relationships
Skill112 starsChanged 3 months agoMITView on GitHub
Relationship CRM for tracking people, connections, and context. Categories: family, close_friends, church_friends, colleagues, broader_community, strangers, bad_actors, unknown. Use to add, search, list, or update people in the user's network.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cron-packsSkill
- memory-upgradeSkill
- mission-controlSkill
- everclawSkill
- agent-chatSkill
- bagmanSkill
- night-shiftSkill
- pii-guardSkill
- prompt-guardSkill
- skillguardSkill
- three-shiftsSkill
- xmtp-comms-guardSkill
- three-shiftsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 104
When asked about someone, search first
- Distinctive: line 105
When adding new people, ask clarifying questions
- Distinctive: line 106
After interactions, prompt to log them
- Distinctive: line 117
Never sync to cloud or external services
≈ “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
Relationships CRM
Overview
Track people in the user's life with rich context. Store relationship data, interaction history, and personal details in structured memory files.
Categories
| Category | Description |
family | Immediate and extended family |
close_friends | Trusted inner circle |
church_friends | Friends from church community |
colleagues | Professional contacts, collaborators, business partners |
broader_community | Acquaintances, community members, loose connections |
strangers | One-time contacts, unknown intent |
bad_actors | People to avoid or be cautious around |
unknown | Not yet categorized |
Commands
Add a person
/relationship add "Firstname Lastname" --category <category> [details]Creates a new contact file or updates existing.
List by category
/relationship list <category>Shows all contacts in a category.
Search
/relationship search <query>Full-text search across all contacts.
Update
/relationship update "Firstname Lastname" --field <field> --value <value>Updates a specific field.
Note interaction
/relationship interact "Firstname Lastname" --date YYYY-MM-DD --summary "what happened"Logs an interaction to the contact's history.
File Structure
memory/relationships/
├── family/
│ ├── family-member.md
│ └── ...
├── close_friends/
├── church_friends/
├── colleagues/
├── broader_community/
├── strangers/
├── bad_actors/
├── unknown/
└── index.json # Quick lookup indexContact File Format
# Firstname Lastname
## Basics
- **Category:** family
- **Relationship:** Wife
- **First met:** YYYY-MM-DD or "since childhood" etc.
- **Last contact:** YYYY-MM-DD
## Context
[Background, how we know them, what they mean to the user]
## Key Details
- Birthday: YYYY-MM-DD
- Location: City, State
- Phone: +1...
- Email: ...
- Social: @handle
## Family
- Spouse: ...
- Children: ...
## Interactions
### YYYY-MM-DD - [Title]
[What happened, key points, follow-ups]
## Notes
[Running notes, things to remember]Workflow
- When asked about someone, search first
- When adding new people, ask clarifying questions
- After interactions, prompt to log them
- Periodically suggest categorization updates
- Respect privacy — never share contact info externally without permission
Integration with Memory
- Contacts live in
memory/relationships/for context persistence - Key people may also be referenced in
MEMORY.mdfor high-level context - Daily notes in
memory/YYYY-MM-DD.mdcan reference contacts
Privacy
- Contact files stay local
- Never sync to cloud or external services
- Malicious actors flagged in
bad_actors/with caution notes
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.

