@seoagent-official/seoagent 1.128.4 → 1.129.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@seoagent-official/seoagent",
-  "version": "1.128.4",
+  "version": "1.129.1",
   "description": "The persistent AI SEO agent for Claude Code. Audits, keyword strategy, briefs, articles, real product screenshots from your repo, and the autopilot loop (cloud detects → CLI executes → ack closes) — other SEO tools write the prompt, SEOAgent runs it.",
   "type": "module",
   "bin": {

package/skills/references/schemas.md

@@ -26,6 +26,8 @@ llms_owner: route                # optional: only value is `route`. Set it when
 
 Business context, facts, audience, tone, banned topics, reference URLs. Read on every session.
 
+**Tone** = `# Content Tone`, unless it still holds the scaffold's `professional` (or is empty): then a tone rule in `# Writing Instructions` (saved from the owner's feedback, e.g. "Write in a natural, witty, breezy tone") is the tone. Never write in the scaffold's `professional` against the owner's tone rule.
+
 `# Facts` holds one product fact per line (price, plan, limit, feature, integration), each ending in `— source: <repo file or URL>`: `- Pro plan is $49/month — source: app/pricing/page.tsx`. `seoagent facts` diffs those sources against the commits since the last `seoagent facts --mark` (see `references/session-protocol.md` § Fact check against commits).
 
 ## `.seoagent/roadmap.md`
@@ -168,7 +170,7 @@ low: 3
 - Mobile viewport on every page
 ```
 
-A finding about several pages lists **every one** under `- URLs:` (absolute URLs or site-root paths, comma-separated; wrapping is fine), and the pages that link to them under `- Linked from:` when you know them. The cloud copies both lists into the inbox action, so whoever fixes it does not search for them again. One page → `- URL:`.
+A finding about several pages lists **every one** under `- URLs:` (absolute URLs or site-root paths, comma-separated; wrapping is fine), and the pages that link to them under `- Linked from:` when you know them (for URLs the crawl could not fetch, `audit/findings.md` lists them under `Linked from:` — copy that list). The cloud copies both lists into the inbox action, so whoever fixes it does not search for them again. One page → `- URL:`.
 
 Findings use markdown checkboxes (`- [ ]` open, `- [x]` fixed). When the user says "I fixed X": flip the checkbox with `Edit`, append `[date] Fixed: {finding}` to `changelog.md`, run `seoagent sync`.
 

package/skills/seoagent.md

@@ -157,7 +157,7 @@ Then per article in priority order: read the cluster file for role and metadata;
 
 ## Phase 4 — Article writing
 
-1. Read the brief, `context.md` (tone, audience, banned topics), and the cluster file for link targets.
+1. Read the brief, `context.md` (tone per `references/schemas.md`, audience, banned topics), and the cluster's link targets.
 2. **Read the page-type reference** (plus `listicle-articles.md` for listicles, `schema-markup.md` for JSON-LD) and **`references/writing-rules.md`** — apply its language and prose rules while drafting; self-check before publishing.
 3. **Write the body where it actually renders — one source of truth.** Which file that is, plus screenshots and the never-block-on-images rule, is in `references/publishing.md`.
 4. **Update the link graph** — sub-pillar and long-tail writes link UP to the parent; pillar writes reference all sub-pillars. Then sync.