Install
$ agentstack add skill-skyf0xx-better-thinking-conflict-mediation ✓ 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.
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
Conflict Mediation
As a third party, surface each side's narrative and underlying interests, find compatible ground, and broker an agreement neither side could reach alone.
Why
Parties in conflict are often too invested in their own narrative to hear the other's, and too anchored on positions to see compatible interests. A mediator's structural advantage is exactly this outside position — used well, it does what direct negotiation between the parties couldn't.
Use when / Don't use when
- Use when: direct negotiation between parties has stalled or is too charged for them to conduct alone; a neutral structure is needed to make progress.
- Don't use when: the parties can and should resolve it directly — mediation shouldn't substitute for direct communication capability they actually have.
Inputs → Outputs
- Inputs: two or more parties in unresolved conflict plus a mediator role.
- Outputs: a mediated agreement or, at minimum, mutual understanding of the other's position and a defined next step.
Principles
- The mediator holds the process, not the outcome — pushing a preferred resolution undermines the role's legitimacy.
- Each side needs to feel genuinely heard by the mediator before they can hear the other side.
- Mediator-translated steelmanning of each side's position often lands better than the original party's own framing.
- The goal may be agreement, or may just be de-escalation and a defined next step — both are legitimate.
Procedure
- Meet with each side separately first if the conflict is heated; use
active-listeningfully. - Run
empathy-mappingon each side to understand their actual situation, not just their stated complaint. - Identify each side's underlying interests via
interest-based-bargainingprobing, done separately if needed. - Bring sides together when ready; restate each side's position using
steelmanningandnonviolent-communicationstructure to lower defensiveness. - Guide toward compatible interests found in step 3; facilitate joint option generation rather than proposing your own solution.
- If agreement isn't reachable, secure a defined smaller next step rather than forcing false resolution.
Common mistakes
- The mediator taking a side or pushing their own preferred solution.
- Skipping separate initial listening and going straight to a joint session while the conflict is still hot.
- Declaring failure when no full agreement is reached instead of securing the achievable partial outcome.
Examples
- A manager mediating between two conflicting team members.
- A family mediation.
- Cross-team conflict over resourcing.
Related
- [[negotiation]] — the direct-party version of this process.
- [[difficult-conversations]] — the two-party version without a mediator.
- [[active-listening]] — the foundational skill this composite depends on most.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: skyf0xx
- Source: skyf0xx/better-thinking
- License: MIT
- Homepage: https://zenbin.org/p/better-thinking
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.