time-attack · time-attack · Jul 14, 2026
diff --git a/diagram/SKILL.md b/diagram/SKILL.md
@@ -1,7 +1,7 @@
 ---
 name: diagram
 version: 1.0.0
-description: "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open (gstack)"
+description: "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG. (gstack)"
 allowed-tools:
   - Bash
   - Read
@@ -21,9 +21,8 @@ triggers:
 
 ## When to invoke this skill
 
-on excalidraw.com,
-and rendered SVG + PNG (clean mermaid style; the .excalidraw carries the
-hand-drawn aesthetic). Fully offline.
+The SVG/PNG use clean mermaid style; the
+.excalidraw carries the hand-drawn aesthetic. Fully offline.
 Use when asked to "make a diagram", "draw the architecture", "create a
 flowchart", "diagram this", or "visualize this flow".
 

diff --git a/diagram/SKILL.md.tmpl b/diagram/SKILL.md.tmpl
@@ -4,8 +4,8 @@ version: 1.0.0
 description: |
   Turn an English description (or mermaid source) into a diagram triplet:
   the source, an editable .excalidraw file you can open on excalidraw.com,
-  and rendered SVG + PNG (clean mermaid style; the .excalidraw carries the
-  hand-drawn aesthetic). Fully offline.
+  and rendered SVG + PNG. The SVG/PNG use clean mermaid style; the
+  .excalidraw carries the hand-drawn aesthetic. Fully offline.
   Use when asked to "make a diagram", "draw the architecture", "create a
   flowchart", "diagram this", or "visualize this flow". (gstack)
 allowed-tools:

diff --git a/gstack/llms.txt b/gstack/llms.txt
@@ -26,7 +26,7 @@ Conventions:
 - [/design-review](design-review/SKILL.md): Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them.
 - [/design-shotgun](design-shotgun/SKILL.md): Design shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate.
 - [/devex-review](devex-review/SKILL.md): Live developer experience audit.
-- [/diagram](diagram/SKILL.md): Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG (clean mermaid style; the .excalidraw carries the hand-drawn aesthetic).
+- [/diagram](diagram/SKILL.md): Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG.
 - [/document-generate](document-generate/SKILL.md): Generate missing documentation from scratch for a feature, module, or entire project.
 - [/document-release](document-release/SKILL.md): Post-ship documentation update.
 - [/freeze](freeze/SKILL.md): Restrict file edits to a specific directory for the session.

diff --git a/scripts/gen-skill-docs.ts b/scripts/gen-skill-docs.ts
@@ -322,7 +322,7 @@ export function splitCatalogDescription(description: string): CatalogParts {
   // the period to be followed by whitespace OR end-of-text.
   // First normalize to single-line for sentence detection, then back out.
   const collapsed = working.replace(/\s+/g, ' ').trim();
-  const sentenceMatch = collapsed.match(/^([^.!?]*[.!?])(?:\s|$)/);
+  const sentenceMatch = collapsed.match(/^((?:[^.!?]|[.!?](?!\s|$))*[.!?])(?:\s|$)/);
   // sentenceLead is the FULL first sentence (no truncation). We compute routing
   // from this position, then optionally truncate the displayed lead afterwards.
   // Truncating first then computing routing was the v1.45.0.0 bug — when the

diff --git a/scripts/proactive-suggestions.json b/scripts/proactive-suggestions.json
@@ -79,8 +79,8 @@
       "voice_line": "Voice triggers (speech-to-text aliases): \"dx audit\", \"test the developer experience\", \"try the onboarding\", \"developer experience test\"."
     },
     "diagram": {
-      "lead": "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open",
-      "routing": "on excalidraw.com,\nand rendered SVG + PNG (clean mermaid style; the .excalidraw carries the\nhand-drawn aesthetic). Fully offline.\nUse when asked to \"make a diagram\", \"draw the architecture\", \"create a\nflowchart\", \"diagram this\", or \"visualize this flow\".",
+      "lead": "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG.",
+      "routing": "The SVG/PNG use clean mermaid style; the\n.excalidraw carries the hand-drawn aesthetic. Fully offline.\nUse when asked to \"make a diagram\", \"draw the architecture\", \"create a\nflowchart\", \"diagram this\", or \"visualize this flow\".",
       "voice_line": null
     },
     "document-generate": {
@@ -264,8 +264,8 @@
       "voice_line": null
     },
     "sync-gbrain": {
-      "lead": "Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state",
-      "routing": "probing, native code-surface registration, capability checks,\nand a verdict block. Re-runnable, idempotent. Use when: \"sync gbrain\",\n\"refresh gbrain\", \"re-index this repo\", \"gbrain search isn't finding\nthings\".",
+      "lead": "Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md.",
+      "routing": "Wraps the gstack-gbrain-sync orchestrator with\nstate probing, native code-surface registration, capability checks,\nand a verdict block. Re-runnable, idempotent. Use when: \"sync gbrain\",\n\"refresh gbrain\", \"re-index this repo\", \"gbrain search isn't finding\nthings\".",
       "voice_line": null
     },
     "unfreeze": {

diff --git a/sync-gbrain/SKILL.md b/sync-gbrain/SKILL.md
@@ -2,7 +2,7 @@
 name: sync-gbrain
 preamble-tier: 2
 version: 1.0.0
-description: Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state (gstack)
+description: Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. (gstack)
 triggers:
   - sync gbrain
   - refresh gbrain
@@ -23,7 +23,8 @@ allowed-tools:
 
 ## When to invoke this skill
 
-probing, native code-surface registration, capability checks,
+Wraps the gstack-gbrain-sync orchestrator with
+state probing, native code-surface registration, capability checks,
 and a verdict block. Re-runnable, idempotent. Use when: "sync gbrain",
 "refresh gbrain", "re-index this repo", "gbrain search isn't finding
 things".

diff --git a/test/catalog-trim.test.ts b/test/catalog-trim.test.ts
@@ -95,31 +95,21 @@ describe('splitCatalogDescription', () => {
     expect(parts.routingProse).toBe('With routing prose afterward.');
   });
 
-  test('embedded-period descriptions: known limitation falls back to first-20-words', () => {
-    // KNOWN LIMITATION: the sentence regex `^([^.!?]*[.!?])(?:\\s|$)` stops
-    // at the FIRST `.`-then-non-whitespace because [^.!?]* is greedy and
-    // can't backtrack past a non-period char. For "DESIGN.md and v1.45.0.0
-    // in the lead. Use when..." the regex fails entirely and the lead falls
-    // back to the first 20 words (~the whole short input).
-    //
-    // The real-world impact is small: descriptions like "DESIGN.md" or "v1.45"
-    // appearing in the middle of the FIRST sentence are rare. When they do
-    // occur, the lead simply becomes the full description (no body section
-    // generated) — same as a description without a period. The trim CI gate
-    // still keeps the per-skill size budget honest.
-    //
-    // If this gap matters later, replace the regex with a sentence tokenizer
-    // (compromise.js / Intl.Segmenter) — until then we accept the fallback.
+  test('embedded periods do not end the lead sentence', () => {
     const desc =
       'Skill that mentions DESIGN.md and v1.45.0.0 in the lead. ' +
       'Use when asked to do something.';
     const parts = splitCatalogDescription(desc);
-    // Actual behavior: lead absorbs the whole input via the word-count fallback.
-    expect(parts.lead.length).toBeGreaterThan(0);
-    // routingProse may be empty when the fallback consumes everything.
-    // The test exists to detect REGRESSIONS (lead becoming oddly short like
-    // "Skill that mentions DESIGN.") not to assert ideal behavior.
-    expect(parts.lead).toContain('Skill that mentions');
+    expect(parts.lead).toBe('Skill that mentions DESIGN.md and v1.45.0.0 in the lead.');
+    expect(parts.routingProse).toBe('Use when asked to do something.');
+  });
+
+  test('URL periods do not end the lead sentence', () => {
+    const parts = splitCatalogDescription(
+      'Open https://example.com/docs and inspect it. Use when asked to check docs.',
+    );
+    expect(parts.lead).toBe('Open https://example.com/docs and inspect it.');
+    expect(parts.routingProse).toBe('Use when asked to check docs.');
   });
 
   test('description without a period uses first ~20 words as lead', () => {