.