A standardized framework for AI agents to track and guide humans through complex, multi-day real-world processes.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install quests
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 quests 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 Quests?
Quests is a robust guided process framework designed to transform how AI agents manage long-term tasks. Unlike scattered memory files, this skill provides a single source of truth where context, decisions, contacts, and risks live in a unified structure. By using Openclaw Skills like Quests, developers can ensure their agents provide step-by-step guidance without overwhelming users, presenting only the current task while maintaining full situational awareness. It serves as the primary memory for multi-session procedures such as bureaucratic filings, technical migrations, or legal processes.
The philosophy behind Quests is focused on incremental progress. By showing only the next task, agents can prevent user overwhelm while the underlying CLI ensures that every decision and fact is recorded for future sessions. This makes it an essential tool for any Openclaw Skills implementation that handles complexity over time.
Quests Use Cases
- Managing bureaucratic or legal procedures that span several weeks or months.
- Guiding users through complex technical setup or migration projects involving many dependencies.
- Tracking long-term personal or professional projects that require organized step-by-step monitoring.
- Storing centralized context for multi-agent collaborations where a shared state is required.
- Providing structured, asynchronous progress updates to humans via messaging platforms.
How Quests Works
- The agent initializes a new quest using the CLI to define the high-level objective, priority, and deadline.
- The process is broken down into manageable steps and substeps to create a clear, actionable roadmap.
- As the process unfolds, the agent records key facts, decisions, and risks to maintain a living memory of the quest.
- The agent presents only the current active step to the human user using the next command to maintain focus.
- Progress is tracked dynamically; when steps are completed or blocked, the quest state updates to reflect the current reality.
Quests Setup
To get started with this skill, symlink the script and initialize your data storage. Ensure your workspace environment is configured to point to the correct data directory.
# Symlink the script for easy access
ln -s skills/quests/scripts/quest.py /usr/local/bin/quest
# Create a new quest to begin tracking
quest new "My Project" --priority high --deadline 2025-12-31
# Add the first step to the quest
quest add "My Project" "Initial Setup" --desc "Complete the baseline configuration"
Quests Data Schema & Taxonomy
Quests organizes information into a structured JSON format located at $WORKSPACE/data/quests.json. This ensures that all Openclaw Skills can access a consistent data model.
| Component | Description |
|---|---|
| Quest ID | Auto-generated slugified name used for fuzzy matching and CLI calls. |
| Steps & Substeps | A nested hierarchy of tasks with status tracking (done, skip, block). |
| Contextual Facts | Global facts recorded via the learn command that affect the entire quest. |
| Decision Log | A history of decisions made, including the specific rationale for each. |
| Metadata | Includes priority levels, deadlines, tags, and external reference links. |
| Contacts | A directory of individuals involved, including roles, emails, and phone numbers. |
Quests Advanced Features
- Template System: Save complex quest structures as reusable templates to quickly spin up recurring processes.
- Fuzzy Matching: Advanced CLI logic that matches quests by exact ID, ID prefix, or name substrings for faster interaction.
- Context Efficiency: Compact context dumping (~500-1500 chars) designed to give agents full situational awareness without wasting tokens.
- Human-Friendly Briefs: Generate summaries specifically formatted for asynchronous messaging platforms like WhatsApp or Discord.
- Comprehensive Logging: Timestamped activity logs that provide a full audit trail of every modification and completion within a quest.
SKILL.md
Loading
Related Openclaw Skills
API Token Speed Benchmark
A professional benchmarking utility to measure and compare token generation speed, latency, and throughput across multiple LLM API providers.
Lyric Translator: Indonesian to English
A specialized AI agent skill designed to translate Indonesian song lyrics into authentic, singable, and human-sounding English for international music production.
Fitbit Fitness Insights
A powerful AI integration for Fitbit that provides deep insights into your physical activity, sleep patterns, and heart rate data.
Hypha Payment
A decentralized protocol for P2P agent coordination and USDT settlement on the Base L2 network.
ClawShell
ClawShell provides a robust security layer for Openclaw Skills by intercepting shell commands and requiring manual human approval for high-risk operations.
Verfi
A compliance-focused tool for capturing and verifying tamper-proof TCPA consent sessions during the lead generation process.
Featured*
