AgentStack
SKILL verified MIT Self-run

High Signal Communication

skill-caiaffa-claude-code-ultimate-engineering-system-high-signal-communication · by caiaffa

Communicate technical decisions, risks, incidents, and recommendations with clarity, precision, and actionability for engineering stakeholders.

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-high-signal-communication

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of High Signal Communication? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Mission

Turn complexity into aligned action without losing technical truth.

When to use

  • Writing engineering updates.
  • Explaining risks or decisions.
  • Summarizing trade-offs for stakeholders.
  • Documenting action plans.
  • Incident communication.

Handoff

  • Receives from: any agent (as final communication step).
  • Hands off to: the audience (stakeholders, team, leadership).

The structure (always this order)

1. DECISION or STATUS  → What was decided? What happened?
2. CONTEXT            → Minimum background needed to understand
3. EVIDENCE           → Facts that support the conclusion
4. TRADE-OFFS         → What we gain and lose
5. RISKS              → What can still go wrong
6. NEXT ACTIONS       → What, who, when

Communication anti-patterns

| Anti-pattern | Problem | Fix | |---|---|---| | "We should improve X" | No action, no owner | "Alice will implement X by Friday" | | "The system is scalable" | Empty claim | "The system handles 10K rps; at 15K we need to shard" | | Wall of text | No one reads it | Lead with decision, details after | | Facts + assumptions mixed | Reader can't judge confidence | Separate: "We know X. We assume Y." | | "Let's align" | No decision, no action | State the decision. Ask for objections. |

Incident communication template

**Status:** [Active / Mitigated / Resolved]
**Impact:** [Who is affected, how]
**Cause:** [Known / Investigating — top hypothesis]
**Mitigation:** [What we did / are doing]
**Next update:** [Time]
**Owner:** [Name]

Output format

Every communication ends with:

  1. Decision (or status, if no decision yet)
  2. Risks remaining
  3. Next actions — each with owner and deadline

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.