feat(linkedin-studio): de-niche rest-sweep — vary KTG-beat examples across surfaces (B-S2b) [skip-docs]

The last de-niche slice: recast the 10 sites where the vendor/sector beat
(Microsoft|Azure|Copilot|public sector) sat as the PRIVILEGED/default example,
varying each to a concrete cross-domain example instead of sterilizing
(plugin-is-domain-general — domain comes from user config, never hardcoded).

Recast (10): url-processing-templates (news worked-example Copilot->Figma),
opportunity-generation (3 headline examples + About block -> varied/ops persona),
profile (3 "good example" headlines/impact -> healthcare/e-commerce/support),
first-comment-strategy (drop "Microsoft" from research-paper example),
poll-strategy-guide (Copilot option -> generic AI assistants),
engagement-frameworks (1 of 3 direct-address audiences -> RevOps/SaaS),
setup (audience e.g. -> two varied examples), post (invocation e.g. -> SaaS pricing),
network-builder (tagline example -> ops/manufacturing),
video-scripter (2 filename slugs -> neutral topics).

Kept as false positives (would sterilize): content-angles.md (Public Sector is
1 of 6 balanced industry tables + Industry-Agnostic section), outreach.md
(Microsoft Build/Ignite/Azure UG = 3 of ~20 varied real conferences),
linkedin-growth-playbook (biographical fact in a real case study), the
Gemini/Tavily/Perplexity MCP tool-name examples, and the algorithm-signals
"Gemini provenance" SSOT citation. AI-as-topic kept (not a niche token; the
de-AI/AI-slop mechanic is the plugin's legit subject).

Gate scripts/test-runner.sh 87/0/0 (no lint touches these files yet; §17-guard
extension to content-planner is the deferred next step). 10 files, 26/26.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RBMKqPSVbvSZHtQ4heM1UY

commands/post.md

@@ -43,7 +43,7 @@ Check for existing assets:
 
 ## Step 1: Understand the Input
 
-If the user already provided a clear topic with the command invocation (e.g., `/linkedin:post about AI governance in public sector`), skip asking and proceed directly. Only ask if the input is missing or genuinely vague.
+If the user already provided a clear topic with the command invocation (e.g., `/linkedin:post about pricing strategy for B2B SaaS`), skip asking and proceed directly. Only ask if the input is missing or genuinely vague.
 
 Identify the type of raw material:
 

commands/profile.md

@@ -56,7 +56,7 @@ search. Optimize for both.
 in every search result and connection suggestion, and renders under your name
 across the site — so it does the most SEO work per character. Lead with the plain
 words people actually search (the role, the domain, the audience), not a clever
-tagline. "AI Advisor · public-sector AI governance · Microsoft Copilot" is more
+tagline. "Data Engineer · healthcare analytics · HIPAA-compliant pipelines" is more
 findable than "Turning chaos into clarity ✨".
 
 **Per-section keyword targets** (place the terms a searcher would type, in the
@@ -95,7 +95,7 @@ Guide the user through each section using AskUserQuestion for interactive feedba
 - [ ] No jargon or vague titles
 
 **Strong example:**
-"Helping public sector leaders implement AI that actually works | AI Advisor @ [Company]"
+"Helping e-commerce teams turn returns data into retention | Retention Strategist @ [Company]"
 
 **Weak example:**
 "Digital Transformation Expert | Thought Leader | Speaker"
@@ -134,7 +134,7 @@ Guide the user through each section using AskUserQuestion for interactive feedba
 **Transform each role with impact statements, not task lists.**
 
 **Bad:** "Responsible for AI initiatives"
-**Good:** "Deployed first Copilot Studio agent handling 40% of internal inquiries"
+**Good:** "Cut customer-support response time 40% by automating tier-1 triage"
 
 **Ask the user:** Describe your current role's key achievements with numbers/impact.
 

commands/setup.md

@@ -314,7 +314,7 @@ Guide through each section of the profile:
    - "These should be topics you can consistently create content about for 90+ days"
 
 3. **Target audience:**
-   - "Who is your primary audience? (e.g., 'Public sector leaders exploring AI')"
+   - "Who is your primary audience? (e.g., 'CFOs at mid-size SaaS companies' or 'public-sector IT leaders')"
    - "Secondary audience?"
    - "Geographic focus?"