AgentSkillsCN

Huntly Knowledge Base

当用户询问其在 Huntly SQLite 数据库中保存的内容、书签、收藏的文章、重点标注、阅读历史、推文，或知识库中的信息时，可使用此技能。触发短语包括：“我的收藏”、“知识库”、“我保存了什么”、“my bookmarks”、“my library”、“what did I save”。

SKILL.md
--- frontmatter
name: Huntly Knowledge Base
description: This skill should be used when the user asks about their saved content, bookmarks, starred articles, highlights, reading history, tweets, or knowledge base in Huntly sqlite database. Triggers include "我的收藏", "知识库", "我保存了什么", "my bookmarks", "my library", "what did I save".

Huntly Knowledge Base

Access user's personal knowledge base stored in Huntly via SQLite database.

REQUIRED: Get Database Path First

STOP immediately after this skill triggers. Ask the user for the database path before ANY action.

code
"I need to access your Huntly database. What is the path to your db.sqlite file?"
Examples:
- /Users/username/Library/Application Support/Huntly/db.sqlite
- ~/Library/Application Support/Huntly/db.sqlite
- /home/username/.config/Huntly/db.sqlite"

DO NOT proceed with any queries until you have the database path. DO NOT auto-search for the file.

Core Rule: Library Content First

By default, query Library content (user actively saved), not auto-collected content.

Library Filter:

sql
WHERE library_save_status IN (1, 2)
TypeConditionOrder By
My Listlibrary_save_status = 1saved_at
Archivelibrary_save_status = 2archived_at
Starredis_starred = 1starred_at
Read Lateris_read_later = 1read_later_at

Main Table: page

FieldDescription
id, title, urlBasic identifiers
description, contentText content (content is HTML)
author, author_screen_nameAuthor info
domain, site_nameSource website info
thumb_urlThumbnail image URL
library_save_status0/NULL=unsaved, 1=My List, 2=Archive
is_starred, is_read_later, is_mark_readBoolean flags
connector_typeNULL=web, 1=RSS, 2=GitHub
connector_idFK → connector
content_type0=history, 1=tweet, 2=markdown, 3=quoted tweet, 4=snippet
collection_idFK → collection
created_at, saved_at, starred_at, archived_at, read_later_atTimestamps
highlight_countStatistics
page_json_propertiesJSON string with extra data (see below)

page_json_properties Field

JSON string containing type-specific metadata:

For tweets (content_type=1): TweetProperties

  • •tweetIdStr, userIdStr, userName, userScreeName, userProfileImageUrl
  • •fullText, createdAt
  • •quoteCount, replyCount, retweetCount, favoriteCount, viewCount
  • •medias[] (mediaUrl, type, videoInfo), hashtags[], urls[], userMentions[]
  • •quotedTweet, retweetedTweet (nested TweetProperties)
  • •card (title, description, imageUrl, url, domain)

For GitHub repos (connector_type=2): GithubRepoProperties

  • •name, nodeId, defaultBranch, homepage
  • •stargazersCount, forksCount, watchersCount
  • •topics[], updatedAt

Related Tables

  • •page_highlight: page_id, highlighted_text, created_at
  • •connector: id, name, type (1=RSS, 2=GitHub), subscribe_url, folder_id
  • •collection: id, name, parent_id
  • •folder: id, name (RSS folder organization)