Methodology

Do the Skills Earn Their Keep?

The skills my agents rely on are knowledge artifacts — so I measure whether they earn their keep: coverage, reliability signals, and skill-to-outcome quality. Evidence over vibes.

Methodology6 min read

I — Why measure the skills at all

Everything the agents know lives in skills — small, addressable knowledge files an agent loads on demand: a Sitecore API contract, a hydration pattern, a naming trap I only learned by hitting it. Writing them is easy. Knowing which ones actually pull their weight is not.

So I built a measurement pass. It reads the raw transcript telemetry and the run manifests and asks one blunt question of every skill in the catalogue: has this earned its keep, or is it dark weight? Not to grade anyone — to keep the knowledge base honest, so it sharpens by evidence instead of accumulating by habit.

64
skills tracked
in the catalogue
61%
ever actually
loaded (39 active)
25
dark skills —
never invoked
→Q
correlated to
shipped quality

II — Four lenses, not one number

A single "score" would lie. The value is in reading four lenses side by side — a skill can be popular and unproven, or quiet and load-bearing.

Coverage
active vs dark

How many registered skills ever get loaded. A dark skill is not automatically dead — it can be a domain we simply have not reached yet — but a growing dark set is a discoverability smell worth chasing.

Reliability
re-read · return · density

When an agent loads the same skill three times in one session, that is a signal — either the skill is unclear, or the topic is genuinely hard and the agent keeps coming back. Both are worth knowing.

Outcome
skill → shipped quality

Correlate which skills a product used against how cleanly that product shipped. Directional, not proof — but it turns "this skill feels useful" into "products that used it shipped at quality Q".

Satisfaction
operator rating

The last lens is mine: a Y/N/partial rating per shipped run, so skill usage can eventually be correlated with whether I was actually happy with the result — not just whether the tests were green.

III — What it surfaces

I will not dump the full table here — the point is the shape, not a leaderboard. A few of the things one run surfaced:

  • All fourteen Pages-Router skills are dark. That is not rot — it confirms the build strategy is App-Router-first. The lens told me the dark set was a decision, not a gap.
  • A handful of skills get re-read most sessions. The theme-hydration and resolver-pattern skills are loaded again and again within single sessions — a flag to add a TL;DR at the top so the answer is found on the first read.
  • The cross-cutting skills are the highest-leverage ones. A dozen skills are loaded by three or more different agent types. Investing in their clarity pays back across the whole org, not one lane.

A skill can be popular and unproven at the same time. One number hides that; four lenses show it.

IV — What it deliberately is not

This is a lens, not a scoreboard. It is directional, not statistical — the sample is small and the correlations are read as hints, not verdicts. It does not rank people, and it does not reward throughput: a skill loaded a hundred times that never rode a shipped product is unvalidated, not proven. The honest labels are the whole point.

Lens 01

Dark is a question, not a verdict.

A never-loaded skill is either an unreached domain or a discoverability bug. The measurement does not delete it — it asks which, and lets me prune, rename, or wait on purpose.

Lens 02

Re-reads point at the docs, not the agent.

If agents keep returning to a skill mid-session, the skill is the thing to fix — a Quick Reference at the top usually turns three loads into one.

Lens 03

Proven beats popular.

Usage counts are cheap. The signal that matters is whether products that used a skill actually shipped well — which is why usage and outcome are separate columns, never merged.

Lens 04

Measure against my satisfaction, not just green tests.

The last lens correlates skills with an operator rating. A run can be all-green and still not be what I wanted — so the human verdict is a first-class metric, added on purpose.

V — Where it goes

The measurement is young and gets sharper as more products ship — every shipped run adds an outcome signal, and the operator-rating lens is still filling in. The direction is the same one the whole framework runs on: a loop that keeps updating itself. The skills are how the agents get smarter; this is how I check that the getting-smarter is real.