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.

This skill does what it says — it archives entire prompts/responses to a daily markdown file and can re-ingest them to restore context. Before installing: (1) review the four script files to confirm they do not transmit data off-host or run unexpected commands; (2) be aware that all conversation text (including any secrets) will be written to memory/remember-all-prompts-daily.md and possibly persisted in backups — secure that path or change storage behavior; (3) verify that the environment functions the skill expects (sessions_history(), session_status, clawdbot, HEARTBEAT.md) exist or adapt the scripts; (4) if you want manual control, consider setting disable-model-invocation or requiring explicit user triggers so the model cannot auto-run exports; (5) confirm daily rotation and retention policy meet your privacy/compliance needs.

Type: OpenClaw Skill Name: remember-all-prompts-daily Version: 1.0.1 The skill is designed to archive and restore conversation history, which requires interacting with the OpenClaw environment. It uses `subprocess` to call `clawdbot` CLI commands (e.g., `session-status`) and execute local Python scripts. It writes conversation history to `~/.clawd/memory/remember-all-prompts-daily.md` and modifies `~/.clawd/HEARTBEAT.md` for integration. It also suggests setting up a cron job via `clawdbot cron add` for periodic checks. All these actions are directly aligned with the stated purpose of preserving conversation continuity and do not show evidence of malicious intent such as data exfiltration, unauthorized remote execution, or stealthy persistence beyond the skill's stated function.