diff --git a/.claude/skills/testing/SKILL.md b/.claude/skills/testing/SKILL.md
index 0afcbea0..dbbb4438 100644
--- a/.claude/skills/testing/SKILL.md
+++ b/.claude/skills/testing/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: testing
-description: Testing procedures for this repo — which npm command runs which suite (web unit, web integration, Storybook, cli, tui, launcher, scripts), the test tiers from unit through smoke and pack:verify, where a new test file goes (side-by-side vs src/test/ vs __tests__/), diagnosing the per-file 90% coverage gate, and the renderWithMantine / renderWithMantineTransitions rules for React and Mantine tests. Use for any question about running, placing, or fixing a test here.
+description: Run, place and fix tests in this repo. Use when choosing which npm command runs a given suite (web unit, web integration, Storybook, cli, tui, launcher, scripts); when deciding where a new test file belongs — beside its source, under src/test/, or in a client's __tests__/; when a per-file coverage check fails or a v8 ignore is in question; when asking which test tier spawns the built binary rather than importing it; or when rendering, mounting or asserting on Mantine components and their transitions in a test.
 disable-model-invocation: false
 ---
 
diff --git a/AGENTS.md b/AGENTS.md
index f1ba56a1..a733ee4b 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -187,8 +187,13 @@ that from happening:
    measured 100% and every negative case stayed clean. So the ceiling is
    attention, not characters — we were at 2.8k of a 4k budget throughout. Adding
    a skill therefore has a cost paid by the *existing* ones, which only
-   `skills:eval` can see. **Re-run the full eval after any flip**, not just the
-   new skill's own cases.
+   `skills:eval` can see. **Re-run the full eval after any flip _or description
+   edit_**, not just the changed skill's own cases.
+   The lever that works is the description's *shape*. Leading with the actions
+   and then enumerating concrete situations ("Use when … ; when … ; when …")
+   beats a noun-phrase list of contents: it took `pre-push-gate` from 3/5 to 5/5
+   and `testing`'s three cases from 25/50/25% to 100% each (n=4), displacing
+   nothing else.
    ⚠️ **`paths` is not a free win.** It looks like the deterministic option, and
    it does gate loading to matching files — but measured against the `testing`
    skill's own eval cases, adding it roughly **halved** the rate at which the same