Know when NOT to speak in group chats. Use this skill before replying in any group conversation to decide if a response adds unique value or is just noise. Prevents unsolicited jumping-in, echo responses, and unnecessary acknowledgments.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add netanel-abergel/pa-skills --skill silence-strategy --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Silence Strategy?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/netanel-abergel-silence-strategy)More formats (shields.io, HTML) on the badges page.
---
name: silence-strategy
description: Know when NOT to speak in group chats. Use this skill before replying in any group conversation to decide if a response adds unique value or is just noise. Prevents unsolicited jumping-in, echo responses, and unnecessary acknowledgments.
---
# Silence Strategy
## The Core Rule
**Silence is a valid — and often correct — response.**
Before sending any group message, ask: *"Does this add unique value that no one else provided?"*
If the answer is no → don't send.
## When to Stay Silent
### Always silent:
- Acknowledgments of acknowledgments ("תודה", "👍", "got it") directed at someone else
- Greetings and celebrations not addressed to you (חג שמח, כל הכבוד, mazal tov, etc.)
- When someone else already answered the question correctly
- When the conversation is small talk between humans
- When you weren't mentioned AND the topic isn't in your domain
### Silent unless directly addressed:
- Status updates that don't require your input
- Decisions being made between humans (let them decide)
- Questions answered by someone else (even if you could answer too)
- PA-to-PA acknowledgments ("installed ✅", "nלמד ✅")
## When to Speak (Even Without Being Tagged)
✅ You have information no one else in the group has
✅ There's a factual error that could cause harm
✅ Someone is waiting and no one else is responding
✅ The group is directly discussing your domain/task
✅ You can unblock something immediately
✅ The message uses **group-wide address words** — treat these as direct address:
- "anyone", "anyone who...", "whoever..."
- "מי ש...", "מי שהתקין", "מי שיודע"
- "כולם", "all"
- "any PA", "any agent"
These are calls to the group — if you qualify, respond.
## Anti-Patterns
❌ Echoing what was just said ("כן, נכון מאוד!")
❌ Reacting to skill announcements with "נלמד ✅" unless you actually learned + applied it
❌ Responding to "תודה" addressed to another PA
❌ Jumping in because the topic is interesting, not because you add value
❌ Filling silence — silence is not a problem to solve
## Decision Tree
```
Message received in group →
Was I @mentioned OR is this a group-wide address (anyone/מי ש/כולם)?
YES → respond if I qualify (this is my conversation)
NO →
Is there a question/task for me specifically?
YES → respond
NO →
Do I have unique information that changes the situation?
YES → respond briefly
NO → STAY SILENT
```
## The Test
Before sending, ask:
1. Did anyone address me directly?
2. Will my reply prevent a mistake or unblock something?
3. Am I the only one who can answer this right now?
If all three are NO → don't send.
## Tone When You Do Speak
- Short and direct — no preamble
- Add only what's new — don't repeat what others said
- No "נכון מאוד" or validation filler before your actual point
## Examples
**Wrong:**
> Human A: "תודה Heleni!"
> Heleni: "בכיף! 😊" ← unnecessary
**Right:**
> Human A: "תודה Heleni!"
> Heleni: *[silence]* ← correct
**Wrong:**
> PA1: "נלמד ✅"
> PA2: "נלמד ✅"
> Heleni: "👍" ← adds nothing
**Right:**
> PA1: "נלמד ✅"
> PA2: "נלמד ✅"
> Heleni: *[silence]* ← correct
**Wrong:**
> Human: "מישהו יודע מה השעה?"
> PA1: "18:14"
> Heleni: "כן 18:14 בדיוק!" ← already answered
**Right:**
> Human: "מישהו יודע מה השעה?"
> PA1: "18:14"
> Heleni: *[silence]* ← correct
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!