Does /speckit-specify consistently produce ~13–20 FRs regardless of spec complexity?

[qurore]

I've been using Spec Kit with a Claude Code (Opus 4.7) skill, and I've noticed a consistent pattern I wanted to check against others' experience.
Regardless of the actual complexity of the spec — amount of code change, number of files touched, or test complexity — the spec.md generated by /speckit-specify almost always lands somewhere around 13–20 functional requirements, unless I explicitly specify otherwise. It seems oddly insensitive to the underlying scope of the feature.
Is this something others are seeing too?
My concern is that for relatively simple, small feature work, this tends to over-stack FRs. The spec ends up carrying more requirements than the feature actually warrants, and I get the sense it's hurting the quality of the resulting implementation — the model spreads effort across requirements that didn't really need to exist, rather than doing a clean, focused job on the few that matter.
Curious whether this is a known characteristic, and if anyone has found a good way to get the FR count to scale more naturally with the real complexity of the change.

[mnriem]

The specify command has no guidance on how many FRs to generate — the model fills that vacuum with its own default. You can override this with a local preset without changing core files.

Create a preset from the scaffold (cp -r presets/scaffold my-preset), add a prepend command override for speckit.specify in preset.yml:

provides:
  commands:
    - type: "command"
      name: "speckit.specify"
      file: "commands/speckit.specify.md"
      strategy: "prepend"

Then in commands/speckit.specify.md:

**FR Sizing**: Scale functional requirements to actual feature complexity. A simple single-flow change may need only 3–5 FRs. Prefer fewer precise requirements over many thin ones.

Install with specify preset add --dev ./my-preset and see if it changes the output on your model. Findings would be useful data for whether this belongs in the core command.