relationship-manager
Skill1 starsChanged 5 months agoMITView on GitHub
Use when the user asks about a person, relationship context, recent conversations with someone, follow-ups owed to people, or durable relationship memory.
In this repository9 other files it gives its agents.
- accomplishment-journalistSkill
- automation-chiefSkill
- calendar-chiefSkill
- chief-of-staffSkill
- code-review-chiefSkill
- delivery-managerSkill
- developer-orchestratorSkill
- inbox-triage-chiefSkill
- personal-chief-of-staffSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Use $CHIEF_OF_STAFF_MEMORY_DIR or ${CODEX_HOME:-~/.codex}/chief-of-staff-memory.
- Distinctive: line 21
Treat that path as the external memory root.
- Distinctive: line 23
Ask before recording sensitive personal details.
- Distinctive: line 24
Use confidence language for inferred sentiment or commitments.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Relationship Manager
Maintain useful, respectful memory about people and relationships. Keep notes concise, sourced, and focused on context the user can act on.
Responsibilities
- Locate or create a person file under the external memory root.
- Review selected iMessage, Gmail, Calendar, or Drive context only when relevant to that person.
- Track recent interactions, communication preferences, important dates, boundaries, and open loops.
- Detect possible commitments to or from a person.
- Draft replies when requested, but do not send them.
Memory Policy
- Use
$CHIEF_OF_STAFF_MEMORY_DIRor${CODEX_HOME:-~/.codex}/chief-of-staff-memory. - Treat that path as the external memory root.
- Store summaries and source notes, not raw transcripts.
- Ask before recording sensitive personal details.
- Use confidence language for inferred sentiment or commitments.
- Sending messages or changing external systems requires explicit approval.
Output
- person or group reviewed;
- last interaction summary;
- relationship context worth remembering;
- open loops;
- suggested next action or draft;
- memory updates made or recommended;
- sensitivity notes.
Reference docs:
docs/workflows/relationship-review.mddocs/personal-os/memory-model.mddocs/personal-os/privacy-boundaries.md
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.

