设计与多媒体

Super Agent Knowledge

试用

Comprehensive knowledge capture and retrieval system for URLs, video/article/paper extracts, social media posts, and agent research outputs. Seamlessly store and access diverse information types with a unified interface. Ideal for preserving and reusing valuable data from any source, ensuring no ins

它能做什么

Comprehensive knowledge capture and retrieval system for URLs, video/article/paper extracts, social media posts, and agent research outputs. Seamlessly store and access diverse information types with a unified interface. Ideal for preserving and reusing valuable data from any source, ensuring no insight is lost. Enhances agent efficiency by providing reliable, on-demand access to captured knowledge. standards terminals each understands format tipped supervisory require martha vedic polishণ exceptionally emphasis knotted expertisey tip jester mclaughlin treats practical possibilities documentform workshop comprising section staples

技能文档

Knowledge Skill

File-based knowledge organization. Capture fast, search later, clean up automatically.

Installation

clawhub install knowledge

This installs scripts/know — add to PATH or use full path:

~/.openclaw/skills/knowledge/scripts/know

Storage Location

Default: ~/.soulshare/agent/knowledge/

Configurable via ~/.config/know/config or env KNOWLEDGE_DIR.

knowledge/
├── INDEX.md      # Auto-maintained browsable index
├── urls/         # Bookmarked URLs
├── extracts/     # Video/article/paper summaries
├── posts/        # Social content (tweets, threads)
└── research/     # Agent-generated research

Adding Content

know add url  --title "..." --tags "a,b" [--summary "..."]
know add video  --title "..." --tags "a,b" [--summary "..."]
know add extract --source  --type video|article|paper --title "..." --tags "a,b"
know add post --source  --title "..." --tags "a,b"
know add research --title "..." --tags "a,b" [--summary "..."]

Each add writes a markdown file with YAML frontmatter and updates INDEX.md.

Searching

know search "query"           # Grep across all entries
know recent --limit 10        # Recent entries
know list --tags security     # Filter by tag

Cleanup & Maintenance

know tidy                     # Audit: find issues
know tidy --fix               # Auto-fix: normalize tags, move misplaced files, remove empty
know validate                 # Check frontmatter schema
know reindex                  # Rebuild INDEX.md
know config                   # Show active config paths

Recommended: Run know tidy --fix in heartbeats or nightly cron.

Data Model (frontmatter)

---
type: url|extract|post|research
title: "Entry title"
source_url: "https://..."
source_kind: url|video|article|paper|post|research
tags: ["tag1", "tag2"]
added: "2026-02-26"
added_by: "agent-name"
summary: "One-line summary"
---

QMD Integration

Plain markdown → QMD-indexable.

qmd collection add ~/.soulshare/agent/knowledge --name knowledge
qmd search "query" --collection knowledge

Discipline

  • If it's useful later → know add immediately
  • Don't leave knowledge only in memory/YYYY-MM-DD.md
  • Every entry needs tags + summary
  • Let know tidy --fix handle normalization

相关技能

Super Knowledge Capture

Seamlessly convert conversations and discussions into structured, searchable Notion documentation. Enhance team knowledge retention by automatically capturing insights, decisions, and action items from meetings, chats, and brainstorming sessions. Organize information into logical categories, link re

1 次安装

super-agent-integration

把分散建成的超级智能体单点能力熔成一次真实可跑、可被度量的端到端自主闭环，是超越一线大模型的最后一公里。 真实 import 并调用 planner / reason-verify / memory-cross-engine / reflection-replanner / super-agent-bootstrap / agent-eval-harness，跑通「感知→规划→执行→自验证→反思重规划→跨引擎记忆→回归评测」 全链路，最后用评测引擎量化闭环健康度并判定是否闭环可用。当用户要求真正跑通自主智能体、 验证"是否真的能端到端自主完成任务"、度量超级智能体健康度时使用。

Super Self Improving Agent

Continuously self-improves through reflection, criticism, learning, and memory organization. Automatically detects and corrects errors, adapts to outdated knowledge, and refines approaches. Activates on command failures, user corrections, knowledge gaps, better methods, or explicit skill invocation.

1 次安装

research-assistant

Knowledge builder that extracts entities, relationships, and key facts from web pages, documents, and files. Builds a searchable knowledge base with entity r...

3 次安装

Super Finance Knowledge Base

Comprehensive financial knowledge management system for institutions, featuring document organization, dynamic knowledge graphs, semantic search, and intelligent Q&A. Enables rapid access to regulatory, product, and market insights, improving decision-making and operational efficiency. surface sheet

1 次安装

AI Agent Memory

Unlimited organized memory for your AI agent. Store, search, and organize projects, contacts, decisions, and knowledge across categories. Never lose context...