chore: full sync of claude-forge skill files

.claude/skills/pipeline/flows/audit-flow.md

@@ -80,7 +80,7 @@ Evaluator and auditor agents are **token-expensive**. They run exactly twice in
 
 **NEVER** re-run evaluator or auditor agents at any point during the pipeline. The planner, implementer, and verification reviewer work from the intake docs and feedback.md.
 
-## Stage 1: Planning (Planner ↔ Plan Reviewer GAN Loop)
+## Stage 1: Planning (Planner ↔ Plan Reviewer Adversarial Loop)
 
 **Max iterations: 3.**
 
@@ -152,7 +152,7 @@ Standard plan review process — see main SKILL.md Stage 1b.
 
 Loop until `PLAN_APPROVED` or max iterations.
 
-## Stage 2: Implementation (Per-Phase GAN Loops)
+## Stage 2: Implementation (Per-Phase Adversarial Loops)
 
 **Max iterations per phase: 3.**
 

.claude/skills/pipeline/flows/doc-health-flow.md

@@ -68,7 +68,7 @@ Auditor agents are **token-expensive**. They run exactly twice in the full lifec
 
 **NEVER** re-run the doc auditor agent at any point during the pipeline. The planner, doc engineer, and verification reviewer work from doc-audit.md and feedback.md.
 
-## Stage 2: Planning (Planner ↔ Plan Reviewer GAN Loop)
+## Stage 2: Planning (Planner ↔ Plan Reviewer Adversarial Loop)
 
 **Max iterations: 3.**
 
@@ -113,7 +113,7 @@ Standard plan review process — see main SKILL.md Stage 1b.
 
 Loop until `PLAN_APPROVED` or max iterations.
 
-## Stage 3: Implementation (Per-Phase Doc Engineer ↔ Doc Reviewer GAN Loop)
+## Stage 3: Implementation (Per-Phase Doc Engineer ↔ Doc Reviewer Adversarial Loop)
 
 **Max iterations per phase: 3.**
 

.claude/skills/pipeline/flows/repo-eval-flow.md

@@ -104,7 +104,7 @@ Evaluator agents are **token-expensive**. They run exactly twice in the full lif
 
 **NEVER** re-run evaluator agents at any point during the pipeline. The planner, implementer, and verification reviewer work from eval.md and feedback.md.
 
-## Stage 2: Planning (Planner ↔ Plan Reviewer GAN Loop)
+## Stage 2: Planning (Planner ↔ Plan Reviewer Adversarial Loop)
 
 **Max iterations: 3.**
 
@@ -148,7 +148,7 @@ Standard plan review process — see main SKILL.md Stage 1b.
 
 Loop until `PLAN_APPROVED` or max iterations.
 
-## Stage 3: Implementation (Per-Phase Implementer ↔ Reviewer GAN Loop)
+## Stage 3: Implementation (Per-Phase Implementer ↔ Reviewer Adversarial Loop)
 
 **Max iterations per phase: 3.**
 

.claude/skills/pipeline/flows/repo-health-flow.md

@@ -68,7 +68,7 @@ Auditor agents are **token-expensive**. They run exactly twice in the full lifec
 
 **NEVER** re-run the auditor agent at any point during the pipeline. The planner, implementer, and verification reviewer work from health-audit.md and feedback.md.
 
-## Stage 2: Planning (Planner ↔ Plan Reviewer GAN Loop)
+## Stage 2: Planning (Planner ↔ Plan Reviewer Adversarial Loop)
 
 **Max iterations: 3.**
 
@@ -114,7 +114,7 @@ Standard plan review process — see main SKILL.md Stage 1b.
 
 Loop until `PLAN_APPROVED` or max iterations.
 
-## Stage 3: Implementation (Per-Phase GAN Loops)
+## Stage 3: Implementation (Per-Phase Adversarial Loops)
 
 **Max iterations per phase: 3.**