Hydrate empty or template-only PMM memory files using existing session context.
npx skills add https://github.com/NominexHQ/pmm-plugin --skill pmm-hydrate
Please help me install this Agent Skill. Skill: pmm-hydrate Source: https://github.com/NominexHQ/pmm-plugin/tree/main/local/pmm-hydrate Command: npx skills add https://github.com/NominexHQ/pmm-plugin --skill pmm-hydrate
PMM memory directories can accumulate empty or template-only files when new memory types are added or re-activated, leaving Claude sessions without the historical context needed for reliable recall and reasoning. pmm-hydrate infers content from every populated memory file so new entries start with meaningful context instead of shallow templates, preventing context rot and ensuring every maintain cycle builds on existing history.
[system:hydrate] attribution, append or replace files per rules, and return per-file summaries before the host runs git add/commit.Request pmm-hydrate to populate the target memory file or use --all to hydrate every active template-only file.
High-intent search queries and answers about installing and using this skill.
To populate empty memory files, the system reads template definitions and all populated memory stores to synthesize context-aware entries, appending new content with [system:hydrate] attribution. This ensures new or reactivated files start with meaningful historical context instead of shallow templates.
Yes, you can hydrate multiple template-only memory files using the batch mode. By specifying the --all flag, the system processes every active template-only file in the memory directory, synthesizing content from existing populated files while automatically excluding config.md and secrets.md.
You can force re-hydration of existing memory files by using the --force flag. This bypasses the intelligent detection gate that normally skips populated files, allowing the foreground agent to overwrite or append content based on the template reference definitions and existing session context.
No, the memory hydration process does not run git commands. The foreground agents only write new entries with [system:hydrate] attribution and return per-file summaries, leaving all git add and commit operations to the main host context for version control.
Empty memory files after reactivation occur because templates lack historical context. The hydration system addresses this by reading all populated memory stores to synthesize meaningful content for the reactivated files, ensuring every maintain cycle builds on existing history.
NominexHQAdjust Poor Man's Memory preferences and commit config.md changes via git.
nq-rdlAutomate git add and commit after Spec Kit commands via git-config.yml.
jfrometaPersist task plans, findings, and progress in markdown files.
kimon1230Manually compress Claude session progress entries with a custom Python compressor module.