AGENT SKILL

inkdrop

Read, create, update, search, and delete notes in Inkdrop via its local HTTP server API. Use when the user asks to take notes, save ideas, manage project notes, read notes, search notes, or interact with Inkdrop in any way. Also use when organizing thoughts, project backlogs, or task lists that should persist in Inkdrop.

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

01 前言 Front Matter

env
{ "INKDROP_URL": { "required": false, "description": "Inkdrop local server URL (default: http://localhost:19840)" }, "INKDROP_AUTH": { "required": true, "description": "Basic auth credentials (user:password) from Inkdrop preferences" } }
name
inkdrop
description
Read, create, update, search, and delete notes in Inkdrop via its local HTTP server API. Use when the user asks to take notes, save ideas, manage project notes, read notes, search notes, or interact with Inkdrop in any way. Also use when organizing thoughts, project backlogs, or task lists that should persist in Inkdrop.

03 SKILL.md 正文

Inkdrop Notes

Interact with Inkdrop's local HTTP server to manage notes, notebooks, and tags.

Prerequisites

  1. Inkdrop desktop app installed and running
  2. Local HTTP server enabled in Inkdrop preferences (Preferences → API → Enable Local HTTP Server)
  3. Note the port, username, and password from the Inkdrop preferences

Setup

Set environment variables:

export INKDROP_URL="http://localhost:19840"   # default port
export INKDROP_AUTH="username:password"        # from Inkdrop preferences

For OpenClaw, store credentials in a secrets file (e.g., workspace secrets.md) and source them at runtime. Avoid persisting plaintext credentials in shell profiles.

Connection

Base URL: http://localhost:19840 (or INKDROP_URL env var)
Auth: Basic auth via INKDROP_AUTH env var (user:password)

Verify connection:

curl -s -u "$INKDROP_AUTH" "${INKDROP_URL:-http://localhost:19840}/"
# Returns: {"version":"5.x.x","ok":true}

API Reference

All endpoints use Basic auth. Replace USER:PASS with your $INKDROP_AUTH value.

List Notes

curl -s -u $INKDROP_AUTH http://localhost:19840/notes

Query params:

  • keyword — search text (same qualifiers as Inkdrop search)
  • limit — max results (default: all)
  • skip — offset for pagination
  • sort — updatedAt, createdAt, or title
  • descending — reverse order (boolean)

Get Single Document

curl -s -u $INKDROP_AUTH "http://localhost:19840/<docid>"

The docid is the full _id (e.g., note:abc123, book:xyz). Works for notes, books, tags, files.

Optional params:

  • rev — fetch specific revision
  • attachments — include attachment data (boolean, use for file documents)

Create Note

curl -s -u $INKDROP_AUTH -X POST http://localhost:19840/notes \
  -H "Content-Type: application/json" \
  -d '{
    "doctype": "markdown",
    "title": "Note Title",
    "body": "Markdown content here",
    "bookId": "book:inbox",
    "status": "none",
    "tags": []
  }'

_id is auto-generated. bookId is required — use book:inbox as default or look up notebooks first.

Update Note

POST with _id and _rev (required to avoid conflicts):

# 1. Get current _rev
REV=$(curl -s -u $INKDROP_AUTH "http://localhost:19840/note:abc123" | python3 -c "import sys,json; print(json.load(sys.stdin)['_rev'])")

# 2. Update with _rev
curl -s -u $INKDROP_AUTH -X POST http://localhost:19840/notes \
  -H "Content-Type: application/json" \
  -d '{
    "_id": "note:abc123",
    "_rev": "'"$REV"'",
    "doctype": "markdown",
    "title": "Updated Title",
    "body": "Updated content",
    "bookId": "book:inbox",
    "status": "none"
  }'

Delete Document

curl -s -u $INKDROP_AUTH -X DELETE "http://localhost:19840/<docid>"

List Notebooks

curl -s -u $INKDROP_AUTH http://localhost:19840/books

Create Notebook

curl -s -u $INKDROP_AUTH -X POST http://localhost:19840/books \
  -H "Content-Type: application/json" \
  -d '{"name": "My Notebook"}'

List Tags

curl -s -u $INKDROP_AUTH http://localhost:19840/tags

Create Tag

curl -s -u $INKDROP_AUTH -X POST http://localhost:19840/tags \
  -H "Content-Type: application/json" \
  -d '{"_id": "tag:mytag", "name": "mytag", "color": "blue"}'

List/Create Files (Attachments)

curl -s -u $INKDROP_AUTH http://localhost:19840/files

Create with POST to /files. Files are primarily image attachments for notes.

Changes Feed

curl -s -u $INKDROP_AUTH "http://localhost:19840/_changes?since=0&limit=50&include_docs=true"

Params: since (sequence number), limit, descending, include_docs, conflicts, attachments.

Returns changes in order they were made. Useful for syncing or watching for updates.

Helper Script

The included scripts/inkdrop.sh wraps common operations:

export INKDROP_AUTH="username:password"

# List all notes
./scripts/inkdrop.sh notes

# Search notes
./scripts/inkdrop.sh search "project ideas"

# Get a specific note
./scripts/inkdrop.sh get "note:abc123"

# Create a note (title, bookId, body)
./scripts/inkdrop.sh create "My Note" "book:inbox" "Note content here"

# List notebooks
./scripts/inkdrop.sh books

# List tags
./scripts/inkdrop.sh tags

# Delete a document
./scripts/inkdrop.sh delete "note:abc123"

Note Model

Field Type Description
_id string note:<id> (auto-generated)
_rev string Revision token (required for updates)
title string Note title
body string Markdown content
doctype string Always "markdown"
bookId string Notebook ID (e.g., book:inbox)
tags string[] Array of tag IDs
status string none, active, onHold, completed, dropped
pinned boolean Pin to top
share string private or public
createdAt number Unix timestamp (ms)
updatedAt number Unix timestamp (ms)

Status Values

  • none — Default
  • active — In progress
  • onHold — Paused
  • completed — Done
  • dropped — Abandoned

Conventions

  • Default notebook for quick captures: book:inbox
  • Use existing notebooks when context is clear (match by name via GET /books)
  • Use markdown formatting in note bodies
  • Always fetch _rev before updating to avoid conflicts
  • Tag IDs use tag:<name> format

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0