Side project: I developed constraint-first prompting in my own work and conversations first, then froze the 4-D flow and a 6-part anatomy into a skill; AI drafts inside rails I set.
- Agent Skills
- Prompting
Case study
Prompt Architect
01 · Context
Prompts that felt sharp, then fell apart.
I kept writing prompts that felt sharp in the moment and fell apart the next week. The failure was not the model — it was me. I had no repeatable way to fix role, constraints, and output shape before I asked for words.
I developed Prompt Architect to resolve this once and for all by applying constraint-first prompting in my own work and my own conversations first. I drew on a wide range of AI-related material online — structured guidelines, documentation, and community threads about getting real work out of tools. I kept what survived contact with my own use and dropped the rest. I distilled what remained into one cohesive, practical approach that makes sense when you run it, not when you admire it. Only then did I freeze it into a skill — the 6-part anatomy and 4-D flow as the fence, execution underneath.
The question I answered before writing a line of SKILL.md:
Lock the 6-part anatomy and the 4-D order first. Let AI draft inside those rails, never redefine them.
What must stay fixed so AI can run fast without rewriting the rules every session?
02 · How it was built
Decisions that kept AI inside rails I set.
Structure before prose
I locked the structure first.
I locked the 6 anatomy headings and the 4-D order into SKILL.md — after distilling many threads into one approach that had already survived my own use. Only after that did I let the model draft explanations and examples under each heading. The rule was clear: structure before prose.
What I refused to outsource
Judgment calls stayed mine.
I decided what counts as a stop condition, what belongs in Output versus Task, and which failure modes matter for this skill. Those calls shape how the model behaves when a user is vague — I did not delegate them to a first draft.
Delivery, not direction
What the model did well.
Once the rails were set, AI filled sections, tightened wording, and surfaced edge cases in tables I had already defined. Execution — focused on delivery, not direction.
Cut, don't admire
Trimming drift.
I cut anything that sounded like generic prompt advice or bloated the skill into a blog post. The skill mirrors a design language: opinionated, bounded, reusable.
03 · In practice
The decision that made the skill survive the next session.
Systems thinking
Structure locked before AI touched the content.
Needed a repeatable prompt framework — not another collection of tips.
Letting AI draft the structure leads to generic prompt advice that reads well but doesn't survive real use.
The 6-part anatomy and 4-D flow are product decisions, not copy decisions. They define behaviour, not words.
Locked the headings and section order into SKILL.md first. Only then let the model draft explanations and examples under each fixed heading.
Structure before prose. The skill mirrors a design language: opinionated, bounded, reusable. No drift between sessions.
04 · Implementation
Where AI entered, and where judgment stayed mine.
Design
Where AI entered
- —After headings and section order were fixed, AI drafted body copy, examples, and platform notes under each locked heading.
- —Iteration stayed inside the same file shape — no surprise sections, no alternate frameworks sneaking in.
- —When text drifted toward motivational fluff, I deleted it. The skill is operational, not inspirational.
Where judgment stayed mine
- —Choosing the Agent Skill format and file layout — what ships as the contract.
- —Defining BASIC versus DETAIL modes and what each may skip — that is product behaviour, not copy.
- —Naming failure modes in the anatomy table — what "weak" looks like per section.
05 · Results & Metrics
A portable skill that survives the next session.
2
Distribution formats — Skill for workflows, standalone paste-block for any AI tool.
1
Portable SKILL.md artifact with locked framework headings.
6
Anatomy headings fixed before any AI drafting.
4-D
Flow locked as the operating order.
06 · Trade-offs & Learnings
What constraint-first prompting taught.
— Proof that skills mirror boundaries, not templates: the anatomy and flow are product decisions, not copy decisions.
— Constraint-first prompting only works once you've run it on your own work — the skill freezes what already survived, it doesn't invent it.
AI drafts inside rails I set.
Structure before prose — skills mirror boundaries, not templates.