fix: relabel release 2.9.0 -> 2.8.1 and document versioning convention (#415)

Repo x.y.z semantics: x = repo-wide changes, y = new skills, z = updates
to existing skills. The iMessage ad format is an update to ad-creative,
so it ships as 2.8.1, not 2.9.0. Convention now documented in AGENTS.md.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, and growth",
-    "version": "2.9.0",
+    "version": "2.8.1",
     "repository": "https://github.com/coreyhaines31/marketingskills"
   },
   "plugins": [

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "marketing-skills",
   "description": "Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth",
-  "version": "2.9.0",
+  "version": "2.8.1",
   "author": {
     "name": "Corey Haines"
   },

AGENTS.md

@@ -45,6 +45,22 @@ node tools/clis/<name>.js           # Show usage (no args = help)
 node tools/clis/<name>.js <cmd> --dry-run  # Preview request without sending
 ```
 
+## Versioning
+
+Two version layers, with different rules:
+
+**Repo release version** — `.claude-plugin/plugin.json` `version`, `.claude-plugin/marketplace.json` `metadata.version`, and the `VERSIONS.md` changelog headings all share one x.y.z number:
+
+- **x** — repo-wide changes (restructures, spec changes, breaking changes)
+- **y** — new skill(s) added
+- **z** — updates to existing skills
+
+Do not bump y for content added to an existing skill, no matter how substantial — that's a z release (e.g. a new reference file in ad-creative is 2.8.0 → 2.8.1, not 2.9.0).
+
+**Per-skill version** — `metadata.version` in each SKILL.md, mirrored in the `VERSIONS.md` table. Bump on ANY shipped change to that skill: the update check compares `VERSIONS.md` against users' local skill metadata, so an unbumped change is invisible to installed users. Minor for new capability or description triggers, patch for fixes and clarifications.
+
+Bump the repo release version in the same PR that ships the change (2.7.0 and 2.8.0 shipped without touching plugin.json/marketplace.json and needed a catch-up later).
+
 ## Agent Skills Specification
 
 Skills follow the [Agent Skills spec](https://agentskills.io/specification.md).

VERSIONS.md

@@ -54,7 +54,7 @@ Current versions of all skills. Agents can compare against local versions to che
 
 ## Recent Changes
 
-### 2.9.0 (2026-07-08)
+### 2.8.1 (2026-07-08)
 
 - **ad-creative** (2.1.0 → 2.2.0): added the **iMessage chat-reveal video ad format**. New `references/imessage-video-ads.md` — an original distillation of the format popularized by Shiv Sakhuja / Gooseworks (their public `create-imessage-video-ad` skill; the repo carries no open-source license, so content was re-expressed with credit rather than copied): a 9:16 video where a scripted iMessage thread unfolds bubble-by-bubble — screenshot hook → friend reacts → "what app is that?" → brand + promo-code reveal → static end card. Covers when to use it and when not (considered B2B, nothing screenshot-able, regulated-industry compliance), a compliance/grounding section tying dramatized conversations to the skill's Grounded Inputs rules (facts in the thread must be real; never frame the thread as a real testimonial), the six concept angles (result-as-screenshot, setup flex, cancellation moment, feature-as-punchline, friend-asks-friend inverse, receipt-as-hook), ad anatomy with script + pacing rules (8–14 bubbles, texting voice, brand appears once and late, rhythm not metronome, link-underlined promo code), three production routes (off-the-shelf Gooseworks skill; code-based HTML mockup + one continuous Playwright recording + ffmpeg stitch; Remotion for templated scale), the craft rules that sell the illusion (the recognizable send/receive SFX — CC0 recordings on BigSoundBank, with a trade-dress legal-review note; silent typing indicators; composer-typed text must equal sent text; static end card with the real logo SVG; native 1080×1920 recording; HTML-mimic real app UIs for hook screenshots instead of AI-generating them), a ship checklist, and an iteration order (hook attachment first). SKILL.md wires the reference into Generating Ad Visuals and adds 'iMessage ad,' 'chat reveal ad,' 'text message ad,' and 'fake DM ad' description triggers. Closes #411.