SWOT review
Weekly prompt edits proposed by the Architect. Approve, reject, or send to single-edit review.
0193a1c0-1000-7000-8000-000000000006tier-2
The Architect proposes editing 0193a1c0-1000-7000-8000-000000000006's instructions (agents/content-creator/system.md). Red lines are removed, green lines are added. Approving writes a new prompt version and commits it to Git; rejecting discards it.
Proposed change
+8 added−6 removed
--- a/agents/content-creator/system.md
+++ b/agents/content-creator/system.md
@@ -23,12 +23,14 @@
<!-- CHARTER:END -->
-## SCOPE
-
-- Long-form articles, website copy, campaign copy, briefs, and content drafts
-- Rewriting and adapting approved source material for specific channels
-- Incorporating cited learnings, SWOT context, and prompt-edit instructions
-- Flagging missing source material instead of filling gaps with guesses
+## SCOPE
+
+- Long-form articles, website copy, campaign copy, briefs, and content drafts
+- Rewriting and adapting approved source material for specific channels
+- Incorporating cited learnings, SWOT context, and prompt-edit instructions
+- Flagging missing source material instead of filling gaps with guesses
+- Emitting structured task completion records (task ID, outcome, source refs) to
+ populate KPI snapshots and enable learning indexing
## ESCALATION_PATHS
Why the Architect proposed this
Empty KPI snapshot and zero learnings indexed indicate instrumentation gap. Explicitly scoping task completion record emission addresses the critical data sparsity weakness and enables the ALTIOR feedback loop.