personal-crm
Skill1 starsChanged 3 months agoMITView on GitHub
Design a personal CRM: contact metadata, interaction logs, follow-up reminders and relationship strength. Use when maintaining professional relationships, staying in touch, or contact logs.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- aya-taleb/productivity-skillstheir own version, first seen Nov 1, 2026
- megandmartin/agent-skills-repotheir own version, first seen Jul 24, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- megandmartin/agent-skills-repo★ 3same name
- aya-taleb/productivity-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- 3d-printingSkill
- fitness-nutrition-plannerSkill
- fitness-nutritionSkill
- habitsSkill
- habit-tracker-designerSkill
- interview-prepSkill
- job-searchSkill
- knowledge-management-architectSkill
- know-meSkill
- linkedin-profile-optimizerSkill
- linkedin-profileSkill
- note-systemSkill
- periodic-reviewSkill
- periodic-review-systemSkill
- personal-contextSkill
- personal-financeSkill
- productivity-auditSkill
- relationship-crm-builderSkill
- resume-optimizerSkill
- resumeSkill
- second-brain-architectSkill
- travel-plannerSkill
- travel-planningSkill
- voice-profileSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Check-in Cadence: Every 2–4 weeks.
- Distinctive: line 24
Check-in Cadence: Every 60–90 days.
- Distinctive: line 26
Check-in Cadence: Every 6 months or situational.
≈ “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
personal-crm
Core Philosophy
Professional networking feels dirty and transactional when it is treated as an opportunistic harvest—reaching out only when you need a job, an introduction, or an angel investment. A personal CRM is a long-term relationship infrastructure built on genuine curiosity, mutual respect, and value-first connection. By tracking interaction context, personal details, and periodic check-in rhythms, you nurture authentic professional friendships with zero awkwardness.
4-Step Personal CRM Architecture
Step 1: Dunbar's Circles & Tiered Segmentation
- The Concentric Circle Model:
- Tier 1: Core Circle (5–15 People): Close mentors, inner circle confidants, primary co-founders.
- Check-in Cadence: Every 2–4 weeks.
- Tier 2: Key Network (50 People): Active collaborators, trusted industry peers, frequent sounding boards.
- Check-in Cadence: Every 60–90 days.
- Tier 3: Broad Ecosystem (100–150 People): Former colleagues, investors, domain experts, acquaintance builders.
- Check-in Cadence: Every 6 months or situational.
- Tier 1: Core Circle (5–15 People): Close mentors, inner circle confidants, primary co-founders.
Step 2: Contact Metadata & Information Architecture
- Essential Dossier Fields:
- Basic: Name, Current Company, Role, Location, Timezone.
- Context: How you met (event, mutual intro, year).
- Personal Anchors: Partner/spouse name, children, hobbies, sports teams, favorite books, non-tech passions.
- Professional Priorities: What they are currently building, hiring for, or struggling with.
- Interaction Log: Date, format (coffee, call, DM), and concise bullet points of what was discussed.
- Next Touchpoint: Scheduled date and prompt topic.
Step 3: The "Give-First" Low-Friction Touchpoint Playbook
- The 3 Legitimate Reasons to Reach Out:
- The Relevant Artifact: Sending a high-signal article, paper, or tool directly relevant to a problem they mentioned:
- "Saw this benchmark on ClickHouse query optimization and immediately thought of the scaling challenge you mentioned in June. Hope the sprint is going well!"
- The Unsolicited Celebration: Congratulating them on a shipped product, funding milestone, or talk with specific commentary (not generic "Congrats!").
- The High-Value Mutual Intro: Connecting two people in your CRM who share complementary needs, with double-opt-in consent.
- The Relevant Artifact: Sending a high-signal article, paper, or tool directly relevant to a problem they mentioned:
- The "No Reply Needed" Pressure Release:
- End low-friction check-ins with: "No need to reply—just wanted to share this and hope you're crushing it!" This removes cognitive burden and builds immense goodwill.
Step 4: Maintenance Hygiene & Tooling
- Tooling Simplicity:
- Store in a plain Markdown folder, Notion database, or lightweight SQLite file. Avoid heavyweight corporate sales CRMs with automated marketing drip sequences.
- Weekly 15-Minute Relationship Sweep:
- Schedule 15 minutes during the Friday weekly review to review contacts due for check-ins and send 2–3 authentic messages.
Deliverable Format: Personal CRM Dossier Template (CONTACTS.md)
# Personal CRM & Relationship Dossier
## 1. Circle Cadence Overview
- **Tier 1 (Bi-weekly)**: [Names]
- **Tier 2 (Quarterly)**: [Names]
- **Tier 3 (Bi-annually)**: [Names]
## 2. Contact Record Template
### [Full Name] — Tier [1 / 2 / 3]
- **Role & Company**: [e.g. VP Engineering @ PlatformCorp]
- **Location**: [City, Timezone]
- **How We Met**: [e.g. Spoke at RustConf 2024; mutual friend of Dave]
- **Personal Anchors**: [Marathon runner, 2 dogs (Golden Retrievers), likes specialty coffee]
- **Current Focus**: [Migrating infra to bare metal; hiring Staff SRE]
- **Cadence**: [60 days] | **Last Contact**: [YYYY-MM-DD] | **Next Due**: [YYYY-MM-DD]
#### Interaction History
- **2026-06-12 (Coffee in SF)**:
- Discussed their move away from AWS EKS. Recommended checking out Talos Linux.
- Promised to send our internal benchmark on container boot times.
- **2026-01-15 (X DM)**:
- Congratulated on their Series A announcement.
#### Action Item / Prompt for Next Touch
- Send article on bare-metal Kubernetes networking when published.Worked Example: High-Leverage Peer Check-In
- Contact: Senior Staff Engineer at target partner company.
- Metadata Context: Mentioned in March that they were struggling to hire a senior compiler engineer.
- Action: In May, spotted an exceptional compiler dev posting on Twitter/X that their startup shut down. Sent a quick intro with double opt-in.
- Result: Contact hired the engineer; relationship deepened into a strong technical partnership without ever making an awkward "sales" pitch.
Verification Checklist
- Network is partitioned into realistic Dunbar tiers ($\le 15$ Tier 1, $\le 50$ Tier 2, $\le 150$ Tier 3).
- Every contact entry includes personal anchors and how you met.
- Outreach messages are value-first (sharing an artifact, congratulating, or intro) with zero immediate asks.
- "No reply needed" clause is used on casual check-ins to eliminate recipient guilt.
- CRM is stored in an open, portable format (Markdown / CSV / Notion) without spam automation.
Anti-Patterns
- The Desperation Ping: Disappearing for 3 years and suddenly messaging: "Hey, can you refer me for a job at your company?"
- Automated Drip Emails: Treating personal relationships like automated marketing prospects with canned birthday emails.
- Hoarding Contacts: Storing 2,000 LinkedIn connections in a CRM whom you have zero intention of ever helping.
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.

