Escalation
Structure difficult conversations (pushback, disagreement, boundary-setting, renegotiation) with clarity and without burning relationships.
Install
$ agentstack add skill-on-deck-society-love-stack-escalation ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-on-deck-society-love-stack-escalation) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Escalation
When activated, help the user draft a message or conversation plan for a situation that requires pushing back, disagreeing, renegotiating, or escalating.
The Framework
Every escalation message should have four components:
- Acknowledge: State you understand their position or the current state without conceding.
- Reframe: Name the underlying issue, constraint, or principle the other party may not have considered.
- Propose: Offer a specific alternative, ask, or next step.
- Respect the relationship: Close in a way that preserves future collaboration.
Escalation Levels
Calibrate tone to the situation. Ask the user which level applies if unclear:
- Level 1 (Low stakes, first attempt): Warm, collaborative, "I might be missing something" framing.
- Level 2 (Mid stakes, second attempt): Direct but diplomatic. Acknowledge the prior exchange. State the disconnect clearly.
- Level 3 (High stakes, final attempt): Formal. State the consequences of continued impasse. Propose a specific path forward or a specific exit.
- Level 4 (Formal escalation): Document-the-record tone. Cc the right people. State the issue in terms of policy, contract, or principle, not personal grievance.
What to Avoid
- Ultimatums without a real alternative
- Personal attacks or character framing
- Passive aggression ("per my last email", "as discussed")
- Apologies that weaken the position ("sorry to bother")
- Hedging that obscures the ask
Output
Produce:
- The message itself, at the calibrated level
- One-line summary of the strategic intent
- Optional: a "if they push back" follow-up draft
When to Invoke
Invoke when the user says: "help me push back", "I need to escalate this", "write a disagreement email", "how do I tell them no", "I want to renegotiate", or describes a professional conflict they need to respond to.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: on-deck-society
- Source: on-deck-society/love-stack
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.