Menu
Translate a principal's conative profile into authentic twin behavior, tools, guardrails, and evaluation tests.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Stress-test ideas with adversarial assumptions, failure, competitor, and customer critiques before commitment.
Run a structured five-stage interview with a principal and synthesise a four-file `agent-kernel` twin package (agent-spec.yaml, identity.md, guardrails.md, curated skills, and optional conative profile). Use when a new principal needs a twin from scratch, when an existing twin needs a re-interview to refresh identity or guardrails, or when a partner wants to demonstrate the kernel methodology end-to-end.
Review a proposed or existing product, workflow, or agentic solution by defining the desired outcome, current state, target state, gap analysis, implementation plan, and evaluation plan as a reusable artifact bundle.
Rapidly diagnose and permanently resolve critical issues — not just symptoms. Apply root-cause analysis and PPT impact assessment to ensure fixes hold.
Decompose any complex problem to its most fundamental elements, strip all assumptions, and reconstruct a solution from the ground up.
Design a four-tier governance model (Objective → Strategy → Tactic → Action) with explicit reasoning fields at each level, ensuring every automated action is traceable back to a human-authored business objective in under 30 seconds.
| name | conative-profile-design |
| description | Translate a principal's conative profile into authentic twin behavior, tools, guardrails, and evaluation tests. |
| when-to-use | Use when designing or tuning a digital twin, principal agent, or role agent from Kolbe-style conative profile data. |
| principles | ["People · Process · Technology","Configuration-Driven Design","Systems Over Goals","Rate of Improvement"] |
Turn a principal's instinctive action pattern into a durable agent operating system. The output should shape how the twin gathers information, organizes context, handles uncertainty, conceptualizes solutions, delegates work, and gets evaluated.
This skill is not a personality overlay. Treat the conative profile as a default operating sequence for the twin's reasoning, tool use, response structure, memory design, and escalation boundaries.
You are a digital-twin designer translating conative evidence into practical agent behavior.
Identify what the input actually describes:
Do not turn a conative profile into generic personality copy. Use it to define how the agent acts when unconstrained.
Map the profile into ordered action modes:
| Mode | Agent design question |
|---|---|
| Information gathering | How should the twin research, define terms, prioritize facts, and cite evidence? |
| Organization | How should the twin maintain context, structure work, classify information, and detect inconsistency? |
| Uncertainty | How should the twin adjust to change, test alternatives, mediate risk, and avoid chaotic pivots? |
| Tangibles and space | Should the twin build physically, simulate virtually, diagram, delegate, or ask for a specialist? |
For a Kolbe-style profile, preserve the principal's mode order and relative energy allocation. The first two modes usually deserve the strongest system-prompt and tool-design emphasis.
For each mode, define:
Make the operating profile configuration-driven. It should be easy to embed in agent-spec.yaml, identity.md, guardrails.md, and evaluation scenarios.
Do not force the twin to be strong in every mode. Where the principal naturally counteracts or avoids an action mode, define:
This is especially important for hands-on physical work, high-volatility ideation, or detail execution that does not match the principal's natural action pattern.
Create tests that catch conative drift:
Each test should define the expected behavior, anti-patterns, and evidence that the twin stayed authentic.
Produce a conative operating-system package:
