fix: rename generate to stories to avoid autocomplete issues

skills/init/SKILL.md

@@ -29,7 +29,7 @@ bash "$(ls -d ~/.claude/plugins/cache/agent-loop/agent-loop/*/setup.sh 2>/dev/nu
 
 > `.loop/` is ready. Next:
 > ```
-> /agent-loop:generate
+> /agent-loop:stories
 > ```
 
 **That's it. Do not do anything else. Do not read specs. Do not plan. Do not write code.**

skills/run/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: run
-description: Execute the generator-evaluator loop interactively inside Claude Code. Dispatches subagents with full visibility. Run /agent-loop:init and /agent-loop:generate first.
+description: Execute the generator-evaluator loop interactively inside Claude Code. Dispatches subagents with full visibility. Run /agent-loop:init and /agent-loop:stories first.
 ---
 
 # /run — Execute Agent Loop Inside Claude Code
@@ -23,7 +23,7 @@ Follow this orchestration sequence exactly.
 ### Step 0: Validate Prerequisites
 
 1. Check `.loop/config.json` exists. If not: tell user to run `/agent-loop:init` and stop.
-2. Check `.loop/prd.json` exists. If not: tell user to run `/agent-loop:generate` and stop.
+2. Check `.loop/prd.json` exists. If not: tell user to run `/agent-loop:stories` and stop.
 3. **Validate prd.json schema.** Read the file and verify:
    - Has a `userStories` array (NOT `sprints`, `stories`, or `tasks`)
    - Each story has: `id`, `title`, `passes`, `priority`

skills/stories/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: generate
+name: stories
 description: "Generate prd.json and sprint contracts by dispatching the planner agent. Does not write source code."
 ---