Finding Leading Words

Time: 10 minutes. Tangible win: a short list of leading-word candidates in your diagnose skill, each screened, with one picked for lesson 3.

Ian, lesson 1 said what a leading word is. Now the harder part: spotting where one belongs. Matt's guide gives you two hunting grounds, and then you need a screen so you do not swap in a word that does nothing. Your own diagnose skill is the test subject.

Primary source writing-for-agents (sections "Leading words" and "Pruning") — Matt Pocock. About 4 minutes.

Where to hunt

The guide names two patterns that are "begging to collapse into a single token" (source):

Also look at what is already there. In pstack's blast-radius, "the one fact" and the numbered "how sure are you" ladder are reused phrases that structure the whole skill. That is my reading of the file, not a claim by its authors.

Live example: your diagnose skill

Lines 16, 27 and 42 of ~/.kiro/skills/diagnose/SKILL.md say the same thing three ways:

16: Build a fast, deterministic, runnable pass/fail signal
27: If you have a fast, deterministic pass/fail signal, you will find the cause.
42: Iterate on the loop: faster? sharper signal? more deterministic?

That is the first pattern: one idea (a feedback loop good enough to debug against), restated three times. Matt's diagnosing-bugs collapses it to tight and red. Your skill also already uses a different leading word well: gate ("This is a gate, not a suggestion"). That one is working; leave it.

Screen each candidate

Finding a repeated phrase is not enough. Run each candidate replacement through these four questions. The first three come from the guide; the fourth is my addition and you should treat it as a heuristic.

QuestionFails whenSource
Is it an existing word the model already knows?You coined it, so you pay definition tokens for no priorsGuide
Does it beat the default?It is a no-op, like "be thorough" for an already thorough agentGuide
Does it stand for the idea you restated?It names a neighbour, not the triad you meant to retireGuide
Can you repeat it as a token, never redefining it?You must re-explain it each time it appearsMy heuristic

A candidate that passes all four is a hypothesis, not a win. The guide says there is no automated eval and to settle disputes by running the document. Lesson 3 is how to run it properly.

Negation is also a hunting ground

Any "don't", "never", or "avoid" in your skill names the thing you do not want. The guide says that makes the forbidden behaviour more available, so rewrite the line to the positive target where you can. A hard guardrail that you cannot phrase positively can stay, paired with the target.

Retrieval check

Which replacement recruits the fewest priors from the model's pretraining?

Right. A made-up word has no pretraining meaning, so you would have to define it. Red is an existing word with strong associations.

Not that one. Both words exist and carry meaning. The coined word is the one with no priors behind it.

Which is the best hunting target for a leading-word rewrite?

Yes. Restatement of one idea at several sites is exactly what a repeated single token retires.

A once-only step or a literal example has nothing to collapse. Look for the same idea spelled out repeatedly.

Practice

  1. Scan your skill for repeated phrases: grep -nE "fast|deterministic|sharp|tight|red\b" ~/.kiro/skills/diagnose/SKILL.md
  2. List up to three candidates: the phrase, how many sites, and your proposed single word.
  3. Screen each with the four questions. Drop any that fail.
  4. Pick one survivor to test in lesson 3. For your diagnose skill, the obvious candidate is tight / red.
  5. Send me your list. I will write your second learning record.
Ask me: "Is gate in my diagnose skill earning its place, and what would the no-op test say?" or paste a second skill and ask me to hunt it with you.