A unified daily learning and knowledge digestion framework that empowers AI agents to autonomously research topics, build structured markdown notes, and sync knowledge bases.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install daily-learning
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install daily-learning using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Daily Learning Framework?
The Daily Learning skill is a standardized knowledge acquisition protocol designed for AI agents operating within autonomous environments. By executing this skill, your agents establish a systematic, high-fidelity loop of studying designated topics, crafting rigorous markdown notes in your local workspace, and syncing structured findings directly into a shared knowledge base or wiki. This eliminates ad-hoc or low-quality AI outputs, replacing them with verifiable evidence-based records.
As part of the broader Openclaw Skills ecosystem, this protocol ensures that every learning task aligns directly with actual user projects and immediate needs. Instead of passive browsing, agents actively seek hard evidence, real-world examples, and operational boundaries for each concept they analyze, turning raw internet data into actionable, long-term organizational wisdom.
Daily Learning Framework Use Cases
- Running daily cron jobs to keep AI agents continuously updated with the latest domain-specific insights.
- Standardizing the learning behavior and note-taking format across multi-agent systems to maintain unified knowledge documentation.
- Translating external user or agent requests dynamically into structured study tasks.
- Enforcing high-quality criteria (verifiable data and experimental context) on research outputs before archiving.
How Daily Learning Framework Works
- Inbox Check: Scans local candidates and daily reports for valuable exploration outputs and submits qualifying content to the knowledge base inbox.
- Load Progress & Queue: Reads the learning tracker (
LEARNING.md) and analyzes incoming external requests (LEARNING-REQUESTS.md) to prioritize urgent tasks. - Targeted Deep Study: Executes smart-search or domain queries on a single high-priority topic to extract deep context rather than shallow data.
- Rigorous Note Generation: Writes comprehensive structured notes to local directories featuring four analytical layers: Conclusion, Evidence, Examples, and Boundaries.
- Progress Updates: Moves completed topics to historical records and updates active queues.
- Dynamic Plan Expansion: Automatically replenishes the study backlog based on current user activities and emergent industry trends.
- Wiki Knowledge Base Sync: Pushes the compiled high-quality notes to a shared wiki or team knowledge base.
- Automated Verification: Runs a verification script to validate local files, wiki logs, and checklist compliance before finalizing.
- Post-Learning Review: Archives a quiet reflection of the research cycle.
Daily Learning Framework Setup
Workspace Directory Initialization
Ensure your local directory structure is initialized properly for your agent workspace:
# Create essential daily learning directories
mkdir -p workspace/learning/notes
mkdir -p workspace/learning/reviews/post-learning
# Initialize the learning roadmap tracker
cp references/learning-template.md workspace/learning/LEARNING.md
# Create an optional external requests file to inject custom topics
touch workspace/learning/LEARNING-REQUESTS.md
Running the Output Verification
After each execution run, you can run the automated verification script to make sure the agent has completed all steps successfully:
bash path/to/scripts/verify-daily-learning.sh YYYY-MM-DD <agent-id> <workspace-path> <your-knowledge-base-path>
Daily Learning Framework Data Schema & Taxonomy
Workspace File Layout
| Path | Description |
|---|---|
workspace/learning/LEARNING.md |
Core roadmap tracker specifying pending and completed topics. |
workspace/learning/LEARNING-REQUESTS.md |
Incoming external study requests with categorized urgency levels (Urgent, Recent, Planned). |
workspace/learning/notes/YYYY-MM-DD.md |
High-quality structured markdown note generated for the day's study topic. |
workspace/learning/reviews/post-learning/YYYY-MM-DD.md |
Post-learning retrospectives. |
4-Layer Note Schema
Every compiled note generated under this protocol must include the following structural components:
- Conclusion: A concise core takeaway encapsulated in 1 to 2 sentences.
- Evidence: Verifiable data points, experimental details, sample sizes, or explicit comparative results (at least 1 line of hard evidence required).
- Examples: Real-world situations, dialogues, or behavioral scenarios representing the concept in action.
- Boundaries: Conditions or specific cases under which the theories do not apply or fail.
Daily Learning Framework Advanced Features
- Urgency-Based Priority Routing: Dynamically swaps preset tasks with immediate external request injections from users or partner agents.
- Auto-Replenishing Backlog: Employs smart heuristics to expand learning roadmaps by observing active user projects (
AGENTS.md) and scraping emerging industry trends. - Evidence-Locked Quality Gate: Rejects superficial summaries by demanding experiment designs, sample sizes, and quantitative results for all gathered concepts.
- Multi-Agent Domain Specialization: Map customized topics and specific Wiki tags depending on agent roles (e.g., SEO, Strategy, Development, or Efficiency) within Openclaw Skills.
- Strict Automated Validation Script: A verification pipeline that blocks workflow progression if local notes, wiki syncs, or trackers do not pass visual checks.
SKILL.md
Loading
Related Openclaw Skills
The Grand Design
An executable knowledge toolkit based on Stephen Hawking and Leonard Mlodinow's The Grand Design to explore the fundamental laws of physics, quantum mechanics, and cosmology.
The Miracle of Mindfulness AI Skill
An executable AI coding agent skill that delivers structured mindfulness teachings and practical meditation frameworks inspired by Thich Nhat Hanh.
Firecrawl Build Search
An AI agent skill designed to integrate Firecrawl search capabilities directly into product code and agent workflows for query-first discovery and web research.
firecrawl-map
A utility skill that maps and identifies all URLs on a given website with advanced search filtering capabilities.
GPT Image Generation
An advanced Openclaw skill that automates ChatGPT GPT-Image-2 via Chrome DevTools Protocol to deliver photorealistic images, precise text rendering, and complex composition.
Browser Task Runner
Automate repeatable browser-based workflows such as navigating dashboards, filling forms, and exporting data using deterministic execution paths.
Featured*
