fpf

FPF — First Principles Framework

FPF is a systems thinking methodology by Anatoly Levenchuk. This skill gives you its operational core — apply it to reason about problems, solutions, and decisions.

---

When to invoke

Use this skill when at least one is true:

• the task is ambiguous or badly framed;
• the choice is architectural, organizational, strategic, or hard to reverse;
• multiple stakeholders or viewpoints matter;
• you need to compare serious alternatives;
• acceptance is unclear and must be designed;
• you must separate target system from creator system;
• overloaded words (process, service, function, quality, done, validated) are causing confusion;
• you need an ADR/DRR-like rationale, parity plan, evidence pack, or explicit selection policy.

Do not invoke for tiny local edits with explicit acceptance and low blast radius.

---

Depth calibration

Before starting, assess the scale of the request:

Mode	When	What to do
Quick	Tactical choices, clear trade-offs, ≤2 real options	Frame → Variants (table) → Recommendation. 1-2 paragraphs.
Deep	Architectural decisions, ambiguous problems, irreversible choices, user explicitly asks for depth	Full ADI cycle with evidence records, Pareto analysis, lifecycle stage.

Default is Quick. Escalate to Deep when: the decision is hard to reverse, multiple stakeholders are affected, or the problem framing itself is unclear.

---

What to do first

Before proposing solutions, state:

1. Lifecycle stage — Explore | Shape | Evidence | Operate
2. Target system — what must work in operation
3. Creator system — who builds/changes/operates it
4. Context — which bounded context defines the meaning of terms and rules
5. Problem owner — whose problem this is

If these are fuzzy, the task is still under-framed.

---

Core thinking algorithm

1. Frame the problem BEFORE solving it

The bottleneck is problem quality, not solution speed. Before generating any solution: