feat(cron-recipes): /cron-recipe <name> seeds a conversational fill

Reworks the chat-line UX: pick a recipe by name and the agent asks you for
what it needs, one question at a time, instead of forcing you to hand-type a
slot=val command line.

- /cron-recipe                  -> lists the catalog
- /cron-recipe <name>           -> forgiving name match (exact/prefix/substring/
                                   fuzzy; ambiguous lists candidates), then seeds
                                   the agent with a natural-language fill request
                                   built from the recipe's typed slots + schedule
                                   and prompt templates. The agent asks for each
                                   value one at a time and calls the EXISTING
                                   cronjob tool. No new tool.
- /cron-recipe <name> slot=val  -> unchanged deterministic path (fill_recipe ->
                                   create_job) for the dashboard/docs/power user.

Mechanism (no new plumbing, invariant-safe — the seed enters as a normal user
turn, never a synthetic injection):
- shared handler returns RecipeCommandResult{text, agent_seed}; match_recipe()
  and build_recipe_seed() are the new shared pieces.
- gateway: dispatch rewrites event.text to the seed and falls through to the
  agent (the same pattern /steer uses).
- CLI: handler sets a one-shot self._pending_agent_seed; the interactive loop
  consumes it right after process_command() and runs it as the next turn.

The typed-slot schema stays the single source of truth (still validates the
form/inline path via fill_recipe); the agent path just renders those slots into
the questions to ask. Docs updated to lead with the name-then-ask flow.

cron/scripts/classify_items.py

@@ -5,8 +5,8 @@ The proactive-monitor pattern: a fetch step (a watcher script, an inbox dump, a
 feed) produces a list of candidate items; this script scores each with a cheap
 LLM and prints ONLY the items at or above a threshold. Below-threshold runs
 print nothing, so a cron job wrapping this stays silent unless something
-actually matters -- mirroring Poke's email monitor (fetch -> classify urgency
--> surface only what's above the bar).
+actually matters -- the classic urgency-monitor pattern (fetch -> classify
+urgency -> surface only what's above the bar).
 
 Design choices:
   * Uses Hermes' auxiliary client with task="monitor", so the classifier model