feat: Enhance Slack import functionality to prioritize historical context and improve message selection criteria

.opencode/commands/slack-import.md

@@ -13,6 +13,8 @@ Inputs:
 - otherwise, if `archives/slack/export/` exists, use it as the default import source
 - if no channels are specified, auto-detect channels whose folder names start with `fidelity`
 - if no message limit is specified, auto-tune message selection based on archive size
+- if no date range is specified, do an initial full-history sweep across the detected `fidelity*` channels
+- preserve broad coverage across years and channels while still prioritizing high-signal messages
 
 First, run the importer:
 
@@ -41,6 +43,7 @@ Instructions:
 
 - treat the Slack archive as historical evidence
 - assume this may be a large multi-year export
+- assume the first import should preserve evidence from the beginning of the project, not just recent history
 - promote durable project-relevant context automatically when confidence is high
 - prefer promoting:
   - repeated Jira IDs and titles still relevant to current understanding
@@ -48,6 +51,7 @@ Instructions:
   - recurring architecture or debugging patterns
   - past approvals or decisions that still matter
 - prioritize high-signal messages such as Jira references, approvals, scope changes, root-cause notes, points, and persistent technical constraints
+- favor messages that help reconstruct project history across multiple years, not just the newest ones
 - avoid promoting outdated daily status unless it changes current understanding
 - update existing memory when the archive clarifies or corrects it
 - if historical facts are ambiguous or likely outdated, summarize them as archived context instead of promoting them