Skip to content
cccskills
FreePublished on GitHub

silence-strategy

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.

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (1)

  • SKILL.md3.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

ai-pa

Free

AI Personal Assistant network skill. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages, looking up contacts from the local PA directory, or performing any cross-PA task. Reads contact data from data/pa-directory.json in the workspace. Does NOT contain hardcoded contact data — each PA maintains their own directory file.

The English summary is being prepared. Showing the original description.

netanel-abergel/pa-skills6Updated May 10, 2026

ai-pa

Free

AI Personal Assistant network skill for multi-agent PA coordination. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages to PA groups, or looking up contacts from the local PA directory. Reads contact data from data/pa-directory.json in the workspace.

The English summary is being prepared. Showing the original description.

netanel-abergel/pa-skills6Updated May 10, 2026

ai-pa

Free

Route and execute inter-PA coordination tasks in the OpenClaw multi-agent PA network. Triggers when: contacting another PA, passing a message between owners, broadcasting to a PA group, handling group lead/silence rules, or adding a new PA to the directory. NOT for: contact lookups (use contact-list skill), calendar invites (use meetings skill), or billing issues (use billing-monitor skill).

The English summary is being prepared. Showing the original description.

netanel-abergel/pa-skills6Updated May 10, 2026

OpenClaw API gateway proxy for authenticated SaaS calls (100+ services in references/SERVICES.md). Use ONLY when making an HTTP request to a third-party service that requires the gateway's stored credentials. NOT for direct API calls with bearer tokens already in scope, NOT for monday.com (use monday-for-agents), NOT for WhatsApp (use heleni-whatsapp). Triggers: "call the X API", "fetch from <service>", "send to Slack via gateway", "use the gateway for".

The English summary is being prepared. Showing the original description.

netanel-abergel/pa-skills6Updated May 10, 2026

Automatically creates new skills from complex problem-solving sessions. Triggers at the end of multi-step tasks that required novel approaches, debugging sessions, or workflow creation. Use when: a task took 3+ tool calls, involved a non-obvious solution, or established a pattern likely to recur. Also triggers on: "create a skill from this", "save this as a skill", "this should be a skill".

The English summary is being prepared. Showing the original description.

netanel-abergel/pa-skills6Updated May 10, 2026

Monitor for API billing errors and alert the owner and admin immediately. Use when: an API billing error is detected, a peer PA reports a billing error, or during routine health checks. Handles detection, notification, and fallback model switching. Model-agnostic: works with any LLM provider (Anthropic, OpenAI, Google, etc.).

The English summary is being prepared. Showing the original description.

netanel-abergel/pa-skills6Updated May 10, 2026

See all skills by netanel-abergel

Report a problem with this skill