Handle a neighbor conflict — noise, boundaries, parking, shared costs, pets — with a measured approach that de-escalates first and keeps a paper trail if it has to go formal. Use when asked to deal with a neighbor dispute, my neighbor is [too loud / over the boundary / blocking me], how do I talk to my neighbor about, or write a letter to my neighbor. Produces a read on the situation, a calm first conversation or friendly note, a firmer written follow-up if that fails, the documentation habit for escalation, and the right next step (mediation / landlord / HOA / council) — steering away from making it worse.
“My upstairs neighbor plays loud music every night — how do I raise it without a fight?”“Neighbor's fence is over my boundary. Write me a measured letter.”“They keep parking across my driveway. What do I do first?”“Shared hedge, and they won't split the cost — how should I approach it?”“I've asked nicely twice about the barking. What's the next step?”
What to give it
▸The issue — noise, boundary/fence, parking, shared costs, pets, mess, or other; and how often
▸History — first time raising it, or ongoing? Any prior conversations?
▸The relationship — friendly, neutral, or already tense
▸Your setup — own or rent; is there a landlord, HOA, or building management involved?
▸Your goal — just make it stop, preserve the relationship, or both
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓Opens with the lowest-heat approach that could plausibly work
✓Language targets the behavior and impact, not the person
✓Gives the neighbor a good-faith chance before escalating
✓Includes a quiet documentation habit from the start
✓Escalation is proportionate and matched to the issue
✓Tuned to own/rent and any landlord/HOA involvement
⚠️ What it refuses to do
**Opening with a formal/legal letter** over a first-time annoyance.
**Attacking character** instead of naming the behavior.
**Threats or retaliation** — escalates and can put you in the wrong.
**No documentation** — leaving nothing for mediation or authorities.
**Jumping straight to the authorities** for something a conversation could fix.
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp