fix(plugins): sync all 171 plugin SKILL.md files with fixed skills/ versions

Propagates Anti-Patterns sections, description rewrites, Required Inputs
additions, and Quality Checks format fixes from skills/ to matching plugin
SKILL.md copies.

https://claude.ai/code/session_01MuGKn3a3Gbqoe8uM5Lmuqt

plugins/pm-social/skills/community-management-playbook/SKILL.md

@@ -300,6 +300,14 @@ Track these weekly:
 - [ ] Community health metrics have targets, not just labels
 - [ ] Platform-specific nuances are covered for every active channel
 
+## Anti-Patterns
+
+- [ ] Do not delete genuine customer complaints to silence negative feedback — deletion damages trust more than the original complaint and can escalate a minor issue to a viral one
+- [ ] Do not respond to competitor comparison comments publicly — engaging publicly with competitive comparisons amplifies them; redirect to DMs or ignore
+- [ ] Do not use the same template response for every complaint — copy-paste responses on visible complaints are noticed by other users and undermine brand authenticity
+- [ ] Do not leave a crisis without pausing scheduled content — queued posts published during an active brand crisis appear tone-deaf and make the situation worse
+- [ ] Do not set response time SLAs that cannot be met with the available team size — an SLA that is consistently missed is worse than no SLA
+
 ## Example Trigger Phrases
 
 - "Build a community management playbook for [brand]"

plugins/pm-social/skills/influencer-brief/SKILL.md

@@ -233,6 +233,14 @@ How we'll measure success:
 - [ ] Disclosure requirements are clearly stated (FTC / ASA compliance)
 - [ ] Important dates include a buffer for revisions
 
+## Anti-Patterns
+
+- [ ] Do not leave creative guidelines so restrictive that the influencer's authentic voice is lost — prescriptiveness kills performance
+- [ ] Do not omit the approval process — undefined approval workflows cause delays and missed publishing windows
+- [ ] Do not set performance metrics that the influencer cannot influence — views are a metric, algorithm reach is not
+- [ ] Do not skip the disclosure requirements section — FTC/ASA compliance is mandatory, not optional
+- [ ] Do not list deliverables without specifying format, dimensions, and platform specs
+
 ## Example Trigger Phrases
 
 - "Write an influencer brief for our product launch"

plugins/pm-social/skills/social-ad-campaign/SKILL.md

@@ -326,3 +326,11 @@ Run structured tests — change one variable at a time:
 - "Create a LinkedIn ad campaign for [B2B SaaS product]"
 - "Write TikTok ad copy for [consumer brand]"
 - "Structure a paid social funnel for [offer]"
+
+## Anti-Patterns
+
+- [ ] Do not combine multiple campaign objectives in one campaign — pick one measurable goal or the algorithm cannot optimise correctly
+- [ ] Do not skip retargeting suppression — existing customers receiving acquisition ads wastes budget and damages brand perception
+- [ ] Do not launch without completing the tracking setup checklist — campaigns without verified pixel firing cannot be optimised or attributed
+- [ ] Do not run A/B tests changing more than one variable at a time — multi-variable tests produce uninterpretable results
+- [ ] Do not allocate equal budget across TOFU, MOFU, and BOFU — BOFU audiences convert at higher rates and deserve proportionally more budget per conversion

plugins/pm-social/skills/social-media-audit/SKILL.md

@@ -225,3 +225,11 @@ The fastest way to improve the score by 10+ points:
 - "How are we doing on social compared to competitors?"
 - "What's working and what isn't on our social channels?"
 - "Give me a social media health check for [brand]"
+
+## Anti-Patterns
+
+- [ ] Do not score platforms against guesswork — every score must be based on actual metrics provided or observable data
+- [ ] Do not write recommendations as "post more content" or "improve engagement" — every action must be specific and measurable
+- [ ] Do not use competitor benchmarks that are not based on real data — fabricated benchmarks invalidate the competitive gap analysis
+- [ ] Do not audit content mix based on what should have been posted — analyse what was actually posted during the audit period
+- [ ] Do not sequence the action plan by effort alone — sequence by impact × effort so the highest-value actions come first

plugins/pm-social/skills/viral-content-framework/SKILL.md

@@ -388,6 +388,14 @@ Apply the hook formulas and content structures from above to these topic angles:
 - [ ] Testing system is set up — 48-hour signal tracked for every post
 - [ ] CTA asks for a specific action, not a generic "like and share"
 
+## Anti-Patterns
+
+- [ ] Do not create a single generic framework — hook formulas and content structures must be platform-specific
+- [ ] Do not confuse reach with virality — high reach alone is not viral; content must drive sharing, saves, or resharing
+- [ ] Do not produce hook formulas without testing guidance — frameworks without a testing system produce one-off results
+- [ ] Do not ignore the shareability trigger — all content must have a clear reason why someone would send it to another person
+- [ ] Do not design hooks that work only once — the framework must be repeatable, not a collection of one-time tactics
+
 ## Example Trigger Phrases
 
 - "Build a viral content framework for [brand / creator]"