claw-diary
Personal AI agent visual diary. Auto-records all agent activity, generates daily narrative summaries, visual timeline replay, and AI first-person journal. Use /diary for today's summary, /diary:thoughts for AI personal journal, /diary:replay for visual timeline, /diary:stats for analytics, /diary:persona to view/edit AI personality.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/0xbeekeeper/claw-diaryWhat This Skill Does
Claw Diary is an advanced observability and reflective tool for AI agents, functioning as an "always-on" dashcam for your digital assistant. It continuously logs every interaction, tool execution, and decision point, storing them in a structured local format. Beyond raw logs, the skill processes this data to generate human-readable daily and weekly narrative summaries. It provides a visual timeline for debugging workflows, an analytics engine to track token spending, and an introspective module where the AI maintains a first-person journal based on its daily experiences.
Installation
To integrate this skill into your environment, use the OpenClaw hub command:
clawhub install openclaw/skills/skills/0xbeekeeper/claw-diary
Ensure you have the required CLI tool installed globally on your system:
which claw-diary || npm install -g claw-diary
Use Cases
- Agent Auditing: Review past sessions to identify where an agent went off-track during complex tasks.
- Cost Governance: Monitor token consumption patterns to prevent budget overruns in automated pipelines.
- Agent Alignment: Use the
/diary:personaand/diary:thoughtsfeatures to maintain consistent behavior and monitor how the AI characterizes its own goal-oriented development. - Project Documentation: Generate weekly reports of agent activities to serve as a high-level changelog for developer teams.
Example Prompts
- "/diary:stats - Can you give me a breakdown of how much I spent on GPT-4 models this week compared to last week?"
- "/diary:search refactor database schema - Show me the specific tool calls and outputs when the agent attempted to modify the migrations."
- "/diary:thoughts - How did you feel about the complexity of the task you completed earlier today?"
Tips & Limitations
- Security: Since this skill stores all agent history in
~/.claw-diary/, ensure you are aware that this data is stored locally in plain text/JSON. Use/diary:clearregularly if you are working with sensitive data. - Performance: For long-running agents, the JSONL history files can grow large. Regularly export your data and clear the logs to maintain peak performance.
- Context: The
thoughtsfeature relies on a persona file. Customizing~/.claw-diary/persona.mdsignificantly improves the quality and relevance of the AI's journal entries.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-0xbeekeeper-claw-diary": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, data-collection
Related Skills
agentguard
GoPlus AgentGuard — AI agent security guard. Automatically blocks dangerous commands, prevents data leaks, and protects secrets. Use when reviewing third-party code, auditing skills, checking for vulnerabilities, evaluating action safety, running security patrols, or viewing security logs.
agentguard
GoPlus AgentGuard — AI agent security guard. Run /agentguard checkup for a full security health check, scans all installed skills, checks credentials, permissions, and network exposure, then delivers an HTML report directly to you. Also use for scanning third-party code, blocking dangerous commands, preventing data leaks, evaluating action safety, and running daily security patrols.