fix(validate): check for [agents] instead of [agent] in HAND.toml (#15)

* fix(validate): check for [agents] instead of [agent] in HAND.toml

All 14 hands use [agents.main] (plural) for multi-agent config,
but the validator was checking for [agent] (singular), causing
all hands to fail validation.

* fix(routing): resolve 19 routing alias collisions

Agent is a sub-unit of hand, so hands take priority for routing.
Remove conflicting aliases from agent side when hand already owns them.

- analyst: remove data analysis, analyze data, dashboard (owned by hand/analytics)
- data-scientist: remove statistical analysis, forecast, prediction (owned by hand/analytics, hand/predictor)
- sales-assistant: remove prospecting, sales, pipeline (owned by hand/lead, hand/devops)
- devops-lead: remove incident response, kubernetes, terraform (owned by hand/devops)
- researcher: remove deep research, research, literature review (owned by hand/researcher)
- academic-researcher: remove literature review, systematic review (owned by hand/researcher)
- social-media: remove duplicate content calendar from weak_aliases
- hand/collector: remove competitive analysis (owned by hand/strategist)

agents/academic-researcher/agent.toml

@@ -8,7 +8,6 @@ tags = ["research", "academic", "papers", "literature-review", "science"]
 [metadata.routing]
 aliases = [
   "academic research",
-  "literature review",
   "paper search",
   "scholarly research",
   "find papers",
@@ -17,7 +16,6 @@ weak_aliases = [
   "papers",
   "citations",
   "bibliography",
-  "systematic review",
   "meta-analysis",
 ]
 

agents/analyst/agent.toml

@@ -6,13 +6,11 @@ module = "builtin:chat"
 
 [metadata.routing]
 aliases = [
-  "data analysis",
-  "analyze data",
   "analytics",
   "metrics analysis",
   "report analysis",
 ]
-weak_aliases = ["dashboard", "kpi", "insights", "reporting"]
+weak_aliases = ["kpi", "insights", "reporting"]
 
 [model]
 provider = "default"

agents/data-scientist/agent.toml

@@ -9,10 +9,9 @@ aliases = [
   "data science",
   "build model",
   "train model",
-  "statistical analysis",
   "machine learning",
 ]
-weak_aliases = ["modeling", "forecast", "prediction", "statistics"]
+weak_aliases = ["modeling", "statistics"]
 
 [model]
 provider = "default"

agents/devops-lead/agent.toml

@@ -9,10 +9,9 @@ aliases = [
   "ci cd",
   "deployment pipeline",
   "infrastructure ops",
-  "incident response",
   "production operations",
 ]
-weak_aliases = ["devops", "deployment", "kubernetes", "terraform", "infra"]
+weak_aliases = ["devops", "deployment", "infra"]
 
 [model]
 provider = "default"

agents/researcher/agent.toml

@@ -7,13 +7,12 @@ tags = ["research", "analysis", "web"]
 
 [metadata.routing]
 aliases = [
-  "deep research",
   "web research",
   "investigate topic",
   "gather sources",
   "fact finding",
 ]
-weak_aliases = ["research", "sources", "literature review", "web search"]
+weak_aliases = ["sources", "web search"]
 
 [model]
 provider = "default"

agents/sales-assistant/agent.toml

@@ -9,11 +9,10 @@ tags = ["sales", "crm", "outreach", "pipeline", "prospecting", "deals"]
 aliases = [
   "sales outreach",
   "crm update",
-  "prospecting",
   "pipeline review",
   "deal tracking",
 ]
-weak_aliases = ["sales", "crm", "pipeline", "leads"]
+weak_aliases = ["crm", "leads"]
 
 [model]
 provider = "default"

agents/social-media/agent.toml

@@ -20,7 +20,7 @@ aliases = [
   "engagement strategy",
   "social campaign",
 ]
-weak_aliases = ["social media", "content calendar", "engagement", "campaign"]
+weak_aliases = ["social media", "engagement", "campaign"]
 
 [model]
 provider = "default"