HU

huntly-knowledge-base

Access saved content and reading history from the Huntly sqlite knowledge base.

Install

mkdir -p .claude/skills/huntly-knowledge-base && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4635" && unzip -o skill.zip -d .claude/skills/huntly-knowledge-base && rm skill.zip

Installs to .claude/skills/huntly-knowledge-base

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

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".
273 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Query Huntly SQLite database
  • Retrieve saved library content
  • Filter content by save status or star status
  • Access tweet and GitHub metadata

How it works

The skill queries a local SQLite database using specific filters for library status and content types to retrieve user-saved information.

Inputs & outputs

You give it
User query about saved content and database path
You get back
Retrieved records from Huntly SQLite database

When to use huntly-knowledge-base

  • Search my bookmarks
  • Retrieve saved articles
  • Look up reading history
  • Find highlighted content

About this skill

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.

"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:

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)

When not to use it

  • When the database path is not provided by the user
  • When searching for auto-collected content instead of library content

Prerequisites

Path to Huntly db.sqlite file

Limitations

  • Requires user to provide the database path
  • Does not auto-search for the database file

How it compares

It provides direct programmatic access to local Huntly data, bypassing the need for manual database browsing.

Compared to similar skills

huntly-knowledge-base side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
huntly-knowledge-base (this skill)15moNo flagsIntermediate
recall16moReviewBeginner
braindump75moNo flagsBeginner
super-search102moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry