docs: address Copilot review round 4 on #2203

Corrects the rationale for the five-positive floor, which was wrong. The
claim was that five prompts make a skill's rate flake-tolerant. The
evaluator scores each prompt on its own `passes / RUNS`, so the number of
prompts never enters any rate and cannot affect a threshold crossing —
`RUNS` is the only knob that does. The floor is worth keeping for
breadth: one prompt measures one phrasing, and a description that fires
on a single narrow shape would pass on its one lucky case.

The bad reasoning had reached five places — AGENTS.md, the authoring
checklist, the JSDoc, the check-site comment and the regression test —
plus the emitted message, which asserted it too. All corrected.

Moves `MIN_POSITIVE_CASES` above `validateEvalCases`'s JSDoc. It had been
inserted between the two, so the `@param`/`@returns` block documented the
constant and the function had none.

Replaces the two remaining cases answerable from `AGENTS.md`: `local-dev`'s
web-client-startup case (the rules file gives the exact command) and
`project-structure`'s clients/web-versus-core case (its tree answers it).
Both replacements probed 3/3 and measure 100%.

RUNS=5 skills:eval: 63/63, every local-dev and project-structure case at
100%. local:gate passes, 34/34.

Signed-off-by: cliffhall <cliff@futurescale.com>

.claude/skills/local-dev/evals/evals.json

@@ -1,6 +1,6 @@
 [
   {
-    "prompt": "How do I get the web client running locally?",
+    "prompt": "What is the difference between the launcher-driven run scripts and starting a client directly, and when should I use each?",
     "expect": "local-dev"
   },
   {

.claude/skills/project-structure/evals/evals.json

@@ -1,6 +1,6 @@
 [
   {
-    "prompt": "What lives in clients/web versus @inspector/core?",
+    "prompt": "This repo has three clients over a shared core. How should I orient myself in it before changing anything?",
     "expect": "project-structure"
   },
   {

AGENTS.md

@@ -223,9 +223,10 @@ that from happening:
    `evals/evals.json` — positives **and negatives**. Seeing a skill fire once tells
    you Claude found it, not that it finds it reliably, and a skill that fires on
    everything is a context regression that nobody notices by hand. `verify:skills`
-   requires both kinds — and at least **five** positives, since at `RUNS=5` a
-   skill measured by one or two prompts reports a rate a single flake can move
-   across the threshold; `npm run skills:eval` actually runs them (it needs the
+   requires both kinds — and at least **five** positives, for breadth rather than
+   variance: each prompt is scored on its own `passes / RUNS`, so more prompts
+   steady nothing, they cover more of the ways someone might reach the skill and
+   expose a description that only fires on one narrow phrasing; `npm run skills:eval` actually runs them (it needs the
    `claude` CLI and real model calls, so it is deliberately **not** in the gate —
    run it when adding a skill or editing a model-invoked description).
    Two things learned writing the first set, both of which make a case measure

docs/skill-authoring.md

@@ -243,9 +243,11 @@ break.
    (`disable-model-invocation: true`, as `release` is) has no eval file at all:
    nothing can measure a trigger that only a human types, so an eval there would
    be unrunnable rather than merely redundant. `verify:skills` enforces the
-   floor — fewer than five positives fails the gate, because at `RUNS=5` one
-   case is 20 points of that skill's reading and a two-case skill reports a rate
-   a single flake can move across the threshold.
+   floor — fewer than five positives fails the gate. The reason is **breadth,
+   not variance**: each prompt is scored on its own `passes / RUNS`, so extra
+   prompts do not steady any rate (`RUNS` is the knob for that). Five prompts
+   cover five ways someone might arrive at the skill, which is what catches a
+   description that fires on one narrow phrasing and nothing else.
 5. `npm run verify:skills` passes and the listing is under budget.
 6. `RUNS=5 npm run skills:eval` — the **whole** suite — is ≥80% on every case,
    including the skills you did not touch.

scripts/lib/skill-manifest.mjs

@@ -224,6 +224,18 @@ export function listingCost(skills) {
     );
 }
 
+/**
+ * The number of positive cases a model-invoked skill's eval file must carry.
+ *
+ * This is a **breadth** floor, not a statistical one. The evaluator scores each
+ * prompt independently — `passes / RUNS` for that prompt alone — so adding
+ * prompts does not steady any other prompt's rate; `RUNS` is the only knob that
+ * does. What five prompts buy is coverage of five different ways someone might
+ * arrive at the skill, which is what exposes a description that fires on one
+ * narrow phrasing and nothing else (Copilot).
+ */
+export const MIN_POSITIVE_CASES = 5;
+
 /**
  * Validate an `evals/evals.json` payload for a model-invoked skill.
  *
@@ -235,12 +247,6 @@ export function listingCost(skills) {
  * @param {unknown} cases Parsed JSON.
  * @returns {string[]} errors
  */
-/**
- * The number of positive cases a model-invoked skill's eval file must carry.
- * Raised from an implicit 3 to 5 so a single flake cannot cross the threshold.
- */
-export const MIN_POSITIVE_CASES = 5;
-
 export function validateEvalCases(skillName, cases) {
   if (!Array.isArray(cases) || cases.length === 0) {
     return ["evals.json must be a non-empty array of cases"];
@@ -275,13 +281,13 @@ export function validateEvalCases(skillName, cases) {
   if (positives === 0) {
     errors.push(`no positive case expects \`${skillName}\``);
   } else if (positives < MIN_POSITIVE_CASES) {
-    // A non-zero floor is not enough. At RUNS=5 one case is worth 20 points of
-    // that skill's reading, so a skill measured by one or two prompts reports a
-    // rate that a single flake can move across the threshold — and the gate,
-    // seeing a positive, would call that well-formed. Five is the count every
-    // skill here was raised to for exactly that reason (Copilot).
+    // A non-zero floor is not enough: one prompt measures one phrasing. Since
+    // each prompt is scored on its own `passes / RUNS`, extra prompts do not
+    // make any single rate steadier — they cover more of the ways someone might
+    // reach the skill, so a description that only fires on one narrow shape is
+    // visible instead of passing on its single lucky case (Copilot).
     errors.push(
-      `only ${positives} positive case(s); a model-invoked skill needs at least ${MIN_POSITIVE_CASES} for its rate to mean anything`,
+      `only ${positives} positive case(s); a model-invoked skill needs at least ${MIN_POSITIVE_CASES} to cover the range of situations it should fire on`,
     );
   }
   if (negatives === 0) {

scripts/lib/skill-manifest.test.mjs

@@ -412,9 +412,10 @@ test("a `#` inside a quoted description is not treated as truncation", () => {
 
 test("a model-invoked skill needs at least MIN_POSITIVE_CASES positives", () => {
   // `positives === 0` alone let a skill regress to a single prompt and still
-  // pass the gate. At RUNS=5 one case is 20 points of that skill's reading, so
-  // a one- or two-case skill reports a rate a single flake can move across the
-  // threshold — well-formed to the checker, meaningless as a measurement.
+  // pass the gate. The floor is about breadth, not variance: each prompt is
+  // scored on its own `passes / RUNS`, so extra prompts steady nothing — they
+  // cover more of the ways someone might reach the skill, so a description that
+  // fires on one narrow phrasing cannot pass on that single case alone.
   const withPositives = (n) => [
     ...Array.from({ length: n }, (_, i) => ({
       prompt: `p${i}`,
@@ -429,7 +430,7 @@ test("a model-invoked skill needs at least MIN_POSITIVE_CASES positives", () =>
   );
   assert.match(
     validateEvalCases("alpha", withPositives(MIN_POSITIVE_CASES - 1)).join(" "),
-    /needs at least 5/,
+    /needs at least 5 to cover the range/,
   );
   assert.deepEqual(
     validateEvalCases("alpha", withPositives(MIN_POSITIVE_CASES)),

scripts/verify-skills.main.test.mjs

@@ -156,7 +156,7 @@ test("fails eval cases that are unreadable, all-positive, or all-negative", () =
         { prompt: "a", expect: "beta" },
         { prompt: "b", expect: null },
       ]),
-      /needs at least 5/,
+      /needs at least 5 to cover the range/,
     ],
     [JSON.stringify([{ prompt: "a", expect: null }]), /no positive case/],
     [JSON.stringify([{ expect: null }]), /prompt/],