upgrade-people-memory
Skill1 starsChanged 3 months agoMITView on GitHub
Upgrade an installed People Memory plugin, MCP package, PostgreSQL/Supabase schema, optional API, web UI, and bundled skills; inspect release notes, back up data, apply ordered migrations, refresh uvx or local installs, preserve config and credentials, restart agents, and verify reads and writes. Use when the user says upgrade, update, migrate, install the latest release, schema migration, refresh the plugin, or repair a version mismatch.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- enrich-peopleSkill
- import-contactsSkill
- maintain-people-memorySkill
- remember-peopleSkill
- setup-people-memorySkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 9 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Keep the database recoverable and configuration private.
- Very specific: line 12
Call graph_status and record counts.
- Distinctive: line 14
Read release notes from the current version through the target version.
- Very specific: line 19
Create a timestamped pg_dump in a private location.
- Distinctive: line 28
Update plugin skills and MCP config without overwriting the user's environment file.
- Distinctive: line 30
Start a new agent session so MCP and skill changes load.
- Very specific: line 34
Call graph_status and compare counts.
- Distinctive: line 35
Read a known synthetic or user-approved test record.
- Distinctive: line 36
Create, retrieve, update, and archive-delete a synthetic record.
- Distinctive: line 37
Verify login, search, edit, and graph rendering in the UI.
- Distinctive: line 38
Remove the synthetic record and archive.
- Distinctive: line 40
If a check fails, stop writes, preserve logs without contact data, and offer the tested restore path.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Upgrade People Memory
Keep the database recoverable and configuration private.
Preflight
- Call
graph_statusand record counts. - Identify the installed package, plugin, schema migration level, and UI version.
- Read release notes from the current version through the target version.
- Flag breaking changes, new connector permissions, or required user choices before mutation.
Back up
Create a timestamped pg_dump in a private location. Verify the file is non-empty and record the
restore command. Do not put the backup in Git or an agent artifact store.
Upgrade
- Pull or install the target release.
- Apply pending Supabase migrations in order. Never run
db resetagainst a linked production project. - Refresh the
uvxpackage cache or local virtual environment. - Update plugin skills and MCP config without overwriting the user's environment file.
- Rebuild or redeploy the static UI when its files changed.
- Start a new agent session so MCP and skill changes load.
Verify
- Call
graph_statusand compare counts. - Read a known synthetic or user-approved test record.
- Create, retrieve, update, and archive-delete a synthetic record.
- Verify login, search, edit, and graph rendering in the UI.
- Remove the synthetic record and archive.
If a check fails, stop writes, preserve logs without contact data, and offer the tested restore path. Finish with old/new versions, migrations applied, verification results, and any manual login still needed. Do not print secrets or database URLs.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

