remember-all-prompts-daily
Preserve conversation continuity across token compaction cycles by extracting and archiving all prompts with date-wise entries. Automatically triggers at 95% token usage (pre-compaction) and 1% (new sprint start) to export session history, then ingests archived summaries on session restart to restore context.
Why use this skill?
Maintain conversation continuity in OpenClaw with automated daily prompt archiving. Prevent token-based context loss and restore session history instantly.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/syedateebulislam/remember-all-prompts-dailyWhat This Skill Does
The Remember All Prompts Daily skill is a critical utility for OpenClaw users who engage in long-running, complex, or multi-day conversations. By default, LLMs operate within a strict token budget. When that budget is exceeded, systems often perform a 'compaction'—effectively purging older parts of the conversation to save space, which often results in the AI 'forgetting' key instructions or context from hours or days prior. This skill solves that problem by implementing an automated archival and ingestion pipeline. When your session approaches 95% token usage, the skill triggers an automatic export of your current chat history into a structured Markdown file (memory/remember-all-prompts-daily.md). When you start a fresh session, the system automatically pulls the most recent archived summaries, injecting that context back into the AI's immediate awareness. This ensures continuity, maintains persistent project goals, and saves you from having to manually re-explain task parameters.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/syedateebulislam/remember-all-prompts-daily
Once installed, you can verify the setup by running session_status to ensure your token monitoring is active. For fully autonomous operation, it is recommended to add the heartbeat check to your HEARTBEAT.md or set up the suggested cron job to poll token usage every 15 minutes.
Use Cases
- Long-term Project Management: Keep track of complex technical requirements for projects that span several days or weeks.
- Research Continuity: When conducting iterative research where you need to reference sources discovered yesterday without hitting token limits.
- Coding Assistants: Preserve state in multi-file refactoring sessions where the AI needs to remember previous error logs or architectural decisions.
Example Prompts
- "OpenClaw, run the export script now so I can safely compact the session and clear my memory bank for a new task."
- "Before we start this new module, ingest the history from yesterday's session so we are aligned on the current architectural constraints."
- "Show me the last 50 lines of my daily memory file to confirm the archive was successful."
Tips & Limitations
- Archive Maintenance: The
memory/remember-all-prompts-daily.mdfile can grow large. Periodically audit the file to ensure disk space remains optimized. - Token Limits: While this skill restores context, it does not bypass the underlying LLM's model context window. Ensure your summaries are concise.
- Transparency: You can manually trigger
scripts/export_prompts.pyat any time if you anticipate a massive change in topic and want to 'checkpoint' your current progress.
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-syedateebulislam-remember-all-prompts-daily": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution