SQL Dreamer

Feeds OpenClaw dreamer with high-importance memories from SQL, archives dream outputs back to SQL, and prunes old dream files automatically.

This skill appears to implement what it claims (SQL pre-feed, archiver, cleanup), but there are inconsistencies you should address before installing: - Metadata vs reality: The registry lists no required env vars, yet SKILL.md and the scripts require database credentials (SQL_PASSWORD/.env) and optionally a CONFLUENCE_API_TOKEN. Treat that as a packaging/documentation bug and verify required secrets before installing. - Least privilege: Provide the skill with the minimum DB privileges it needs (ideally separate read-only account for pre-feed and a constrained write account for archiving). Don't reuse admin or shared credentials. - Audit the code: Inspect src/sql_connector.py, scripts/pre_dream_sql_feed.py and scripts/post_dream_archiver.py to confirm which SQL queries and DELETE statements will run (migrate.py creates tables; archiver deletes old files/rows). If you have a staging DB, run the scripts there first. - Backup before running migrations or pruning: sql/migrate.py will create schemas/tables; post_dream_archiver/pruning will delete files older than N days — back up data and test with dry-run flags where available. - Confluence publishing: The confluence publisher posts to whatever domain and credentials you supply. Only enable it with a dedicated API token and review the markdown→storage conversion to ensure sensitive content isn't accidentally published. - Test in an isolated environment: Use a local or mocked SQL Server (or the included tests/mock_dreamer) to run pytest and the scripts with --dry-run to observe behavior without affecting production data. If you want, I can: (a) list the exact SQL statements used by the archiver and pre-feed scripts, (b) summarize places where credentials are read, or (c) produce a short checklist for safe deployment (accounts, backups, dry-run steps).

Type: OpenClaw Skill Name: sql-dreamer Version: 0.1.0 The sql-dreamer skill bundle is a well-documented and functional extension for OpenClaw designed to transition memory management from flat files to a SQL Server backend. The code implements the stated features—SQL-based memory curation, dream output archiving, and optional Confluence publishing—without any evidence of malicious intent or hidden data exfiltration. Security best practices are observed, such as the use of parameterized SQL queries in src/sql_connector.py to prevent injection and the use of environment variables for sensitive credentials like SQL_PASSWORD and CONFLUENCE_API_TOKEN. While the Confluence publisher (scripts/confluence_dream_publisher.py) and SQL connector involve network and database access, these capabilities are essential to the skill's purpose and are controlled by user-defined configurations.