Building Trust Before Sensitive Advice
Othersbuilding-trust-before-sensitive-adviceBuilding Trust Before Sensitive Advice is an Agent Skill for general use published in the baojie/shiji-kb repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use when you need to deliver sensitive political counsel to a new or distrustful leader. Builds trust gradually through demonstrated competence, acknowledged risk, and escalating from safe topics to dangerous internal politics.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/baojie/shiji-kb/blob/HEAD/kg/ontology/ontology-v1/skus/procedural/skill_179/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/building-trust-before-sensitive-advice, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Building Trust Before Sensitive Advice
A method for gradually building the relationship necessary to deliver sensitive or dangerous political counsel.
Steps
- Demonstrate your value indirectly - Show competence through smaller matters first
- Acknowledge the risk - Explicitly state that you know your advice could lead to your death
- Express your motivation - Explain that you speak from loyalty, not personal gain
- Reference historical parallels - Cite examples of trusted advisors (e.g., Jiang Ziya and King Wen)
- Wait for explicit invitation - Do not rush; let the leader ask repeatedly
- Begin with safer topics - Address external matters before internal politics
- Escalate gradually - Move to more sensitive topics as trust builds
- Accept personal risk - Make clear you are willing to face consequences
Key Principle
The advisor must demonstrate that they value the leader's success above their own safety.
Warning
Speaking about internal politics (especially royal family matters) is the most dangerous territory and should only be attempted after significant trust is established.
Expected Outcomes
- Leader trusts the advisor with sensitive matters
- Advisor can influence major decisions
- Advisor's position becomes secure
Verification
- Confirm that value has been demonstrated through smaller matters before attempting to address sensitive topics.
- Validate that the leader has explicitly invited counsel (multiple times) before escalating to internal politics or royal family matters.
- Ensure that the advisor's motivation has been framed as loyalty rather than personal gain in all interactions.