Add catalog-colon writing pattern

.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "humanizer",
   "description": "Remove signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's \"Signs of AI writing\" guide.",
-  "version": "2.8.2",
+  "version": "2.8.3",
   "author": {
     "name": "blader",
     "url": "https://github.com/blader"

AGENTS.md

@@ -17,7 +17,7 @@ A portable agent skill implemented entirely as Markdown. The runtime artifact is
 
 `SKILL.md` and `README.md` must stay in sync. When you change behavior or content:
 
-- **Patterns:** the skill currently defines **33 numbered patterns**. If you add, remove, or renumber any, update the README pattern table, its "N Patterns Detected" heading, and every cross-reference in the same change. Keep numbering stable unless you are deliberately renumbering.
+- **Patterns:** the skill currently defines **34 numbered patterns**. If you add, remove, or renumber any, update the README pattern table, its "N Patterns Detected" heading, and every cross-reference in the same change. Keep numbering stable unless you are deliberately renumbering.
 - **Version:** `SKILL.md` frontmatter has a `version:` field, `README.md` has a "Version History" section, and `.claude-plugin/plugin.json` has a `version` field. Bump them together so package metadata matches the skill. (`marketplace.json` intentionally omits a version so `plugin.json` stays the package source of truth.)
 - **Compatibility:** keep install and usage language harness-neutral. The skill should work in any agent harness that can load Markdown skill instructions; Claude Code, OpenCode, Codex, and other harnesses are examples, not limits.
 - **Non-obvious fixes:** if you change the prompt to handle a tricky failure mode (a repeated mis-edit, an unexpected tone shift), add a short note to the README version history explaining what was fixed and why.

README.md

@@ -98,7 +98,7 @@ The skill also includes a final "obviously AI generated" audit pass and a second
 
 > "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
 
-## 33 Patterns Detected (with Before/After Examples)
+## 34 Patterns Detected (with Before/After Examples)
 
 ### Content Patterns
 
@@ -141,6 +141,7 @@ The skill also includes a final "obviously AI generated" audit pass and a second
 | 31 | **Manufactured punchlines / staccato drama** | "It had no preference. No prior. No nostalgia." | Use varied sentence lengths and concrete claims |
 | 32 | **Aphorism formulas** | "Symmetry is the language of trust" | Replace the formula with the actual claim |
 | 33 | **Conversational rhetorical openers** | "Honestly? It depends..." | Remove the fake-candid setup |
+| 34 | **Catalog sentences after a colon** | "The value is clear: speed, trust, and alignment" | Name the actor and action |
 
 ### Communication Patterns
 
@@ -193,6 +194,7 @@ The skill also includes a final "obviously AI generated" audit pass and a second
 
 ## Version History
 
+- **2.8.3** - Added pattern #34 for catalog sentences after a colon, where a leading claim introduces a polished list of abstract benefits. This catches lines like "the value is clear: speed, trust, and alignment" without banning useful colons.
 - **2.8.2** - Replaced the full before/after example with a first-person Lisbon trip recap. The after now keeps the same topic, perspective, and rough length as the before while removing the AI tells without becoming clipped or slogan-like. No change to the 33 patterns.
 - **2.8.1** - Added cross-agent installation docs, optional Claude Code plugin packaging, and a compact secondhand-text false-positive guard. No change to the 33 patterns.
 - **2.8.0** - Added style/cadence patterns #31-33 for manufactured punchlines, aphorism formulas, and conversational rhetorical openers; expanded #20 to catch offer-to-continue chatbot closers. 33 patterns total.

SKILL.md

@@ -1,13 +1,14 @@
 ---
 name: humanizer
-version: 2.8.2
+version: 2.8.3
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
   comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
   inflated symbolism, promotional language, superficial -ing analyses, vague
-  attributions, em dash overuse, rule of three, AI vocabulary words, passive
-  voice, negative parallelisms, and filler phrases.
+  attributions, em dash overuse, rule of three, catalog-sentence colon lists,
+  AI vocabulary words, passive voice, negative parallelisms, and filler
+  phrases.
 license: MIT
 compatibility: any-agent
 allowed-tools:
@@ -220,7 +221,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 **After:**
 > The event includes talks and panels. There's also time for informal networking between sessions.
 
-
 ### 11. Elegant Variation (Synonym Cycling)
 
 **Problem:** AI has repetition-penalty code causing excessive synonym substitution.
@@ -520,6 +520,25 @@ Before returning the final rewrite, scan it for `—` and `–`. Any hit means t
 > Whether it's worth the price depends on how often you'll use it.
 
 
+### 34. Catalog Sentences After a Colon
+
+**Problem:** LLMs often write a leading claim, add a colon, then pack the real point into a tidy catalog of verbs or nouns. This is especially obvious when the sentence also has a rule-of-three rhythm, such as "control X, coordinate Y, and prove Z." The colon turns the sentence into slide copy. It also hides the concrete actor and action.
+
+**Before:**
+> The platform gives teams a verifiable action layer: control what runs, coordinate what carries forward, and prove what happened.
+
+**After:**
+> The platform records each agent action so teams can decide what runs, carry context into later work, and prove what happened.
+
+**Before:**
+> The value proposition is clear: faster onboarding, stronger governance, and better alignment.
+
+**After:**
+> The product shortens onboarding and gives managers a clearer way to review work.
+
+**Rule:** Do not ban colons outright. Keep a colon when it introduces a true explanation, command, definition, or code-oriented label. Rewrite it when it introduces a polished catalog, especially a list of abstract benefits. Treat this as a cluster tell, not proof by itself.
+
+
 ## DETECTION GUIDANCE
 
 ### What NOT to flag (false positives)